P

Posthog技能

ego lite browser

ego lite 是 AI 代理執行網頁自動化最快的瀏覽器，可與 Codex 或 Claude Code 共享您的登入狀態，零成本、零配置。

Alpha Vantage MCP Server

獲取金融市場數據：即時與歷史股票、ETF、期權、外匯、加密貨幣、大宗商品、基本面、技術指標等

account-handover

Draft structured handover notes for transitioning a PostHog account from one TAM or CSM to another. Use this skill when a TAM needs to hand over an account,…

account-handover

為將 PostHog 帳戶從一位技術客戶經理或客戶成功經理交接給另一位，草擬結構化的交接備忘錄。當技術客戶經理需要交接帳戶時，使用此技能…

為 posthog-definitions 新增支援新的 PostHog 資源類型（功能旗標、群組、動作、調查、註解、警示……）。逐步說明八個檔案……

Add support for a new PostHog resource type (feature flag, cohort, action, survey, annotation, alert, …) to posthog-definitions. Walks through the eight files…

adding-framework-support

Add a new framework integration to the PostHog wizard. Use when adding support for a new language or framework (e.g. Ruby on Rails, Go, Angular). Covers…

adding-inbox-sources

Add a new warehouse-backed source to the PostHog Desktop Self-driving Inbox (the feature that ships GitHub, Linear, Zendesk, pganalyze, Jira). A source syncs…

adding-ingestion-warnings

如何在事件攝取管線中新增一種攝取警告類型。用於從 Node.js 攝取程式碼（emitIngestionWarning,…）發出新警告時。

adding-mcp-store-servers

Add a third-party MCP server (Linear, Notion, GitHub, ...) to the PostHog MCP store catalog. Use when asked to "add X to the MCP store", expand the MCP server…

adding-personhog-rpc

在 personhog-replica 和 personhog-router 中新增 RPC 的指南。涵蓋資格檢查、proto 定義、Python 與 Node.js 的程式碼生成…

adding-personhog-rpc

在 personhog-replica 和 personhog-router 中新增 RPC 的指南。涵蓋資格檢查、proto 定義、Python 與 Node.js 的程式碼生成…

adding-personhog-rpc

Guide for adding a new RPC to personhog-replica and personhog-router. Covers eligibility checks, proto definition, code generation for Python and Node.js…

adding-personhog-rpc

Guide for adding a new RPC to personhog-replica and personhog-router. Covers eligibility checks, proto definition, code generation for Python and Node.js…

adding-product-alerting

Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform. Routes lifecycle state machines,…

adding-project-secret-api-key-auth

如何用專案密鑰 API 金鑰（PSAK）驗證來保護 PostHog API 端點——這是一種專案範圍內、無使用者的服務憑證。在為某個功能添加 PSAK 支援時使用…

adding-project-secret-api-key-auth

How to gate a PostHog API endpoint with project secret API key (PSAK) auth — a project-scoped, user-less service credential. Use when adding PSAK support to a…

adding-project-secret-api-key-auth

How to gate a PostHog API endpoint with project secret API key (PSAK) auth — a project-scoped, user-less service credential. Use when adding PSAK support to a…

adding-project-secret-api-key-auth

如何用專案密鑰 API 金鑰（PSAK）驗證來保護 PostHog API 端點——這是一種專案範圍內、無使用者的服務憑證。在為…添加 PSAK 支援時使用。

adding-skill-program

Create a new skill-based program for the PostHog wizard. Use when adding a program type (like revenue analytics, audit, error tracking) that installs a…

adopting-generated-api-types

Use when migrating frontend code from manual API client calls (`api.get`, `api.create`, `api.surveys.get`, `api.dashboards.list`, `new ApiRequest()`) and…

adopting-generated-api-types

用於從手動 API 客戶

adopting-generated-api-types

Use when migrating frontend code from manual API client calls (`api.get`, `api.create`, `api.surveys.get`, `api.dashboards.list`, `new ApiRequest()`) and…

adopting-generated-api-types

Use when migrating frontend code from manual API client calls (`api.get`, `api.create`, `api.surveys.get`, `api.dashboards.list`, `new ApiRequest()`) and…

analysing-exported-session-recordings

Decode and analyse a downloaded session-recording export zip (the `data/` blocks plus ClickHouse metadata) to understand what is making a recording large or…

analyzing-expensive-users

分析AI可觀測性中最昂貴的使用者，並解釋其成本高昂的原因。當使用者詢問關於頂級花費者、高成本使用者、每位使用者等問題時使用。

analyzing-experiment-query-performance

Pull and interpret production experiment query-performance data from the staff-only `/api/debug_ch_queries` endpoints backing the `/instance/query_performance`…

analyzing-experiment-session-replays

分析實驗變體中的會話重播模式，以了解使用者行為差異。當使用者想了解使用者如何與……互動時使用。

analyzing-experiment-session-replays

Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with…

analyzing-experiment-session-replays

Analyze session replay patterns across experiment variants to understand user behavior differences. Use when the user wants to see how users interact with…

analyzing-experiment-session-replays

分析實驗變體中的會話重播模式，以了解使用者行為差異。當使用者想了解使用者如何與……互動時使用。

analyzing-experiment-session-replays

分析實驗變體中的會話重播模式，以了解使用者行為差異。當使用者想了解使用者如何與……互動時使用。

analyzing-insights-across-teams

Analyze PostHog insights, dashboards, or teams beyond the current project by querying the prod Postgres replicas synced into the dogfood data warehouse (US…

assessing-heatmaps

評估頁面熱圖所傳達的資訊，並建議具體的變更。擷取某個網址的點擊、憤怒點擊、滾動深度數據，並標出熱門元素的名稱…

assessing-heatmaps

Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by…

assessing-heatmaps

Assesses what a page's heatmap is telling you and recommends concrete changes. Pulls click / rageclick / scroll-depth data for a URL, names the hot elements by…

assessing-heatmaps

評估頁面熱圖所傳達的資訊，並建議具體的變更。擷取某個網址的點擊、憤怒點擊、滾動深度數據，並標出熱門元素的名稱…

assessing-heatmaps

評估頁面熱圖所傳達的資訊，並建議具體的變更。擷取某個網址的點擊、憤怒點擊、滾動深度數據，並標出名稱中的熱門元素…

auditing-endpoints

審計 PostHog 專案中的每個端點，檢查是否有過時、失敗的具體化，以及未使用的具體化版本。當使用者詢問「哪些端點可以…」時使用。

auditing-endpoints

Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can…

auditing-endpoints

Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can…

auditing-endpoints

審計 PostHog 專案中的每個端點，檢查是否有過時、失敗的具體化，以及未使用的具體化版本。當使用者詢問「哪些端點可以…」時使用。

auditing-endpoints

審計 PostHog 專案中的每個端點，檢查是否有過時、失敗的具體化，以及未使用的具體化版本。當使用者詢問「哪些端點可以…」時使用。

auditing-experiments-flags

稽核 PostHog 實驗與功能開關的設定問題、過時狀態及最佳實務違規。當使用者要求稽核、健康檢查…時讀取。

auditing-experiments-flags

auditing-experiments-flags

稽核 PostHog 實驗與功能旗標的配置問題、過時狀態及最佳實務違規。當使用者要求稽核、健康檢查…時讀取。

auditing-llm-gateway-parity

Audits services/llm-gateway against PostHog/ai-gateway and updates services/llm-gateway/PARITY.md from current implementation evidence. Use when either gateway…

auditing-the-fleet

The fleet-wide audit — sweep every agent, mine recent sessions for failures/anomalies, classify root causes, and branch a DRAFT proposal per fix (never…

auditing-the-fleet

全艦隊審計——掃描所有代理，挖掘近期會話中的失敗/異常，分類根本原因，並為每個修復方案建立草稿提案（從不……

auditing-warehouse-data-health

此技能可對資料倉儲管線進行全專案稽核。當使用者需要了解所有異常的總覽，而非深入探討單一同步時，請使用此技能。深入分析個別失敗的同步屬於 diagnosing-failed-warehouse-syncs 的範疇；此技能則是用於掃描並告知使用者應優先檢查何處。

auditing-warehouse-data-health

此技能會產生專案層級的資料倉儲管線稽核。當使用者想要了解所有異常項目的摘要，而非深入探討單一同步時，請使用此技能。深入分析個別失敗的項目屬於 diagnosing-failed-warehouse-syncs 技能；此技能則是提供掃描結果，指引使用者優先檢查的方向。

auditing-warehouse-data-health

此技能會對資料倉儲管線進行專案層級的稽核。當使用者想要取得所有異常項目的摘要，而非深入探討單一同步時，請使用此技能。深入探討個別失敗的項目是「diagnosing-failed-warehouse-syncs」；此技能則是掃描，告訴他們應優先查看何處。

auditing-warehouse-data-health

Audit the health of a PostHog project's data warehouse — find every broken or degraded pipeline item across sources, sync schemas, materialized views, batch…

auditing-warehouse-source-coverage

Audit already-implemented Data warehouse import sources for endpoints, schemas, and tables the vendor's API offers but we never wired up. Use when asked…

auditing-warehouse-source-health

審核 PostHog 專案資料倉儲來源與同步的健康狀態——找出所有損壞或降級的來源連線、同步結構與 Webhook 頻道。

auditing-warehouse-source-health

審核 PostHog 專案資料倉儲來源與同步的健康狀態——找出所有損壞或降級的來源連線、同步結構與 Webhook 頻道。

auditing-warehouse-source-health

Audit the health of a PostHog project's data warehouse sources and syncs — find every broken or degraded source connection, sync schema, and webhook channel.…

auditing-warehouse-view-health

稽核 PostHog 專案具體化檢視（已儲存查詢）的健康狀態——找出所有失敗的具體化作業，並標記未使用或過時的具體化檢視，這些檢視…

auditing-warehouse-view-health

Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that…

auditing-warehouse-view-health

Audit the health of a PostHog project's materialized views (saved queries) — find every failed materialization and flag unused or stale materialized views that…

author-stepwise-skill

建立一個新的 context-mill 技能，引導代理依序處理一系列範圍狹窄的參考檔案。適用於任意數量的步驟。當需要…

author-stepwise-skill

Scaffold a new context-mill skill that walks an agent through an ordered series of narrowly-scoped reference files. Works for any number of steps. Use when the…

authoring-ci-workflows

Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under `.github/` — new CI jobs, triggers, matrices, checkout/clone…

authoring-ci-workflows

Use when adding or editing a GitHub Actions workflow, composite action, or reusable workflow under `.github/` — new CI jobs, triggers, matrices, checkout/clone…

authoring-error-tracking-alerts

當問題被建立、重新開啟或開始激增時觸發的作者錯誤追蹤警示。當使用者要求設定錯誤通知、路由…時使用。

authoring-error-tracking-alerts

Author error tracking alerts that fire when an issue is created, reopened, or starts spiking. Use when the user asks to set up error notifications, route…

authoring-error-tracking-alerts

當問題被建立、重新開啟或開始激增時觸發的作者錯誤追蹤警示。當使用者要求設定錯誤通知、路由…時使用。

authoring-log-alerts

撰寫警示是一個測量問題，而非猜測問題。你的目標不是窮舉所有可能性，而是針對實際生產環境中重要的服務，設定每週觸發0到3次的閾值。

authoring-log-alerts

在 PostHog 專案中為服務撰寫實用且低雜訊的日誌警示。當使用者要求為其日誌設定警示，或建議應新增的警示時使用。

authoring-log-alerts

Author useful, low-noise log alerts on services in a PostHog project. Use when the user asks to set up alerts for their logs, suggest alerts they should add,…

authoring-log-alerts

Author useful, low-noise log alerts on services in a PostHog project. Use when the user asks to set up alerts for their logs, suggest alerts they should add,…

authoring-log-alerts

在 PostHog 專案中為服務撰寫實用且低雜訊的日誌警示。當使用者要求設定日誌警示或建議應新增的警示時使用。

authoring-scouts

如何撰寫、編輯及調整 PostHog Signals scouts——這些排程代理會掃描專案並將報告寫入 Signals 收件匣。當使用者……時使用。

authoring-scouts

How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user…

authoring-scouts

如何撰寫、編輯及調整 PostHog Signals scouts——這些排程代理會掃描專案並將報告寫入 Signals 收件匣。當使用者……時使用。

authoring-signals-scouts

如何撰寫、編輯及調整 PostHog Signals scouts——這些排程代理程式會掃描專案並將發現結果發送至 Signals 收件匣。當使用者…

authoring-signals-scouts

How to author, edit, and adapt PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user…

authoring-signals-scouts

如何撰寫、編輯及調整 PostHog Signals scouts——這些排程代理程式會掃描專案並將發現結果發送至 Signals 收件匣。當使用者…

autoresolving-pr-conflicts

Operating procedure for the conflict-autoresolver agent: sweep open PostHog/posthog PRs that conflict with master, resolve the trivial conflicts (generated…

building-a-dashboard

Build a new dashboard, or update an existing one, from a set of insights — the same job the in-app assistant does with its upsert-dashboard tool, but over MCP.…

building-product-empty-states

Guide for adding a product setup empty state — the skippable first-run screen a product scene shows until real data arrives, built on the shared…

building-workflows

在 MCP 上建置、編輯、測試、啟用並監控 PostHog 工作流程。編寫動作/邊緣圖表，使其能順利執行並在視覺化編輯器中乾淨開啟，然後變更…

building-workflows

在 MCP 上建置、編輯、測試、啟用並監控 PostHog 工作流程。編寫動作/邊緣圖表，使其能順利執行並在視覺編輯器中乾淨開啟，然後變更…

check-posthog-loading

Inspect how the PostHog JavaScript SDK is loaded across a list of URLs. Use to confirm consistent installation across pages, find pages missing the snippet,…

check-posthog-loading

檢查 PostHog JavaScript SDK 在一系列 URL 中的載入情況。用於確認跨頁面的一致安裝，找出缺少程式碼片段的頁面，…

checking-deploy-timing

判斷 PostHog 程式碼變更何時到達指定環境，方法是讀取專案中隱藏的 GIT 部署註解，並將其與…

checking-deploy-timing

Determine when a PostHog code change reached a given environment by reading the hidden GIT deploy annotations in the project and correlating them with the…

checking-deploy-timing

判斷 PostHog 程式碼變更何時到達指定環境，方法是讀取專案中隱藏的 GIT 部署註解，並將其與…

choosing-trend-or-slope-view

在建立趨勢之前，先釐清如何視覺化一段時間內的變化。每當使用者詢問某事物變化了多少、成長、下降、改善或……時使用。

choosing-trend-or-slope-view

Clarify how to visualize change over a time range before building a trend. Use whenever the user asks how much something changed, grew, dropped, improved, or…

choosing-trend-or-slope-view

在建立趨勢之前，先釐清如何視覺化一段時間範圍內的變化。每當使用者詢問某事物變化了多少、成長、下降、改善或……時使用。

cleaning-up-stale-feature-flags

識別並清理 PostHog 專案中過時的 feature flags。當使用者想要找出未使用、已全面推出或已棄用的 feature flags，並進行檢視…

cleaning-up-stale-feature-flags

Identify and clean up stale feature flags in a PostHog project. Use when the user wants to find unused, fully rolled out, or abandoned feature flags, review…

cleaning-up-stale-feature-flags

Identify and clean up stale feature flags in a PostHog project. Use when the user wants to find unused, fully rolled out, or abandoned feature flags, review…

cleaning-up-stale-feature-flags

識別並清理 PostHog 專案中過時的 feature flags。當使用者想找出未使用、已全面推出或已廢棄的 feature flags，檢視…

cleaning-up-stale-feature-flags

識別並清理 PostHog 專案中過時的 feature flags。當使用者想要找出未使用、已全面推出或已廢棄的 feature flags 時使用，檢視…

clickhouse-migrations

ClickHouse 遷移模式與規則。用於建立或修改 ClickHouse 遷移時使用。

clickhouse-migrations

ClickHouse migration patterns and rules. Use when creating or modifying ClickHouse migrations.

clickhouse-migrations

ClickHouse migration patterns and rules. Use when creating or modifying ClickHouse migrations.

clickhouse-migrations

ClickHouse 遷移模式與規則。在建立或修改 ClickHouse 遷移時使用。

competitor-data-verifier

透過使用WebFetch/WebSearch抓取競爭對手網站，驗證並更新競爭對手產品資料。當使用者要求驗證、檢查或更新…時使用。

competitor-data-verifier

Verify and update competitor product data by scraping competitor websites using WebFetch/WebSearch. Use when the user asks to verify, check, or update…

configuring-experiment-analytics

Configures the analytics side of a PostHog experiment — exposure criteria (default `$feature_flag_called` vs custom exposure events), primary and secondary…

configuring-experiment-analytics

引導實驗分析配置：曝光條件、指標類型、指標設定及結果解讀。涵蓋分析中包含的對象、如何…

configuring-experiment-analytics

configuring-experiment-analytics

Configures the analytics side of a PostHog experiment — exposure criteria (default `$feature_flag_called` vs custom exposure events), primary and secondary…

configuring-experiment-analytics

Configures the analytics side of a PostHog experiment — exposure criteria (default `$feature_flag_called` vs custom exposure events), primary and secondary…

configuring-experiment-rollout

設定 PostHog 實驗的推出形狀——變體分配（50/50、80/20、A/B/C 比例），以及控制多少用戶能參與的整體推出百分比……

configuring-experiment-rollout

Configures the rollout shape of a PostHog experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that gates how many users…

configuring-experiment-rollout

Configures the rollout shape of a PostHog experiment — the variant split (50/50, 80/20, A/B/C ratios), the overall rollout percentage that gates how many users…

configuring-experiment-rollout

引導實驗的推出配置：變體拆分、整體推出百分比，以及當用戶提及特定…時的關鍵消歧

configuring-experiment-rollout

設定 PostHog 實驗的推出形狀——變體分配（50/50、80/20、A/B/C 比例）、控制多少用戶的整體推出百分比……

consuming-endpoints-from-client-code

將 PostHog 端點接入客戶端應用程式或 SDK。涵蓋擷取 OpenAPI 規格、使用 openapi-generator 或 @hey-api/openapi-ts 生成型別化客戶端…

consuming-endpoints-from-client-code

Wire a PostHog endpoint into a client app or SDK. Covers fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api/openapi-ts,…

consuming-endpoints-from-client-code

Wire a PostHog endpoint into a client app or SDK. Covers fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api/openapi-ts,…

consuming-endpoints-from-client-code

將 PostHog 端點接入客戶端應用程式或 SDK。涵蓋擷取 OpenAPI 規格、使用 openapi-generator 或 @hey-api/openapi-ts 生成型別化客戶端…

consuming-endpoints-from-client-code

將 PostHog 端點接入客戶端應用程式或 SDK。涵蓋擷取 OpenAPI 規格、使用 openapi-generator 或 @hey-api/openapi-ts 生成型別化客戶端…

copying-endpoints-across-projects

Copy a PostHog endpoint (a saved HogQL/insight query exposed as an API route) to another project in the same organization, or duplicate it under a new name in…

copying-flags-across-projects

將一個功能標誌從同一個組織中的一個 PostHog 專案複製到一個或多個目標專案。當使用者想要複製標誌、推廣…時使用。

copying-flags-across-projects

Copy a feature flag from one PostHog project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote a…

copying-flags-across-projects

Copy a feature flag from one PostHog project to one or more target projects in the same organization. Use when the user wants to duplicate a flag, promote a…

copying-flags-across-projects

將一個功能標誌從同一個組織中的一個PostHog專案複製到一個或多個目標專案。當使用者想要複製標誌、推廣…時使用。

copying-flags-across-projects

將一個功能標誌從同一個組織中的一個 PostHog 專案複製到一個或多個目標專案。當使用者想要複製標誌、推廣…時使用。

creating-ai-subscription

建立一個定期執行的 AI 生成 PostHog 報告 — 排程一個自由文字提示以 cron 方式執行，並將 LLM 合成的 Markdown 透過電子郵件或 Slack 傳送…

creating-ai-subscription

Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email or Slack on…

creating-ai-subscription

Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email or Slack on…

creating-ai-subscription

建立一個定期執行的 AI 生成 PostHog 報告 — 排程一個自由文字提示以 cron 方式執行，並將 LLM 合成的 markdown 傳送到電子郵件或 Slack 上…

creating-ai-subscription

建立一個定期執行的 AI 生成 PostHog 報告 — 排程一個自由文字提示以 cron 方式執行，並將 LLM 合成的 Markdown 透過電子郵件或 Slack 傳送…

creating-an-endpoint

首次嘗試就建立出形狀正確的 PostHog 端點 — 涵蓋查詢類型選擇、命名慣例、應作為變數暴露的內容（HogQL code_name 與…）

creating-an-endpoint

Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name vs…

creating-an-endpoint

Create a PostHog endpoint with the right shape on the first try — covers query kind choice, name conventions, what to expose as variables (HogQL code_name vs…

creating-an-endpoint

首次嘗試就建立形狀正確的 PostHog 端點 — 涵蓋查詢類型選擇、命名慣例、應作為變數暴露的內容（HogQL code_name 與…）

creating-an-endpoint

首次嘗試就建立出形狀正確的 PostHog 端點 — 涵蓋查詢類型選擇、命名慣例、應暴露為變數的內容（HogQL code_name 與…）

creating-experiments

引導代理完成三步實驗創建流程：定義假設、配置推出、設置分析。委派推出決策…

creating-experiments

Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions…

creating-experiments

Guides agents through the 3-step experiment creation flow: defining the hypothesis, configuring rollout, and setting up analytics. Delegates rollout decisions…

creating-experiments

引導代理完成三步驟的實驗建立流程：定義假設、設定逐步推出機制，以及配置分析工具。將逐步推出決策委派…

creating-experiments

引導代理完成三步驟的實驗建立流程：定義假設、設定逐步推出機制，以及配置分析工具。委派逐步推出的決策…

creating-online-evaluations

在 PostHog AI 可觀測性中持續運行線上評估，基於你已識別的實際故障模式。當使用者想要…時使用。

creating-online-evaluations

在 PostHog AI 可觀測性中持續運行線上評估，基於你已識別的實際故障模式。當使用者想要…時使用。

creating-online-evaluations

Author continuously-running online evaluations in PostHog AI observability, grounded in a real failure mode you've identified. Use when the user wants an…

creating-replay-vision-scanners

引導代理人建立並安全調整 Replay Vision 掃描器：選擇掃描器類型（監控器/分類器/評分器/摘要器）、塑造…

creating-replay-vision-scanners

Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the…

creating-replay-vision-scanners

Guides agents through creating and safely sizing a Replay Vision scanner: choosing the scanner type (monitor/classifier/scorer/summarizer), shaping the…

creating-replay-vision-scanners

引導代理建立並安全調整 Replay Vision 掃描器：選擇掃描器類型（監控器/分類器/評分器/摘要器）、塑造…

creating-replay-vision-scanners

引導代理建立並安全調整 Replay Vision 掃描器：選擇掃描器類型（監控器/分類器/評分器/摘要器）、塑造…

dashboard-widgets

引導 PostHog 工程師在儲存庫中進行儀表板小工具平台相關工作 — 推出新的 widget_type（WIDGET_REGISTRY、catalog、run_widgets、WidgetCard）或…

debugging-ci-failures

偵錯 PostHog 的 Pull Request、提交和分支中失敗的 GitHub Actions CI 執行，並回答廣泛的 CI 健康狀況問題（例如「CI 是紅燈嗎？」、「今天 master 是綠燈嗎？」……）

debugging-ci-failures

Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?",…

debugging-ci-failures

Debugs failing GitHub Actions CI runs for PostHog PRs, commits, and branches, and answers broad CI-health questions ("is CI red?", "is master green today?",…

debugging-ci-failures

找出第一個有意義的失敗，對其進行分類，在適當情況下於本地重現最小可用案例，並報告結果。除非使用者明確要求，否則避免公開可見或不可逆的操作。

debugging-local-replay

當開發者說「本地重播無法運作」或「錄影沒有顯示」時，請依序檢查以下層級。本地重播管線包含多個動態環節，且失敗通常不會有提示。

debugging-local-replay

當開發者說「本地回放無法運作」或「錄影沒有顯示」時，請依序檢查以下層級。本地回放管線包含多個活動部件，且故障通常不會有提示。

debugging-local-replay

Debugs why session recordings aren't appearing in the local dev environment. Use when a developer reports that local replay ingestion isn't working, recordings…

debugging-local-replay

Debugs why session recordings aren't appearing in the local dev environment. Use when a developer reports that local replay ingestion isn't working, recordings…

debugging-local-replay

調試為何工作階段錄製內容未顯示在本機開發環境中。當開發人員回報本機重播攝取功能無法運作、錄製內容…時使用。

debugging-local-task-agent-runs

Debug the output of local PostHog task runs — the wizard cloud-run path that executes inside a Docker sandbox under the local Temporal `process-task` workflow…

debugging-signals-pipeline

在本機端對端偵錯訊號管線。涵蓋從測試固定裝置發射測試訊號、透過 REST API 監控 Temporal 工作流程、讀取沙箱…

debugging-signals-pipeline

在本機端對端偵錯訊號管線。涵蓋從測試固定裝置發射測試訊號、透過 REST API 監控 Temporal 工作流程、讀取沙盒…

debugging-signals-pipeline

Debug the signals pipeline locally end-to-end. Covers emitting test signals from fixtures, monitoring Temporal workflows via the REST API, reading sandbox…

debugging-signals-pipeline

Debug the signals pipeline locally end-to-end. Covers emitting test signals from fixtures, monitoring Temporal workflows via the REST API, reading sandbox…

debugging-signals-pipeline

在本機端到端除錯訊號管線。涵蓋從測試固定裝置發射測試訊號、透過 REST API 監控 Temporal 工作流程、讀取沙箱…

debugging-surveys

在後端及所有五個SDK（web/posthog-js、iOS、Android、Flutter、React Native）中除錯、支援及建構PostHog Surveys。每當需要處理Surveys相關問題時使用。

debugging-surveys

在後端及所有五個SDK（web/posthog-js、iOS、Android、Flutter、React Native）中除錯、支援及建置PostHog Surveys。每當需要處理Surveys相關問題時使用。

depot-container-builds

Configures and runs Depot remote container builds using `depot build` and `depot bake`. Use when building Docker images, creating Dockerfiles with Depot,…

depot-container-builds

Configures and runs Depot remote container builds using `depot build` and `depot bake`. Use when building Docker images, creating Dockerfiles with Depot,…

depot-container-builds

Configures and runs Depot remote container builds using `depot build` and `depot bake`. Use when building Docker images, creating Dockerfiles with Depot,…

depot-container-builds

Configures and runs Depot remote container builds using `depot build` and `depot bake`. Use when building Docker images, creating Dockerfiles with Depot,…

depot-github-runners

設定 Depot 管理的 GitHub Actions 執行器，作為 GitHub 託管執行器的直接替代方案。適用於設定或遷移 GitHub Actions 工作流程時…

depot-github-runners

Configures Depot-managed GitHub Actions runners as a drop-in replacement for GitHub-hosted runners. Use when setting up or migrating GitHub Actions workflows…

depot-github-runners

Configures Depot-managed GitHub Actions runners as a drop-in replacement for GitHub-hosted runners. Use when setting up or migrating GitHub Actions workflows…

depot-github-runners

將 Depot 管理的 GitHub Actions 執行器配置為 GitHub 託管執行器的直接替代方案。適用於設定或遷移 GitHub Actions 工作流程時…

designing-email-templates

在PostHog工作流程库中编写、保存和编辑电子邮件模板——使用Liquid个性化功能撰写电子邮件设计JSON，并创建及往返编辑……

designing-email-templates

在 PostHog 工作流程庫中撰寫、儲存和編輯電子郵件範本 — 使用 Liquid 個人化技術組合電子郵件設計 JSON，並建立與往返編輯…

designing-email-templates

在 PostHog 工作流程庫中撰寫、儲存和編輯電子郵件範本 — 使用 Liquid 個人化技術組合電子郵件設計 JSON，並建立與往返編輯…

diagnosing-ci-and-merge-bottlenecks

診斷 GitHub 儲存庫的 CI 與合併請求管道健康狀況，使用工程分析 MCP 工具——合併請求（含 CI 狀態的 PR 列表）……

diagnosing-ci-and-merge-bottlenecks

診斷 GitHub 儲存庫的 CI 與合併請求管道健康狀況，使用工程分析 MCP 工具——合併請求（含 CI 狀態的 PR 列表）……

diagnosing-ci-and-merge-bottlenecks

Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools — pull-requests (PR list with CI status),…

diagnosing-ci-and-merge-bottlenecks

Diagnoses CI and pull-request pipeline health for a GitHub repo using the engineering analytics MCP tools — pull-requests (PR list with CI status),…

diagnosing-ci-and-merge-bottlenecks

診斷 GitHub 儲存庫的 CI 與合併請求管道健康狀況，使用工程分析 MCP 工具——合併請求（含 CI 狀態的 PR 列表）……

diagnosing-endpoint-performance

診斷 PostHog 端點為何緩慢或成本高昂，並提出具體修復方案——例如提高快取 TTL、啟用具體化、重構變數或改寫……

diagnosing-endpoint-performance

Diagnose why a PostHog endpoint is slow or expensive and propose a concrete fix — bump the cache TTL, enable materialisation, restructure variables, or rewrite…

diagnosing-endpoint-performance

Diagnose why a PostHog endpoint is slow or expensive and propose a concrete fix — bump the cache TTL, enable materialisation, restructure variables, or rewrite…

diagnosing-endpoint-performance

診斷 PostHog 端點為何緩慢或成本高昂，並提出具體修復方案——提高快取 TTL、啟用具體化、重構變數或改寫……

diagnosing-endpoint-performance

診斷 PostHog 端點為何緩慢或成本高昂，並提出具體修復方案——例如提高快取 TTL、啟用具體化、重構變數或改寫……

diagnosing-experiment-results

診斷特定PostHog實驗中的偏差、異常和看似奇怪的結果。涵蓋空白/0曝光實驗、樣本比率不匹配、身份…

diagnosing-experiment-results

Diagnoses bias, anomalies, and strange-looking results on a specific PostHog experiment. Covers empty / 0-exposure experiments, sample ratio mismatch, identity…

diagnosing-experiment-results

Diagnoses bias, anomalies, and strange-looking results on a specific PostHog experiment. Covers empty / 0-exposure experiments, sample ratio mismatch, identity…

diagnosing-experiment-results

診斷特定PostHog實驗中的偏差、異常和看似奇怪的結果。涵蓋空白/0曝光實驗、樣本比率不匹配、身份…

diagnosing-experiment-results

診斷特定PostHog實驗中的偏差、異常及看似奇怪的結果。涵蓋空白/零曝光實驗、樣本比率不匹配、身份…

diagnosing-failed-warehouse-syncs

當資料倉儲來源或資料表發生失敗、卡住或產出錯誤資料時，請由上而下處理：來源 → 結構描述 → 復原動作。不要直接跳到「從頭重新同步」——這會丟棄已同步的資料並從零開始，通常不是正確的第一步。

diagnosing-failed-warehouse-syncs

Diagnose why a data warehouse sync is failing and recommend the right recovery action. Use when the user asks "why isn't my Stripe/Postgres/Hubspot sync…

diagnosing-failed-warehouse-syncs

Diagnose why a data warehouse sync is failing and recommend the right recovery action. Use when the user asks "why isn't my Stripe/Postgres/Hubspot sync…

diagnosing-failed-warehouse-syncs

我们要求翻译一段文本，目标语言是繁体中文。需要保留产品名、协议名、URL、数字、技术术语。不要添加声明、解释、Markdown、项目符号、链接、标签、前缀或额外评论。只翻译<text>内的内容，不包括名称"diagnosing-failed-warehouse-syncs"除非它出现在源文本中。源文本中没有出现该名称，所以不翻译它。源文本："Work top-down when a data warehouse source or table is failing, stuck, or producing bad data: source → schema → recovery action. Do not jump straight to "resync from scratch" — that discards synced data and restarts from zero, which is rarely the right first step." 翻译成繁体中文。注意技术术语如"data warehouse"、"source"、"schema"、"recovery action"、"resync from scratch"等应保留或使用常见译法。考虑使用"資料倉儲"、"來源"、"結構描述"、"復原動作"、"從頭重新同步"。注意箭頭符號

diagnosing-failed-warehouse-syncs

當資料倉儲來源或資料表發生失敗、卡住或產出錯誤資料時，請由上而下處理：來源 → 結構描述 → 復原動作。不要直接跳到「從頭重新同步」——這會丟棄已同步的資料並從零開始，很少是正確的第一步。

diagnosing-missing-recordings

當用戶詢問「為什麼這個會議沒有被錄製？」或「為什麼我沒有任何錄製檔案？」時，請依照此工作流程系統性地診斷原因。

diagnosing-missing-recordings

當用戶詢問「為什麼這個會議沒有被錄製？」或「為什麼我沒有任何錄製檔案？」時，請依照此工作流程系統性地診斷原因。

diagnosing-missing-recordings

當用戶詢問「為什麼這個會議沒有被錄製？」或「為什麼我沒有任何錄製檔案？」時，請依照此工作流程系統性地診斷原因。

diagnosing-sdk-health

當使用者詢問 PostHog SDK 版本、過時的 SDK，或是否應該升級時，請使用預先處理過的 SDK Doctor 報告，而非自行推斷版本。後端會套用智慧語意化版本規則（寬限期、次要版本數量門檻、基於使用時間的偵測）、流量百分比門檻，並提供與 SDK Doctor 使用者介面完全一致的使用者面向文案。

diagnosing-sdk-health

Diagnoses the health of a project's PostHog SDK integrations — which SDKs are out of date and how to fix them. Use when a user asks about PostHog SDK versions,…

diagnosing-sdk-health

Diagnoses the health of a project's PostHog SDK integrations — which SDKs are out of date and how to fix them. Use when a user asks about PostHog SDK versions,…

diagnosing-sdk-health

當使用者詢問 PostHog SDK 版本、過時的 SDK，或是否應該升級時，請使用預先處理過的 SDK Doctor 報告，而非自行推斷版本。後端會套用智慧語意化版本規則（寬限期、次要版本數量門檻、基於使用時間的偵測）、流量百分比門檻，並提供與 SDK Doctor 使用者介面完全一致的使用者面向文案。

diagnosing-sdk-health

當使用者詢問 PostHog SDK 版本、過時的 SDK，或是否應該升級時，請使用預先處理過的 SDK Doctor 報告，而非自行推斷版本。後端會套用智慧語意化版本規則（寬限期、次要版本數量門檻、基於使用時間的偵測）、流量百分比門檻，並提供與 SDK Doctor 使用者介面完全一致的使用者面向文案。

diagnosing-stacktrace-symbolication

幫助使用者對任何支援平台上的 PostHog Error Tracking 堆疊追蹤符號化進行除錯 — JavaScript/TypeScript 網頁、React Native (Hermes)、Android…

diagnosing-stacktrace-symbolication

幫助使用者偵錯任何支援平台上的 PostHog Error Tracking 堆疊追蹤符號化解譯 — JavaScript/TypeScript 網頁、React Native (Hermes)、Android…

diagnosing-stacktrace-symbolication

幫助使用者對任何支援平台上的 PostHog Error Tracking 堆疊追蹤符號化進行除錯 — JavaScript/TypeScript 網頁、React Native (Hermes)、Android…

django-migrations

Django 遷移模式與 PostHog 的安全工作流程。適用於建立、調整或審查 Django/Postgres 遷移，包括非阻塞性…

django-migrations

Django migration patterns and safety workflow for PostHog. Use when creating, adjusting, or reviewing Django/Postgres migrations, including non-blocking…

django-migrations

Django migration patterns and safety workflow for PostHog. Use when creating, adjusting, or reviewing Django/Postgres migrations, including non-blocking…

django-migrations

Django 遷移模式與 PostHog 的安全工作流程。適用於建立、調整或審查 Django/Postgres 遷移，包括非阻塞…

django-startup-time

將重量級導入移出每個進程（web、celery、temporal、migrate、shell、CI）都會執行的 django.setup() 路徑。在觸及 AppConfig.ready() 時使用…

django-startup-time

將重量級導入移出每個進程（web、celery、temporal、migrate、shell、CI）都會執行的 django.setup() 路徑。在觸及 AppConfig.ready() 時使用…

documenting-warehouse-sources

撰寫或更新面向用戶的 posthog.com 文件，內容關於 PostHog 資料倉儲匯入來源。用於新增來源文件、修正不一致之處…

documenting-warehouse-sources

撰寫或更新 PostHog Data Warehouse 匯入來源的使用者面向文件（位於 posthog.com）。用於新增來源文件、修正不一致之處…

documenting-warehouse-sources

Write or update the user-facing posthog.com documentation for a PostHog Data warehouse import source. Use when adding a new source doc, fixing an inconsistent…

documenting-warehouse-sources

Write or update the user-facing posthog.com documentation for a PostHog Data warehouse import source. Use when adding a new source doc, fixing an inconsistent…

downloading-batch-export-files

按需匯出 PostHog 事件、人員或工作階段，並下載產生的檔案。當使用者要求下載/匯出原始 PostHog 資料、建立…時使用。

downloading-batch-export-files

Export PostHog events, persons, or sessions on demand and download the resulting files. Use when the user asks to download/export raw PostHog data, create a…

downloading-batch-export-files

Export PostHog events, persons, or sessions on demand and download the resulting files. Use when the user asks to download/export raw PostHog data, create a…

downloading-batch-export-files

按需匯出 PostHog 事件、人物或會話，並下載產生的檔案。當使用者要求下載/匯出原始 PostHog 資料、建立…時使用。

downloading-batch-export-files

按需匯出 PostHog 事件、人物或會話，並下載產生的檔案。當使用者要求下載/匯出原始 PostHog 資料、建立…時使用。

啟動 duckgres 與 DuckLake（以 S3 為後端儲存並使用 PostgreSQL 元數據）進行本地測試。在測試 duckgres 與 DuckLake 的相容性或重現 Fivetran…

Start duckgres with DuckLake (S3-backed storage with PostgreSQL metadata) for local testing. Use when testing duckgres against DuckLake or reproducing Fivetran…

error-tracking-android

PostHog error tracking for Android

error-tracking-android

PostHog Android 錯誤追蹤

error-tracking-angular

PostHog error tracking for Angular

error-tracking-angular

PostHog 錯誤追蹤 for Angular

error-tracking-flutter

PostHog error tracking for Flutter

error-tracking-flutter

PostHog 錯誤追蹤 for Flutter

error-tracking-go

PostHog error tracking for Go

error-tracking-go

PostHog 錯誤追蹤 for Go

error-tracking-hono

PostHog 的 Hono 錯誤追蹤

error-tracking-hono

PostHog error tracking for Hono

error-tracking-nextjs

PostHog error tracking for Next.js

error-tracking-nextjs

PostHog 的 Next.js 錯誤追蹤

error-tracking-node

PostHog 錯誤追蹤 for Node.js

error-tracking-node

PostHog error tracking for Node.js

error-tracking-nuxt

PostHog 錯誤追蹤 for Nuxt

error-tracking-nuxt

PostHog error tracking for Nuxt

error-tracking-python

PostHog 的 Python 錯誤追蹤

error-tracking-python

PostHog error tracking for Python

error-tracking-react

PostHog 錯誤追蹤 for React

error-tracking-react

PostHog error tracking for React

error-tracking-react-native

PostHog 的 React Native 錯誤追蹤

error-tracking-react-native

PostHog error tracking for React Native

error-tracking-ruby

PostHog 的 Ruby 錯誤追蹤

error-tracking-ruby

PostHog error tracking for Ruby

error-tracking-ruby-on-rails

PostHog error tracking for Ruby on Rails

error-tracking-ruby-on-rails

PostHog 錯誤追蹤 for Ruby on Rails

error-tracking-svelte

PostHog error tracking for Svelte

error-tracking-svelte

PostHog 的 Svelte 錯誤追蹤

error-tracking-web

PostHog error tracking for Web (JavaScript)

error-tracking-web

PostHog 網頁錯誤追蹤（JavaScript）

establishing-code-ownership

Determine which PostHog team owns a file, directory, or code path, or enumerate all code a team owns (via distributed `owners.yaml`, `products/*/product.yaml`,…

establishing-code-ownership

Determine which PostHog team owns a file, directory, or code path, or enumerate all code a team owns (via `products/*/product.yaml` and…

establishing-code-ownership

Determine which PostHog team owns a file, directory, or code path, or enumerate all code a team owns (via `products/*/product.yaml` and…

experiment-audit

稽核客戶的PostHog A/B實驗——驗證配置、曝光、歸因與指標。觸發詞包括「稽核[客戶]的實驗」……

exploring-ai-failures

在生產環境中找出AI/LLM應用程式的失敗點，並從實際追蹤中呈現失敗模式。當有人想了解…時使用。

exploring-ai-failures

Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand…

exploring-ai-failures

找出AI/LLM應用在生產環境中失敗的位置，並從真實追蹤中呈現失敗模式。當有人想了解…時使用。

exploring-apm-traces

PostHog 從 OpenTelemetry 擷取分散式追蹤。每個追蹤都是一個跨度樹，代表請求在服務間的路徑。

exploring-apm-traces

Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow…

exploring-apm-traces

PostHog 從 OpenTelemetry 擷取分散式追蹤。每個追蹤都是一個跨度樹，代表請求在服務間的路徑。

exploring-apm-traces

使用 PostHog APM（OpenTelemetry span）資料透過 MCP 調查分散式應用程式效能。當使用者詢問服務追蹤、緩慢…時使用。

exploring-autocapture-events

如果用戶選擇加入，posthog-js 會自動將點擊、表

exploring-autocapture-events

若用戶選擇加入，posthog-js 會自動將點擊、表單提交及頁面變更記錄為 $autocapture 事件。每個事件會將被點擊的 DOM 元素及其祖先元素記錄在 elements_chain 欄位中。

exploring-autocapture-events

若用戶選擇加入，posthog-js 會自動將點擊、表單提交及頁面變更記錄為 $autocapture 事件。每個事件會將被點擊的 DOM 元素及其祖先元素記錄在 elements_chain 欄位中。

exploring-autocapture-events

Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr attributes),…

exploring-autocapture-events

Guides exploration of $autocapture events captured by posthog-js to understand user interactions, find CSS selectors (especially data-attr attributes),…

exploring-endpoint-execution-logs

探索並診斷 PostHog 端點的執行日誌 — 錯誤訊息、執行失敗、快取未命中、執行緩慢，或端點執行期間出現意外的行數…

exploring-endpoint-execution-logs

Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint…

exploring-endpoint-execution-logs

Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint…

exploring-endpoint-execution-logs

探索並診斷 PostHog 端點的執行日誌 — 錯誤訊息、執行失敗、快取未命中、執行緩慢，或端點執行期間出現意外的行數…

exploring-endpoint-execution-logs

探索並診斷 PostHog 端點的執行日誌 — 錯誤訊息、執行失敗、快取未命中、執行緩慢，或端點執行期間出現意外的行數…

exploring-live-traffic

檢查 PostHog Web 分析即時分頁資料 — 當前線上使用者、過去30分鐘頁面瀏覽量、熱門頁面、來源、裝置、瀏覽器、國家、機器人…

exploring-live-traffic

Inspects PostHog Web analytics Live tab data — current users online, last-30-minutes pageviews, top pages, referrers, devices, browsers, countries, bot…

exploring-live-traffic

Inspects PostHog Web analytics Live tab data — current users online, last-30-minutes pageviews, top pages, referrers, devices, browsers, countries, bot…

exploring-live-traffic

檢查 PostHog Web 分析即時分頁資料 — 當前線上使用者、過去30分鐘頁面瀏覽量、熱門頁面、來源、裝置、瀏覽器、國家、機器人…

exploring-live-traffic

檢查 PostHog Web 分析即時分頁資料 — 當前線上使用者、過去30分鐘頁面瀏覽量、熱門頁面、來源、裝置、瀏覽器、國家、機器人…

exploring-llm-clusters

調查LLM分析集群——了解AI/LLM流量中的使用模式，比較集群行為，計算成本/延遲指標，並深入探討…

exploring-llm-clusters

調查LLM分析集群——了解AI/LLM流量中的使用模式，比較集群行為，計算成本/延遲指標，並深入探討…

exploring-llm-clusters

調查LLM分析集群——了解AI/LLM流量中的使用模式，比較集群行為，計算成本/延遲指標，並深入探討…

exploring-llm-clusters

Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into…

exploring-llm-clusters

Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into…

exploring-llm-costs

PostHog 在擷取時，為每個 $ai_generation 和 $ai_embedding 事件附加每次呼叫的成本元數據。每個成本問題都歸結為對這兩種事件類型的彙總——有趣的變化僅在於你如何分組、篩選和比較。

exploring-llm-costs

PostHog 在擷取時，為每個 $ai_generation 和 $ai_embedding 事件附加每次呼叫的成本元數據。每個成本問題都簡化為對這兩種事件類型的彙總——唯一的差異在於如何分組、篩選和比較。

exploring-llm-costs

Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost…

exploring-llm-costs

Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost…

exploring-llm-costs

調查 PostHog 中的 LLM 花費——隨時間變化的總成本、按模型、供應商、用戶、追蹤或自訂維度劃分的成本、Token 與快取命中經濟學，以及成本……

exploring-llm-evaluations

PostHog 評估會對 $ai_generation 事件進行評分。每個評估屬於兩種型別之一，兩者皆為一級公民：

exploring-llm-evaluations

PostHog 評估會對 $ai_generation 事件進行評分。每個評估屬於兩種型別之一，兩者皆為一級公民：

exploring-llm-evaluations

Investigate AI observability evaluations — `hog` (deterministic code-based), `llm_judge` (LLM-prompt-based), and `sentiment` (user-message sentiment). Find…

exploring-llm-evaluations

Investigate AI observability evaluations of both types — `hog` (deterministic code-based) and `llm_judge` (LLM-prompt-based). Find existing evaluations,…

exploring-llm-evaluations

PostHog 評估會對 $ai_generation 事件進行評分。每個評估屬於兩種型別之一，兩者皆為一級公民：

exploring-llm-traces

PostHog 將 LLM/AI 代理活動記錄為追蹤。每個追蹤都是一個事件樹，代表單一 AI 互動——從頂層代理調用到底層 LLM API 呼叫。

exploring-llm-traces

PostHog 將 LLM/AI 代理活動擷取為追蹤記錄。每條追蹤記錄都是一個事件樹，代表單一 AI 互動——從頂層代理調用到底層的個別 LLM API 呼叫。

exploring-llm-traces

PostHog 將 LLM/AI 代理活動記錄為追蹤。每個追蹤都是一個事件樹，代表單一 AI 互動——從頂層代理調用到底層的個別 LLM API 呼叫。

exploring-mcp-intent-clusters

探索 PostHog MCP 意圖集群——按語義相似度分組的代理目標，包含每個集群的工具分佈與錯誤率。當用戶詢問……時使用。

exploring-mcp-intent-clusters

探索 PostHog MCP 意圖集群——按語義相似度分組的代理目標，包含每個集群的工具分佈與錯誤率。當用戶詢問……時使用。

exploring-mcp-intent-clusters

Explore PostHog MCP intent clusters — agent goals grouped by semantic similarity, with each cluster's tool distribution and error rates. Use when the user asks…

exploring-mcp-sessions

調查個別 PostHog MCP 工作階段——單一代理在一次運行中執行的工具呼叫序列、其嘗試達成的目標，以及出錯的位置。使用…

exploring-mcp-sessions

調查個別 PostHog MCP 工作階段——單一代理在一次運行中進行的工具呼叫序列、其嘗試達成的目標，以及出錯之處。使用…

exploring-mcp-tool-quality

Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool…

exploring-mcp-tool-quality

Investigate the quality of PostHog MCP tool calls — error rates, latency, reach, and which tools are failing or slow. Use when the user asks "which MCP tool…

exploring-mcp-tool-quality

調查 PostHog MCP 工具呼叫的品質——錯誤率、延遲、觸及範圍，以及哪些工具失敗或緩慢。當使用者詢問「哪個 MCP 工具…」時使用。

exploring-mcp-tool-usage

探索 PostHog MCP 伺服器工具使用方式的起點 — 將廣泛問題導向能回答的類型化工具。當使用者詢問「如何…」時使用。

exploring-mcp-tool-usage

Starting point for exploring how a PostHog MCP server's tools are used — routes a broad question to the typed tool that answers it. Use when the user asks "how…

exploring-mcp-tool-usage

探索 PostHog MCP 伺服器工具使用方式的起點——將廣泛的問題導向能回答該問題的類型化工具。當使用者詢問「如何…」時使用。

exploring-replay-vision-observations

引導代理提取Replay Vision掃描器的觀測結果、讀取發現並採取行動——總結跨會話的模式、深入分析……

exploring-replay-vision-observations

Guides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling…

exploring-replay-vision-observations

引導代理提取Replay Vision掃描器的觀測結果、讀取發現並採取行動——總結跨會話的模式、深入分析……

exploring-scouts

如何探索並理解 PostHog Signals scouts——這些排程代理會掃描專案並將報告寫入 Signals 收件匣。當使用者……時使用。

exploring-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user…

exploring-scouts

如何探索並理解 PostHog Signals scouts——這些排程代理會掃描專案並將報告寫入 Signals 收件匣。當使用者……時使用。

exploring-signals-scouts

如何探索並理解 PostHog Signals scouts——這些排程代理會掃描專案並將發現結果發送至 Signals 收件匣。當使用者……時使用。

exploring-signals-scouts

How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and emit findings into the Signals inbox. Use when a user…

exploring-signals-scouts

如何探索並理解 PostHog Signals scouts——這些排程代理會掃描專案並將發現結果發送至 Signals 收件匣。當使用者…時使用。

exploring-the-wizard

Run, drive, and explore the PostHog wizard headlessly against an app — boot it on the app and decide each screen yourself over the wizard-ci MCP tools…

exporting-session-recordings

匯出單一會話錄音的原始資料（錄音區塊 + ClickHouse 元數據）為可下載的 zip 檔案，並進行下載。僅限工作人員使用，透過 Django 管理後台…

extending-personhog-test-harness

When and how to add scenarios, chaos events, and invariants to the personhog e2e test harness (rust/personhog-test-harness). Use after fixing a bug or…

feature-flags-android

PostHog 功能開關，適用於 Android 應用程式

feature-flags-android

PostHog feature flags for Android applications

feature-flags-api

PostHog feature flags for API applications

feature-flags-api

PostHog 功能開關，適用於 API 應用程式

feature-flags-dotnet

PostHog feature flags for .NET applications

feature-flags-dotnet

PostHog 功能標誌適用於 .NET 應用程式

feature-flags-elixir

PostHog feature flags for Elixir applications

feature-flags-elixir

PostHog 功能開關，適用於 Elixir 應用程式

feature-flags-flutter

PostHog feature flags for Flutter applications

feature-flags-flutter

PostHog 功能開關，適用於 Flutter 應用程式

feature-flags-go

PostHog feature flags for Go applications

feature-flags-go

PostHog 功能開關，適用於 Go 應用程式

feature-flags-ios

PostHog feature flags for iOS applications

feature-flags-ios

PostHog 功能開關，適用於 iOS 應用程式

feature-flags-java

PostHog feature flags for Java applications

feature-flags-java

PostHog 功能標誌，適用於 Java 應用程式

feature-flags-nextjs

PostHog feature flags for Next.js applications

feature-flags-nextjs

PostHog 功能開關，適用於 Next.js 應用程式

feature-flags-nodejs

PostHog feature flags for Node.js applications

feature-flags-nodejs

PostHog 功能標誌，適用於 Node.js 應用程式

feature-flags-php

PostHog feature flags for PHP applications

feature-flags-php

PostHog 功能標誌，適用於 PHP 應用程式

feature-flags-python

PostHog feature flags for Python applications

feature-flags-python

PostHog 功能開關，適用於 Python 應用程式

feature-flags-react

PostHog feature flags for React applications

feature-flags-react

PostHog 功能標誌，適用於 React 應用程式

feature-flags-react-native

PostHog feature flags for React Native applications

feature-flags-react-native

PostHog 功能開關，適用於 React Native 應用程式

feature-flags-ruby

PostHog feature flags for Ruby applications

feature-flags-ruby

PostHog 功能開關，適用於 Ruby 應用程式

feature-flags-rust

PostHog feature flags for Rust applications

feature-flags-rust

PostHog 功能開關，適用於 Rust 應用程式

feature-flags-web

PostHog feature flags for Web (JavaScript) applications

feature-flags-web

PostHog 功能開關，適用於 Web（JavaScript）應用程式

feature-usage-feed

某些 PostHog 功能（如群組會話摘要、單一會話摘要、重播 AI 搜尋、錯誤追蹤 AI 除錯等）每週會產生數百或數千條 LLM 追蹤記錄。手動逐一閱讀並不可行。此技能涵蓋了將大量追蹤記錄轉換為即時 Slack 摘要的端到端模式，呈現典型使用案例——即使用者實際使用該功能的方式。

feature-usage-feed

某些 PostHog 功能（如群組會話摘要、單一會話摘要、重播 AI 搜尋、錯誤追蹤 AI 除錯等）每週會產生數百或數千條 LLM 追蹤記錄。手動閱讀這些記錄並不實際。此技能涵蓋了將大量追蹤記錄轉化為即時 Slack 資訊流的端到端模式，呈現出典型使用案例——即使用者實際使用該功能的方式。

feature-usage-feed

Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use…

feature-usage-feed

Set up an LLM-judge evaluation that extracts canonical use cases for a PostHog feature at scale and streams the results to a Slack channel as a live feed. Use…

feature-usage-feed

某些 PostHog 功能（如群組會話摘要、單一會話摘要、重播 AI 搜尋、錯誤追蹤 AI 除錯等）每週會產生數百或數千條 LLM 追蹤記錄。手動逐一閱讀並不可行。此技能涵蓋了將大量追蹤記錄轉化為即時 Slack 資訊流的端到端模式，呈現出典型使用案例——即使用者實際使用該功能的方式。

filtering-bot-traffic

在 PostHog 網站與產品分析中，利用流量分類介面（isLikelyBot…）識別、衡量並排除機器人、爬蟲及 AI 代理程式的流量。

filtering-bot-traffic

Identify, measure, and exclude bot / crawler / AI-agent traffic in PostHog web and product analytics using the traffic classification surface (the isLikelyBot…

filtering-bot-traffic

在 PostHog 網站與產品分析中，利用流量分類介面（isLikelyBot…）識別、衡量並排除機器人、爬蟲及 AI 代理程式的流量。

finding-deleted-feature-flags

在近期時間範圍內，尋找活躍專案中被軟刪除的功能開關。當使用者詢問「過去 N 天內有哪些開關被刪除…」時使用。

finding-deleted-feature-flags

Find feature flags that were soft-deleted in the active project within a recent time window. Use when the user asks "what flags were deleted in the last N…

finding-deleted-feature-flags

Find feature flags that were soft-deleted in the active project within a recent time window. Use when the user asks "what flags were deleted in the last N…

finding-deleted-feature-flags

在近期時間範圍內，查找活躍專案中被軟刪除的功能開關。當使用者詢問「過去 N 天內哪些開關被刪除…」時使用。

finding-deleted-feature-flags

在近期時間範圍內，尋找活躍專案中被軟刪除的功能開關。當使用者詢問「最近 N 天內哪些開關被刪除…」時使用。

finding-experiments

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with…

finding-experiments

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with…

finding-experiments

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with…

finding-experiments

將自然語言中的實驗引用解析為具體的實驗ID。處理名稱查詢、模糊描述（如「註冊實驗」、「我最新的…」）。

finding-experiments

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with…

finding-llm-gateway-migration-candidates

Finds and ranks callers that could move from services/llm-gateway to PostHog/ai-gateway. Use when asked what to migrate next, to find low-risk gateway…

finding-replay-for-issue

當使用者說「顯示這個錯誤的重播」或「尋找問題 X 的錄影」，目標並非只是隨便一個關聯的工作階段，而是要找出最能呈現錯誤發生前因後果的那一個。常見問題可能關聯數百個工作階段，其中多數僅為崩潰片段或重複案例。此技能會選出最有用的一個。

finding-replay-for-issue

Finds the most informative session recording linked to an error tracking issue. Use when a user has an error tracking issue ID and wants to watch a replay…

finding-replay-for-issue

Finds the most informative session recording linked to an error tracking issue. Use when a user has an error tracking issue ID and wants to watch a replay…

finding-replay-for-issue

找出與錯誤追蹤問題相關聯、最具資訊性的工作階段錄製。當使用者擁有錯誤追蹤問題 ID 並想觀看重播時使用…

finding-replay-for-issue

我们要求翻译一段英文文本到繁体中文。需要保留产品名、协议名、URL、数字、技术术语。不要添加声明、解释、Markdown、项目符号、链接、标签、前缀或额外评论。只翻译<text>内的内容。注意：名称"finding-replay-for-issue"在文本中没有出现，所以不需要保留。直接翻译文本。文本内容：When a user says "show me a replay for this error" or "find a recording for issue X", the goal isn't just any linked session — it's the one that best shows what led to the error. Popular issues can have hundreds of linked sessions, and most are crash-only fragments or duplicate occurrences. This skill picks the most useful one. 翻译成繁体中文：当用户说「顯示此錯誤的重播」或「尋找問題 X 的錄製內容」時，目標不只是任何連結的工作階段——而是最能顯示導致錯誤原因的那一個。常見問題可能會有數百個連結的工作階段，而其中大部分只是純崩潰片段或重複出現的

finding-sessions-to-watch

引導使用者從「我想看錄影，但不知道該看哪些」到一份簡短、高訊號的值得觀看的場次清單。當使用者詢問哪些……時使用。

finding-sessions-to-watch

Guides a user from "I want to watch recordings but don't know which ones" to a short, high-signal list of sessions worth watching. Use when the user asks which…

finding-sessions-to-watch

Guides a user from "I want to watch recordings but don't know which ones" to a short, high-signal list of sessions worth watching. Use when the user asks which…

finding-sessions-to-watch

引導使用者從「我想看錄影，但不知道該看哪些」到一份簡短、高訊號的值得觀看的場次清單。當使用者詢問哪些…時使用。

finding-sessions-to-watch

引導使用者從「我想看錄影，但不知道該看哪些」到一份簡短、高訊號的值得觀看的場次清單。當使用者詢問哪些……時使用。

fixing-flaky-tests

引導代理在 PostHog 單一儲存庫中重現、根因分析、修復及驗證不穩定測試。當測試在 CI 中偶發失敗時使用，但…

fixing-flaky-tests

Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but…

fixing-flaky-tests

Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but…

fixing-flaky-tests

引導代理在 PostHog 單一儲存庫中重現、根因分析、修復及驗證不穩定測試。當測試在 CI 中偶發失敗時使用，但…

formatting-insight-axes

Pick the right y-axis unit when creating or updating a TrendsQuery insight via `posthog:insight-create` or `posthog:insight-update`. Use when the agent is…

formatting-insight-axes

Pick the right y-axis unit when creating or updating a TrendsQuery insight via `posthog:insight-create` or `posthog:insight-update`. Use when the agent is…

formatting-insight-axes

Pick the right y-axis unit when creating or updating a TrendsQuery insight via `posthog:insight-create` or `posthog:insight-update`. Use when the agent is…

formatting-insight-axes

Pick the right y-axis unit when creating or updating a TrendsQuery insight via `posthog:insight-create` or `posthog:insight-update`. Use when the agent is…

formatting-insight-axes

Pick the right y-axis unit when creating or updating a TrendsQuery insight via `posthog:insight-create` or `posthog:insight-update`. Use when the agent is…

gating-production-deploys

用於新增或編輯 GitHub Actions 工作流程，該流程會將容器映像推送至註冊表（透過 build-push-action 推送至 ECR/ghcr/Docker Hub），或觸發…

gating-production-deploys

Use when adding or editing a GitHub Actions workflow that pushes a container image to a registry (ECR/ghcr/Docker Hub via build-push-action) or dispatches a…

gating-production-deploys

Use when adding or editing a GitHub Actions workflow that pushes a container image to a registry (ECR/ghcr/Docker Hub via build-push-action) or dispatches a…

gating-production-deploys

用於新增或編輯 GitHub Actions 工作流程，該流程會將容器映像推送至註冊表（透過 build-push-action 推送至 ECR/ghcr/Docker Hub），或觸發…

generating-clickhouse-query-performance-reports

為 PostHog 的生產環境 ClickHouse（美國與歐盟）生成並結構化慢查詢效能報告。當被要求提供慢查詢報告、查詢效能…時使用。

generating-clickhouse-query-performance-reports

為 PostHog 的生產環境 ClickHouse（美國和歐盟）生成並結構化慢查詢效能報告。當被要求提供慢查詢報告、查詢效能…時使用。

grouping-noisy-errors

合併 PostHog 錯誤追蹤中，實際相同但被歸為不同指紋的錯誤。當使用者問「為什麼我有這麼多…」時使用。

grouping-noisy-errors

Consolidate PostHog error tracking issues that are the same actual error reported under different fingerprints. Use when the user asks "why do I have so many…

grouping-noisy-errors

Consolidate PostHog error tracking issues that are the same actual error reported under different fingerprints. Use when the user asks "why do I have so many…

grouping-noisy-errors

合併 PostHog 錯誤追蹤中因不同指紋回報的相同實際錯誤。當使用者詢問「為什麼我有這麼多…」時使用。

grouping-noisy-errors

合併 PostHog 錯誤追蹤中因不同指紋回報的相同實際錯誤。當使用者詢問「為什麼我有這麼多…」時使用。

PostHog 開發者 CLI 與儲存庫工具參考。當使用者提及 hogli、詢問儲存庫 CLI 工具、二進位腳本、Makefile、如何...時使用。

PostHog developer CLI and repo tooling reference. Use when the user mentions hogli, asks about repo CLI tools, bin scripts, Makefiles, how to…

PostHog developer CLI and repo tooling reference. Use when the user mentions hogli, asks about repo CLI tools, bin scripts, Makefiles, how to…

統一 CLI，用於 PostHog 開發。將所有儲存庫腳本、二進位指令與工具包裝在單一入口點之後。沒有 Makefile — hogli 即為其對應工具。

implementing-agent-modes

建立/更新 PostHog AI 代理新模式的操作指南。模式是一種限制工具、提示詞及提示詞注入應用範圍與條件的方式…

implementing-agent-modes

Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what…

implementing-agent-modes

Guidelines to create/update a new mode for PostHog AI agent. Modes are a way to limit what tools, prompts, and prompt injections are applied and under what…

implementing-agent-modes

建立/更新 PostHog AI 代理新模式的操作指南。模式是一種限制工具、提示詞及提示詞注入的應用範圍與條件的方式…

implementing-mcp-tools

用於將 PostHog 產品端點暴露為 MCP 工具的指南。在建立新的或更新 API 端點、新增 MCP 工具定義、搭建 YAML 架構時使用…

implementing-mcp-tools

關於將 PostHog 產品端點公開為 MCP 工具的指南。適用於建立或更新 API 端點、新增 MCP 工具定義、搭建 YAML 結構等情境。

implementing-mcp-ui-apps

新增MCP UI應用程式的指南 — 在Claude Desktop等MCP客戶端中渲染工具結果的互動式視覺化。用於新增新的細節或列表…

implementing-mcp-ui-apps

新增MCP UI應用程式的指南 — 在MCP客戶端（如Claude Desktop）中渲染工具結果的互動式視覺化。用於新增新的細節或列表…

implementing-warehouse-sources

實現並擴展 PostHog 資料倉儲匯入來源。用於在 products/warehouse_sources/backend/temporal/data_imports/sources 下新增來源時使用，…

implementing-warehouse-sources

Implement and extend PostHog Data warehouse import sources. Use when adding a new source under products/warehouse_sources/backend/temporal/data_imports/sources,…

implementing-warehouse-sources

Implement and extend PostHog Data warehouse import sources. Use when adding a new source under products/warehouse_sources/backend/temporal/data_imports/sources,…

implementing-warehouse-sources

實現並擴展 PostHog 資料倉儲匯入來源。用於在 posthog/temporal/data_imports/sources 下新增來源、新增資料集/端點…

improving-drf-endpoints

在編輯、審查或稽核 PostHog 中的 DRF viewsets 和 serializers 時使用。觸發條件為 posthog/api/、products/*/backend/api/ 等目錄中的檔案。

improving-drf-endpoints

在編輯、審查或稽核 PostHog 中的 DRF viewsets 和 serializers 時使用。觸發條件為 posthog/api/、products/*/backend/api/ 等目錄中的檔案。

improving-drf-endpoints

Use when editing, reviewing, or auditing DRF viewsets and serializers in PostHog. Triggers on files in posthog/api/, products/*/backend/api/,…

improving-drf-endpoints

Use when editing, reviewing, or auditing DRF viewsets and serializers in PostHog. Triggers on files in posthog/api/, products/*/backend/api/,…

improving-mcp-tools

執行改善我的 MCP 工具活動：一個自動研究風格的循環，使用評估框架測量 MCP 代理體驗，選出影響最大的工具問題…

improving-mcp-tools

Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem…

improving-mcp-tools

執行改善MCP工具活動：一個自動研究風格的循環，使用評估框架測量MCP代理體驗，選出影響最大的工具問題…

inbox-exploration

收件匣是 PostHog 呈現信號報告的地方——這些報告是將相關觀察（信號）彙整成單一問題或趨勢的集群（例如「/checkout 的錯誤率飆升 3 倍」）。報告來自多個來源產品：錯誤追蹤、工作階段重播、網頁分析、實驗，以及 Linear、GitHub 和 Zendesk 等整合服務。

inbox-exploration

Explore PostHog's Inbox and act on what it surfaces — the place where signal reports cluster into actionable issues and trends. Use when the user asks "what's…

inbox-exploration

Explore PostHog's Inbox — the surface where signal reports surface as actionable issues and trends. Use when the user asks "what's in my inbox?", "what should…

inbox-exploration

探索 PostHog 的 Inbox，並對其呈現的內容採取行動——這是信號報告匯聚成可處理問題與趨勢的地方。當使用者詢問「有什麼…」時使用。

inbox-exploration

收件匣是 PostHog 呈現信號報告的地方——這些報告是將相關觀察（信號）彙整成單一問題或趨勢的集群（例如「/checkout 的錯誤率飆升 3 倍」）。報告來自多個來源產品：錯誤追蹤、工作階段重播、網頁分析、實驗，以及 Linear、GitHub 和 Zendesk 等整合服務。

ingestion-pipeline-doctor-nodejs

PostHog 的資料攝取管道框架及其慣例檢查代理的快速參考。

ingestion-pipeline-doctor-nodejs

攝取管線架構概覽與慣例參考。當您需要快速了解管線框架或想知道哪個醫生…

ingestion-pipeline-doctor-nodejs

Ingestion pipeline architecture overview and convention reference. Use when you need a quick orientation to the pipeline framework or want to know which doctor…

ingestion-pipeline-doctor-nodejs

Ingestion pipeline architecture overview and convention reference. Use when you need a quick orientation to the pipeline framework or want to know which doctor…

使用 Ink（React 的 CLI 框架）和 @inkjs/ui 構建終端使用者介面（TUI），採用反應式、會話驅動的精靈模式。適用於建立互動式…

instrument-error-tracking

使用此技能來新增 PostHog 錯誤追蹤功能，以捕捉並監控應用程式中的例外狀況。建議在實作功能或審查 PR 後使用，確保錯誤能搭配完整堆疊追蹤與原始碼對應進行記錄。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何平台或語言。

instrument-error-tracking

Add PostHog error tracking to capture and monitor exceptions. Use after implementing features or reviewing PRs to ensure errors are tracked with stack traces…

instrument-error-tracking

使用此技能來新增 PostHog 錯誤追蹤功能，以捕捉並監控應用程式中的例外狀況。請在實作功能或審查 PR 後使用，確保錯誤能搭配完整的堆疊追蹤與原始碼對應進行記錄。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何平台或語言。

instrument-feature-flags

使用此技能來新增 PostHog 功能開關，以控制新功能或變更功能的發布。在實作功能或審查 PR 後使用，確保透過功能開關安全地逐步推出。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何平台或語言。

instrument-feature-flags

Add PostHog feature flags to gate new functionality. Use after implementing features or reviewing PRs to ensure safe rollouts with feature flag controls. Also…

instrument-feature-flags

使用此技能來新增 PostHog 功能開關，以控制新功能或變更功能的發布。在實作功能或審查 PR 後使用，確保透過功能開關安全地逐步推出。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何平台或語言。

instrument-integration

使用此技能將 PostHog SDK 新增至應用程式。在首次設定 PostHog 或審查需要 PostHog 初始化的 PR 時使用。涵蓋 SDK 安裝、提供者設定及基本配置。支援任何框架或語言。

instrument-integration

使用此技能將 PostHog SDK 新增至應用程式。適用於首次設定 PostHog 時，或審查需要 PostHog 初始化的 PR。涵蓋 SDK 安裝、提供者設定及基本配置。支援任何框架或語言。

instrument-integration

Add PostHog SDK integration to your application. Use when setting up PostHog for the first time or reviewing PRs that need PostHog initialization. Covers SDK…

instrument-llm-analytics

使用此技能在新增或修改的程式碼中加入 PostHog LLM 分析功能，以追蹤 AI 模型的使用情況。在實作 LLM 功能或審查 PR 後使用，確保所有生成內容都記錄了 token 數量、延遲時間與成本。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何供應商或框架。

instrument-llm-analytics

Add PostHog LLM analytics to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token…

instrument-llm-analytics

使用此技能可在新增或修改的程式碼中加入 PostHog LLM 分析功能，以追蹤 AI 模型的使用情況。請在實作 LLM 功能或審查 PR 後使用，確保所有生成內容皆記錄 token 數量、延遲時間與成本。若尚未安裝 PostHog，此技能亦涵蓋初始 SDK 設定。支援任何供應商或框架。

instrument-logs

使用此技能為新增或修改的程式碼加入 PostHog 日誌擷取。在實作功能或審查 PR 後使用，以確保透過結構化屬性擷取有意義的日誌事件。若尚未設定 PostHog 日誌匯出，此技能也涵蓋初始 OTLP 匯出器設定。支援任何平台或語言。

instrument-logs

Add PostHog log capture to track application logs. Use after implementing features or reviewing PRs to ensure meaningful log events are captured with…

instrument-logs

使用此技能為新增或修改的程式碼加入 PostHog 日誌擷取。在實作功能或審查 PR 後使用，以確保能透過結構化屬性擷取有意義的日誌事件。若尚未設定 PostHog 日誌匯出，此技能也涵蓋初始的 OTLP 匯出器設定。支援任何平台或語言。

instrument-product-analytics

使用此技能來新增產品分析事件（capture calls），以追蹤新程式碼或修改後程式碼中有意義的使用者行為。在實作功能或審查 PR 後使用，確保關鍵使用者行為被記錄。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何框架或語言。

instrument-product-analytics

Add PostHog product analytics events to track user behavior. Use after implementing new features or reviewing PRs to ensure meaningful user actions are…

instrument-product-analytics

使用此技能在新增或修改的程式碼中加入產品分析事件（capture 呼叫），以追蹤有意義的使用者行為。建議在實作功能或審查 PR 後使用，確保關鍵使用者行為被記錄。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何框架或語言。

instrumenting-first-party-metrics

How to instrument PostHog's own Metrics product from PostHog-owned code — record counters, gauges, and histograms that land in posthog.metrics, the same way…

integration-android

PostHog 整合用於 Android 應用程式

integration-android

PostHog integration for Android applications

integration-angular

PostHog integration for Angular applications

integration-angular

PostHog 整合用於 Angular 應用程式

integration-astro-hybrid

PostHog integration for Astro hybrid rendering with both static and server-rendered pages

integration-astro-hybrid

此技能可協助您將 PostHog 分析功能新增至 Astro（Hybrid）應用程式中。

integration-astro-ssr

適用於具有 API 路由的伺服器端渲染 Astro 應用程式的 PostHog 整合

integration-astro-ssr

PostHog integration for server-rendered Astro applications with API routes

integration-astro-static

PostHog integration for static Astro sites using SSG

integration-astro-static

使用 SSG 的靜態 Astro 網站的 PostHog 整合

integration-astro-view-transitions

PostHog integration for Astro with ClientRouter view transitions

integration-astro-view-transitions

PostHog 整合至 Astro，支援 ClientRouter 視圖轉場

integration-django

PostHog integration for Django applications

integration-django

PostHog 整合至 Django 應用程式

integration-expo

PostHog integration for Expo applications

integration-expo

適用於 Expo 應用程式的 PostHog 整合

integration-fastapi

PostHog integration for FastAPI applications

integration-fastapi

PostHog 整合用於 FastAPI 應用程式

integration-flask

PostHog integration for Flask applications

integration-flask

PostHog 整合用於 Flask 應用程式

integration-javascript_node

integration-javascript_node — 一個可供 AI 代理安裝的技能，由 posthog/skills 發布。

integration-javascript_node

PostHog integration for server-side Node.js applications using posthog-node

integration-javascript_web

PostHog integration for client-side web JavaScript applications using posthog-js

integration-javascript_web

integration-javascript_web — 一個可安裝的AI代理技能，由posthog/skills發布。

integration-laravel

PostHog integration for Laravel applications

integration-laravel

PostHog 整合至 Laravel 應用程式

integration-nextjs-app-router

PostHog integration for Next.js App Router applications

integration-nextjs-app-router

PostHog 整合，適用於 Next.js App Router 應用程式

integration-nextjs-pages-router

PostHog integration for Next.js Pages Router applications

integration-nextjs-pages-router

PostHog 整合，適用於 Next.js Pages Router 應用程式

integration-nuxt-3.6

PostHog integration for Nuxt versions 3.0 to 3.6

integration-nuxt-3.6

integration-nuxt-3.6 — 一個可安裝的AI代理技能，由posthog/skills發布。

integration-nuxt-4

PostHog integration for Nuxt 4 applications

integration-nuxt-4

PostHog 整合用於 Nuxt 4 應用程式

integration-python

PostHog integration for any Python application using the Python SDK

integration-python

適用於任何使用 Python SDK 的 Python 應用程式的 PostHog 整合

integration-react-native

PostHog integration for React Native applications

integration-react-native

PostHog 整合用於 React Native 應用程式

integration-react-react-router-6

PostHog integration for React Router v6 applications

integration-react-react-router-6

PostHog 整合至 React Router v6 應用程式

integration-react-react-router-7-data

PostHog integration for React Router v7 - Data mode applications

integration-react-react-router-7-data

PostHog 整合 React Router v7 - 資料模式應用程式

integration-react-react-router-7-declarative

PostHog integration for React Router v7 - Declarative mode applications

integration-react-react-router-7-declarative

PostHog 整合 React Router v7 - 宣告式模式應用程式

integration-react-react-router-7-framework

PostHog integration for React Router v7 - Framework mode applications

integration-react-react-router-7-framework

PostHog 整合 React Router v7 - 框架模式應用程式

integration-react-tanstack-router-code-based

PostHog integration for React applications using TanStack Router with code-based routing

integration-react-tanstack-router-code-based

此技能可協助您將 PostHog 分析功能新增至使用 TanStack Router（基於程式碼）的 React 應用程式中。

integration-react-tanstack-router-file-based

此技能可協助您在基於檔案的 React 與 TanStack Router 應用程式中加入 PostHog 分析功能。

integration-react-tanstack-router-file-based

PostHog integration for React applications using TanStack Router with file-based routing

integration-react-vite

PostHog integration for React applications built with Vite (no router)

integration-react-vite

專為使用 Vite 建置的 React 應用程式設計的 PostHog 整合（無路由器）

integration-ruby

適用於任何使用 Ruby SDK 的 Ruby 應用程式的 PostHog 整合

integration-ruby

PostHog integration for any Ruby application using the Ruby SDK

integration-ruby-on-rails

PostHog integration for Ruby on Rails applications

integration-ruby-on-rails

PostHog 整合 Ruby on Rails 應用程式

integration-sveltekit

PostHog integration for SvelteKit applications

integration-sveltekit

PostHog 整合至 SvelteKit 應用程式

integration-swift

PostHog integration for Swift iOS and macOS applications

integration-swift

PostHog 整合，適用於 Swift iOS 與 macOS 應用程式

integration-tanstack-start

PostHog integration for TanStack Start full-stack applications

integration-tanstack-start

PostHog 整合至 TanStack Start 全端應用程式

integration-vue-3

PostHog 整合至 Vue 3 應用程式

integration-vue-3

PostHog integration for Vue 3 applications

investigate-metric

針對「為什麼X改變了？」這類關於已儲存的洞察、儀表板圖塊或貼上的查詢的問題。請勿將此技能用於單純的「X是什麼？」問題——僅在需要解釋觀察到的變化時才載入此技能。

investigate-metric

針對「為什麼X改變了？」這類關於已儲存的洞察、儀表板圖塊或貼上查詢的問題。請勿將此技能用於單純的「X是什麼？」問題——僅在需要解釋觀察到的變化時才使用。

investigate-metric

Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations…

investigate-metric

Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations…

investigate-metric

診斷產品指標為何發生變化（下降、飆升或停滯），透過協調細分、參與者、路徑、生命週期、留存率及註解等方式…

investigating-ci-failures

Investigates a specific CI failure to a verdict: whose fault, which commit, who wrote it, and whether it's fixed. Use for "who broke master", "why did this…

investigating-error-issue

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and wants…

investigating-error-issue

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and wants…

investigating-error-issue

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and wants…

investigating-error-issue

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and wants…

investigating-error-issue

Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error_tracking/<id>`) and wants…

investigating-logs

Investigate logs in a PostHog project: verify a service or deployment is healthy, explain an error spike, triage an incident, or understand what a log stream…

investigating-metric-anomalies

調查 PostHog Metrics 中的伺服器/基礎設施指標異常——從「此指標上升/下降/突增」或觸發的警報到可能的原因……

investigating-metric-anomalies

Investigates server/infrastructure metric anomalies in PostHog Metrics — from "this metric is rising/dropping/spiking" or a fired alert to a probable cause…

investigating-metric-anomalies

調查 PostHog Metrics 中的伺服器/基礎設施指標異常——從「此指標上升/下降/突增」或觸發的警報到可能的原因…

investigating-replay

當使用者詢問「這個工作階段發生了什麼事？」或提供錄製內容／工作階段 ID 進行調查時，應平行收集所有相關背景資訊，而非要求使用者逐一詢問。

investigating-replay

Investigates a session recording by gathering metadata, person profile, same-session events, and linked error tracking issues in one pass. Use when a user…

investigating-replay

Investigates a session recording by gathering metadata, person profile, same-session events, and linked error tracking issues in one pass. Use when a user…

investigating-replay

調查單次工作階段錄影，一次性收集中繼資料、人員檔案、同工作階段事件及相關錯誤追蹤問題。當使用者……時使用。

investigating-replay

當使用者詢問「這個工作階段發生了什麼事？」或提供錄製內容／工作階段 ID 進行調查時，應平行收集所有相關背景資訊，而非要求使用者逐一詢問。

isolating-product-facade-contracts

規劃並執行產品隔離遷移，將其轉換為PostHog中的外觀層與合約層，遵循視覺審查架構。當某個產品仍處於…時使用。

isolating-product-facade-contracts

規劃並執行逐步的產品隔離遷移，將其遷移至 PostHog 中的外觀層與合約層，遵循視覺審查架構。當需要…時使用。

isolating-product-facade-contracts

Plan and execute product isolation migrations to a facade plus contract layer in PostHog, following the Visual review architecture. Use when a product still…

isolating-product-facade-contracts

Plan and execute product isolation migrations to a facade plus contract layer in PostHog, following the Visual review architecture. Use when a product still…

llm-analytics-setup

PostHog LLM analytics for all supported providers

llm-analytics-setup

所有支援的提供者之PostHog LLM分析

PostHog logs for Datadog

PostHog 的 Datadog 日誌

PostHog logs for Go

PostHog 的 Go 日誌

PostHog logs for Java

PostHog 日誌 for Java

PostHog logs for Next.js

PostHog 的 Next.js 日誌

PostHog logs for Node.js

PostHog 的 Node.js 日誌

PostHog logs for Other Languages

PostHog 其他語言的日誌

PostHog logs for Python

PostHog 的 Python 日誌

making-scenes-tab-aware

引導將 PostHog

making-scenes-tab-aware

Guides converting PostHog frontend scenes to be tab aware for internal scene tabs. Use when adding or refactoring a `SceneExport` scene, fixing state leaking…

making-scenes-tab-aware

Guides converting PostHog frontend scenes to be tab aware for internal scene tabs. Use when adding or refactoring a `SceneExport` scene, fixing state leaking…

manage-dashboard-widgets

引導 PostHog 工程師完成儀表板小工具平台相關工作 — 推出新的 widget_type（WIDGET_REGISTRY、catalog、run_widgets、WidgetCard）或更新…

manage-dashboard-widgets

引導 PostHog 工程師完成儀表板小工具平台相關工作 — 推出新的 widget_type（WIDGET_REGISTRY、catalog、run_widgets、WidgetCard）或更新…

managing-endpoint-versions

安全地處理端點版本 — 在遊樂場預覽草稿、回滾至舊版本、在不提升查詢的情況下更新某版本的設定…

managing-endpoint-versions

安全地處理端點版本 — 在遊樂場預覽草稿、回滾到舊版本、在不提升查詢的情況下更新某個版本的設定…

managing-endpoint-versions

Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query…

managing-endpoint-versions

Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query…

managing-endpoint-versions

安全地處理端點版本 — 在遊樂場預覽草稿、回滾至舊版本、在不提升查詢的情況下更新某個版本的設定…

managing-experiment-lifecycle

引導實驗狀態轉換：啟動、暫停、恢復、結束、發布變體、歸檔、重置及複製。涵蓋前置條件、…

managing-experiment-lifecycle

引導實驗狀態轉換：啟動、暫停、恢復、結束、發布變體、歸檔、重置及複製。涵蓋前置條件、…

managing-experiment-lifecycle

Guides experiment state transitions: launching, pausing, resuming, ending, shipping variants, archiving, resetting, duplicating, and copying to another…

managing-experiment-lifecycle

Guides experiment state transitions: launching, pausing, resuming, ending, shipping variants, archiving, resetting, duplicating, and copying to another…

managing-experiment-lifecycle

引導實驗狀態轉換：啟動、暫停、恢復、結束、發布變體、歸檔、重置及複製。涵蓋前置條件、…

managing-github-actions-secrets

為 PostHog 工作流程建立與更新 GitHub Actions 機密。用於新增 CI 機密、輪換現有機密、將工作流程連接至 API…

managing-github-actions-secrets

Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API…

managing-github-actions-secrets

Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API…

managing-github-actions-secrets

為 PostHog 工作流程建立與更新 GitHub Actions 機密。用於新增 CI 機密、輪換現有機密、將工作流程連接到 API…

managing-path-cleaning-rules

檢查URL路徑，並提議、測試、排序及應用專案層級的路徑清理規則，以便動態區段（如數字ID、UUID、slug、日期）被摺疊…

managing-path-cleaning-rules

Inspects URL paths and proposes, tests, orders, and applies project-level path cleaning rules so dynamic segments (numeric IDs, UUIDs, slugs, dates) collapse…

managing-path-cleaning-rules

Inspects URL paths and proposes, tests, orders, and applies project-level path cleaning rules so dynamic segments (numeric IDs, UUIDs, slugs, dates) collapse…

managing-path-cleaning-rules

檢查URL路徑，並提出、測試、排序及應用專案層級的路徑清理規則，使動態區段（數值ID、UUID、slug、日期）折疊…

managing-path-cleaning-rules

檢查URL路徑，並提議、測試、排序及應用專案層級的路徑清理規則，使動態區段（如數字ID、UUID、slug、日期）摺疊…

managing-reminders

建立並管理 PostHog 提醒事項 — 私密、人性化節奏的提示，按排程以應用程式內通知觸發，可選擇連結至 PostHog 資源。使用…

managing-reminders

Create and manage PostHog reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a PostHog resource. Use…

managing-reminders

建立並管理 PostHog 提醒事項 — 私密、人性化節奏的提示，會按排程以應用程式內通知觸發，並可選擇連結至 PostHog 資源。使用…

managing-streamlit-apps

Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, start and stop its sandbox, poll…

managing-subscriptions

管理 PostHog 訂閱 — 排程電子郵件、Slack 或 Webhook 傳送洞察或儀表板快照。當使用者想要訂閱某個…時使用。

managing-subscriptions

Manage PostHog subscriptions — scheduled email, Slack, or webhook deliveries of insight or dashboard snapshots, optionally with an AI-written summary attached…

managing-subscriptions

Manage PostHog subscriptions — scheduled email, Slack, or webhook deliveries of insight or dashboard snapshots, optionally with an AI-written summary attached…

managing-subscriptions

管理 PostHog 訂閱 — 排程電子郵件、Slack 或 Webhook 傳送洞察或儀表板快照。當使用者想要訂閱某項…時使用。

managing-subscriptions

管理 PostHog 訂閱 — 排程電子郵件、Slack 或 Webhook 傳送洞察或儀表板快照。當使用者想要訂閱某項…時使用。

Merge a PR into `master` through the Trunk merge queue and babysit it until it lands. Enqueue with a `/trunk merge` comment, then watch the `Trunk Merge Queue…

migrate-skills-yaml

將舊的平面 skills.yaml 格式轉換為新的每組檔案格式（含變體）。當 PR 或分支仍使用頂層 "skills:" 陣列時使用…

migrating-llm-gateway-callers

Migrates an LLM caller from services/llm-gateway to PostHog/ai-gateway. Use when adding a gateway caller, converting an existing Python gateway integration,…

modeling-activation-metrics

Build reusable activation models — an activation-rate metric and a per-user/per-account activated flag — on either PostHog data-warehouse views (HogQL) or an…

modeling-conversion-metrics

Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external…

modeling-dimension-tables

Build reusable dimension / lookup tables for a star schema — country/region, timezone, currency, date, plan/product, and other descriptive attributes — on…

modeling-product-usage-metrics

Build reusable product-usage and engagement models — retention, stickiness, and lifecycle — on either PostHog data-warehouse views (HogQL) or an external dbt…

modeling-revenue-metrics

Build reusable revenue models — MRR, ARR, gross revenue, new/expansion/contraction/churn, ARPU, LTV, and per-customer/per-account revenue — on either PostHog…

modeling-warehouse-foundations

Shared foundations for building reusable data models in PostHog, on either of two stacks: PostHog-native data-warehouse views / materialized views (HogQL, via…

modifying-taxonomic-filter

引導安全修改 TaxonomicFilter — PostHog 的多標籤選取器，用於事件、動作、屬性、群組等。前置實證…

modifying-taxonomic-filter

引導安全修改 TaxonomicFilter——PostHog 用於事件、動作、屬性、群組等多項目的多標籤選取器。前置實證…

modifying-taxonomic-filter

Guides safe modification of the TaxonomicFilter — PostHog's multi-tab picker for events, actions, properties, cohorts, and more. Front-loads the empirical…

modifying-taxonomic-filter

Guides safe modification of the TaxonomicFilter — PostHog's multi-tab picker for events, actions, properties, cohorts, and more. Front-loads the empirical…

monitoring-capture-service

使用 Grafana MCP 監控與診斷生產環境中的擷取服務（rust/capture）的指南。用於調查延遲、事件遺失、Kafka…

monitoring-capture-service

擷取服務（rust/capture/）是 PostHog 的 Rust HTTP 接收端點。它接收來自 SDK 的事件，套用配額/速率限制，並產生至 Kafka。三個部署角色以不同的 CAPTURE_MODE 設定執行相同的二進位檔。

monitoring-capture-service

Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production. Use when investigating latency, event loss, Kafka…

monitoring-capture-service

Guide for using the Grafana MCP to monitor and diagnose the capture service (rust/capture) in production. Use when investigating latency, event loss, Kafka…

monitoring-ingestion-pipeline

使用 Grafana MCP 監控與診斷生產環境中 Node.js 攝取管線工作者的指南。用於調查事件延遲、丟失、管線…

monitoring-ingestion-pipeline

攝取管道（nodejs/）是PostHog的Node.js事件處理層。它從Kafka（由捕獲服務產生）消費事件，通過處理步驟（人物解析、群組分配、屬性覆蓋等）運行，並將豐富後的事件發送到綁定ClickHouse的Kafka主題。

monitoring-ingestion-pipeline

Guide for using the Grafana MCP to monitor and diagnose the Node.js ingestion pipeline workers in production. Use when investigating event lag, drops, pipeline…

monitoring-ingestion-pipeline

Guide for using the Grafana MCP to monitor and diagnose the Node.js ingestion pipeline workers in production. Use when investigating event lag, drops, pipeline…

monthly-to-annual

Build the case for converting a PostHog monthly/PAYG customer to an annual prepaid credit plan. Pulls 12-24 months of invoice history from the data warehouse,…

monthly-to-annual

建立將PostHog月付/按用量付費客戶轉換為年度預付信用方案的論據。從資料倉儲中提取12至24個月的發票歷史記錄…

multitenant-down

拆除多租戶K8s堆疊，終止埠轉發，並清理工作節點Pod。在完成多租戶模式測試後使用。

multitenant-down

Tear down the multi-tenant K8s stack, kill port-forwards, and clean up worker pods. Use when done testing multi-tenant mode.

在本地 Kubernetes 上建置、部署並進行連接埠轉發多租戶控制平面。當您需要在多租戶模式下測試 duckgres 並按團隊劃分時使用…

Build, deploy, and port-forward the multi-tenant control plane on local Kubernetes. Use when you need to test duckgres in multi-tenant mode with per-team…

omnibus-instrument-error-tracking

Add PostHog error tracking to capture and monitor exceptions. Use after implementing features or reviewing PRs to ensure errors are tracked with stack traces…

omnibus-instrument-error-tracking

使用此技能來新增 PostHog 錯誤追蹤功能，以捕捉並監控應用程式中的例外狀況。請在實作功能或審查 PR 後使用，確保錯誤能搭配完整的堆疊追蹤與原始碼對應進行記錄。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何平台或語言。

omnibus-instrument-feature-flags

Add PostHog feature flags to gate new functionality. Use after implementing features or reviewing PRs to ensure safe rollouts with feature flag controls. Also…

omnibus-instrument-feature-flags

使用此技能來新增 PostHog 功能開關，以控制新功能或變更功能的發布。在實作功能或審查 PR 後使用，確保透過功能開關控制安全推出。若尚未安裝 PostHog，此技能也涵蓋初始 SDK 設定。支援任何平台或語言。

omnibus-instrument-integration

Add PostHog SDK integration to your application. Use when setting up PostHog for the first time or reviewing PRs that need PostHog initialization. Covers SDK…

omnibus-instrument-integration

使用此技能將 PostHog SDK 加入應用程式。適用於首次設定 PostHog，或審查需要初始化 PostHog 的 PR。涵蓋 SDK 安裝、提供者設定及基本配置。支援任何框架或語言。

omnibus-instrument-llm-analytics

Add PostHog LLM analytics to trace AI model usage. Use after implementing LLM features or reviewing PRs to ensure all generations are captured with token…

omnibus-instrument-llm-analytics

使用此技能在新增或修改的程式碼中加入 PostHog LLM 分析功能，以追蹤 AI 模型的使用情況。請在實作 LLM 功能或審查 PR 後使用，確保所有生成內容皆被記錄，包含 token 數量、延遲時間與成本。若尚未安裝 PostHog，此技能亦涵蓋初始 SDK 設定。支援任何供應商或框架。

omnibus-instrument-logs

Add PostHog log capture to track application logs. Use after implementing features or reviewing PRs to ensure meaningful log events are captured with…

omnibus-instrument-logs

使用此技能為新增或修改的程式碼加入 PostHog 日誌擷取。在實作功能或審查 PR 後使用，以確保能透過結構化屬性捕捉到有意義的日誌事件。若尚未設定 PostHog 日誌匯出，此技能也涵蓋初始的 OTLP 匯出器設定。支援任何平台或語言。

omnibus-instrument-product-analytics

使用此技能來新增產品分析事件（capture calls），以追蹤新程式碼或修改程式碼中有意義的使用者操作。在實作功能或審查 PR 後使用，以確保關鍵使用者行為被記錄

omnibus-instrument-product-analytics

Add PostHog product analytics events to track user behavior. Use after implementing new features or reviewing PRs to ensure meaningful user actions are…

optimizing-clickhouse-and-hogql-queries

用於優化 ClickHouse 和 HogQL 查詢的工作流程。當 HogQL 查詢、查詢執行器、洞察或報表速度過慢時使用；當手寫的 ClickHouse…

optimizing-clickhouse-and-hogql-queries

用於優化 ClickHouse 和 HogQL 查詢的工作流程。當 HogQL 查詢、查詢執行器、洞察或報表過慢時使用；當手寫的 ClickHouse…

planning-user-interviews

在 PostHog 中規劃使用者訪談主題——選擇目標對象（群組、電子郵件或 PostHog 獨特 ID）、草擬訪談問題，並準備語音代理…

planning-user-interviews

Plan a user interview topic in PostHog — pick who to target (cohort, emails, or PostHog distinct IDs), draft what to ask about, and prepare the voice-agent…

planning-user-interviews

在 PostHog 中規劃使用者訪談主題——選擇目標對象（群組、電子郵件或 PostHog 獨特 ID）、草擬訪談問題，並準備語音代理……

planning-voice-agent-user-interviews

規劃一輪由PostHog的AI語音代理（「機器人訪談員」）執行的用戶訪談——即自動化語音代理訪談產品。捕捉…

planning-voice-agent-user-interviews

Plan a round of user interviews conducted by PostHog's AI voice agent (a "robo interviewer") — the automated voice-agent interview product. Captures a…

planning-voice-agent-user-interviews

規劃一輪由PostHog的AI語音代理（「機器人訪談員」）執行的用戶訪談——即自動化語音代理訪談產品。捕捉…

playwright-test

撰寫一個 playwright 測試，確保它能正常執行且不具不穩定性。

playwright-test

撰寫一個 playwright 測試，確保它能正常執行且不具不穩定性。

playwright-test

Write a playwright test, make sure it runs, and is not flaky.

playwright-test

Write a playwright test, make sure it runs, and is not flaky.

porting-code-prs

Recreate open PostHog/code pull requests as PostHog/posthog PRs against the imported products/desktop/ tree, preserving commit authorship. Use when asked to…

post-newsletter

將 Substack 電子報文章轉換為原生的 posthog.com 電子報檔案。從 Substack URL 擷取內容，並以正確的前置設定格式化…

post-newsletter

Convert a Substack newsletter post into a native posthog.com newsletter file. Fetches the content from a Substack URL, formats it with correct frontmatter and…

posthog-debugger

Debug and inspect PostHog implementations on any website. Use this skill when a user wants to understand how PostHog is implemented on a page, troubleshoot…

posthog-debugger

在任何網站上除錯和檢查 PostHog 實作。當使用者想了解頁面上 PostHog 的實作方式、進行疑難排解時，請使用此技能。

posthog-desktop

Scopes work to the desktop app at products/desktop — a nested standalone pnpm/turbo/Biome workspace imported from PostHog/code, not part of the root frontend…

posthog-inbound-leads

posthog-instrumentation

自動將 PostHog 分析工具整合至程式碼中。當使用者要求加入追蹤、設定事件監測、添加分析功能或實作功能時觸發…

posthog-instrumentation

自動化跨多個框架的PostHog分析、事件追蹤與功能開關檢測。支援JavaScript/TypeScript、React、Python及Node.js，並提供框架專屬的設定模式。涵蓋三大核心功能：含自訂屬性的事件擷取、用於逐步發布的功能開關評估，以及使用者識別。能偵測現有PostHog設定，在不重複配置的情況下加入檢測功能。包含事件命名慣例、屬性...的最佳實踐。

posthog-onboarding

Help existing PostHog customers improve their PostHog instance. Triggers on "help [customer] improve their PostHog setup", "audit [company]'s PostHog…

posthog-onboarding

協助現有 PostHog 客戶改善他們的 PostHog 實例。觸發條件為「幫助 [客戶] 改善他們的 PostHog 設定」、「稽核 [公司] 的 PostHog…」

posthog-onboarding-lead-research

研究和資格審查PostHog入職團隊的推薦潛在客戶。當TAE收到來自入職團隊的潛在客戶並需要進行完整研究時，使用此技能…

posthog-pls-big-fish

研究、資格審查，並建議針對 PostHog 大客戶產品引導式潛在客戶的推廣方式——這些是使用 PostHog 免費方案的大型公司（500 人或 1000 人以上員工），但尚未……

posthog-pls-transition-leads

為PostHog產品引導的潛在客戶進行資格審核並草擬外展內容，這些客戶正面臨帳單轉換——無論是新創計畫客戶的免費額度即將到期，還是…

posthog-survey-creator

透過引導式對話在 PostHog 中建立和配置調查。當使用者想要建立調查、收集使用者回饋、執行…時，使用此技能。

posthog-survey-creator

Create and configure surveys in PostHog through guided conversation. Use this skill when a user wants to create a survey, collect user feedback, run…

promote-to-prod

Promote the duckgres control-plane image to prod from the CLI — resolve the built image ref from the charts state file, fire the charts Promote-to-Prod…

Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow…

一個由專業代理組成的團隊獨立審查當前分支的變更，並比對真實事件模式。他們的發現會經過匯聚分析，整合成單一報告。

多智能體QA審查團隊，用於程式碼變更。當使用者要求「審查我的程式碼」、「執行QA」、「qa-team」、「審查此分支」、「程式碼…」時，應使用此技能。

Multi-agent QA review team for code changes. This skill should be used when the user asks to "review my code", "run QA", "qa-team", "review this branch", "code…

Multi-agent QA review team for code changes. This skill should be used when the user asks to "review my code", "run QA", "qa-team", "review this branch", "code…

query-clickhouse-via-metabase

PostHog 的生產環境 ClickHouse 叢集可透過內部 Metabase 實例進行臨時分析。這兩個 Metabase 都位於 AWS ALB 後方，並使用 Cognito OAuth，因此驗證需透過 SSO 閘道——僅靠 Metabase API 金鑰無法運作。

query-clickhouse-via-metabase

Run ClickHouse `system.query_log` analysis via the internal Metabase API. Use when investigating slow queries, materialization candidates, per-team query…

query-clickhouse-via-metabase

Run ClickHouse `system.query_log` analysis via the internal Metabase API. Use when investigating slow queries, materialization candidates, per-team query…

query-clickhouse-via-metabase

Run ClickHouse `system.query_log` analysis via the internal Metabase API. Use when investigating slow queries, materialization candidates, per-team query…

HogQL 查詢範例與 PostHog 資料的參考資料。在撰寫 SQL 查詢以尋找分析模式（趨勢、漏斗、留存率等）時閱讀。

HogQL 查詢範例及 PostHog 資料的

HogQL 查詢範例與 PostHog 資料的參考資料。在撰寫 SQL 查詢以尋找分析模式（趨勢、漏斗、留存率等）時閱讀。

querying-local-postgres

對本地 Postgres 應用程式資料庫執行唯讀 SQL（SELECT、EXPLAIN、EXPLAIN ANALYZE on SELECT）。預設本地 URL…

querying-local-postgres

Run read-only SQL against the local Postgres app database (SELECT, EXPLAIN, EXPLAIN ANALYZE on SELECT). Default local URL…

querying-local-postgres

Run read-only SQL against the local Postgres app database (SELECT, EXPLAIN, EXPLAIN ANALYZE on SELECT). Default local URL…

querying-local-postgres

對本機 Postgres 應用程式資料庫執行唯讀 SQL（SELECT、EXPLAIN、EXPLAIN ANALYZE 於 SELECT）。預設本機 URL…

querying-posthog-data

在撰寫任何 HogQL/SQL 或對 PostHog 呼叫 execute-sql 之前，必須先閱讀此內容。每當使用者想要搜尋、查找或進行複雜的彙總時使用…

querying-posthog-data

在撰寫任何 HogQL/SQL 或對 PostHog 呼叫 execute-sql 之前，必須先閱讀此內容。每當使用者想要搜尋、查找或進行複雜的彙總時使用…

querying-posthog-data

在撰寫任何 HogQL/SQL 或對 PostHog 執行 execute-sql 前，必須先閱讀此內容。每當使用者想要搜尋、查找或進行複雜聚合時使用…

querying-tophog

查詢 tophog — ClickHouse 中資料攝取管線的高負載儲存 — 以識別熱門或耗費資源的參與者（team_id、distinct_id、session_id、partition）…

querying-tophog

Query tophog — the ingestion pipeline's heavy-hitter store in ClickHouse — to identify hot or expensive actors (team_id, distinct_id, session_id, partition)…

querying-tophog

Query tophog — the ingestion pipeline's heavy-hitter store in ClickHouse — to identify hot or expensive actors (team_id, distinct_id, session_id, partition)…

querying-tophog

查詢 tophog — ClickHouse 中攝取管線的高流量儲存 — 以識別熱門或高成本的行為者（team_id、distinct_id、session_id、partition）…

診斷並修復 React 程式碼庫的健康問題。適用於審查 React 程式碼、修復效能問題、稽核安全性或改善程式碼品質。

Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.

Diagnose and fix React codebase health issues. Use when reviewing React code, fixing performance problems, auditing security, or improving code quality.

診斷並修復 React 程式碼庫的健康問題。在審查 React 程式碼、修復效能問題、稽

resolving-ingestion-warnings

Diagnoses and resolves PostHog ingestion warnings — problems recorded while ingesting events (dropped events, rejected person merges, oversized payloads,…

result-vs-exceptions

選擇 Result 型別與拋出例外之間的程式碼審查指南。可復原、預期的失敗應以 Result 值回傳；僅…

result-vs-exceptions

Code review guide for choosing between Result types and thrown exceptions. Recoverable, expected failures should be returned as Result values; only…

review-hog-authoring

How to author custom ReviewHog skills — the review perspectives, blind-spot checks, and validation criteria that drive ReviewHog's automated PR reviews. Use…

review-hog-blind-spots-general

The general blind-spot check for ReviewHog — the final sweep that runs after every enabled review perspective has reviewed a chunk. Hunts for real, high-value…

review-hog-perspective-contracts-security

The Contracts & Security review perspective for ReviewHog. Verifies that changed code is safe and maintains compatibility — API contracts and breaking changes,…

review-hog-perspective-logic-correctness

The Logic & Correctness review perspective for ReviewHog. Verifies that changed code does what it is supposed to do — business logic, edge cases, data…

review-hog-perspective-performance-reliability

The Performance & Reliability review perspective for ReviewHog. Verifies that changed code will perform and hold up in production — resource efficiency, error…

review-hog-validation-criteria

The validation criteria for ReviewHog — the bar for deciding whether a flagged PR issue is worth keeping. Keeps real, user-affecting correctness / security /…

reviewing-personhog-protocol

The full review process for personhog coordination-protocol changes — leases, fencing, handoffs, supervisors, failure budgets, warming, and changelog…

啟動、檢查並驅動 PostHog 開發堆疊。用於此儲存庫的 /run 和 /verify — 當被要求啟動 PostHog 時，檢查堆疊是否健康…

Start, inspect, and drive the PostHog dev stack. Use for /run and /verify on this repo — when asked to launch PostHog, check whether the stack is healthy,…

Start, inspect, and drive the PostHog dev stack. Use for /run and /verify on this repo — when asked to launch PostHog, check whether the stack is healthy,…

啟動、檢查並驅動 PostHog 開發堆疊。用於此儲存庫的 /run 和 /verify — 當被要求啟動 PostHog 時，檢查堆疊是否健康…

running-ci-preflight

Catch the deterministic CI failures reachable from your diff before pushing, with `hogli ci:preflight`. Use when the pre-push hook blocks a push, before…

running-ci-preflight

Catch the deterministic CI failures reachable from your diff before pushing, with `hogli ci:preflight`. Use when the pre-push hook blocks a push, before…

running-ci-preflight

Catch the deterministic CI failures reachable from your diff before pushing, with `hogli ci:preflight`. Use when the pre-push hook blocks a push, before…

running-ci-preflight

Catch the deterministic CI failures reachable from your diff before pushing, with `hogli ci:preflight`. Use when the pre-push hook blocks a push, before…

safety-and-boundaries

Hard rules — what the Agent Builder MUST NOT do regardless of user request. Load IMMEDIATELY if a request feels like it crosses into raw-secret handling,…

safety-and-boundaries

硬性規則 — 無論使用者要求為何，Agent Builder 絕對不能做的事。若請求感覺涉及原始機密處理，應立即載入…

在場景的<SceneTitleSection>上方新增或編輯SceneMenuBar的慣例。用於新增選單項目、在選單間移動項目、設定權限…

Conventions for adding or editing the SceneMenuBar above a scene's <SceneTitleSection>. Use when adding new menu items, moving items between menus, gating…

Conventions for adding or editing the SceneMenuBar above a scene's <SceneTitleSection>. Use when adding new menu items, moving items between menus, gating…

在場景的<SceneTitleSection>上方新增或編輯SceneMenuBar的慣例。用於新增選單項目、在選單間移動項目、設定權限…

針對程式碼進行重點安全審計，旨在找出實際可被利用的漏洞，並抑制理論性的發現。當使用者要求「審計」時使用…

Focused security audit of code, calibrated to surface real exploitable bugs and suppress theoretical findings. Use when the user asks to "audit",…

Focused security audit of code, calibrated to surface real exploitable bugs and suppress theoretical findings. Use when the user asks to "audit",…

針對程式碼進行重點安全審計，旨在找出實際可被利用的漏洞，並抑制理論性的發現。當使用者要求「審計」時使用…

sending-notifications

如何從 PostHog 後端程式碼發送即時應用內通知。在將通知整合到新功能、連接通知來源時使用…

sending-notifications

How to send real-time in-app notifications from PostHog backend code. Use when integrating notifications into a new feature, wiring up a notification source…

sending-notifications

How to send real-time in-app notifications from PostHog backend code. Use when integrating notifications into a new feature, wiring up a notification source…

sending-notifications

如何從 PostHog 後端程式碼發送即時應用內通知。在將通知整合到新功能、

setting-feature-flags-in-storybook

Use when writing a Storybook story for a component gated on a feature flag — boolean flags or multivariate/experiment-arm variants. Covers the `featureFlags`…

setting-feature-flags-in-storybook

Use when writing a Storybook story for a component gated on a feature flag — boolean flags or multivariate/experiment-arm variants. Covers the `featureFlags`…

setting-feature-flags-in-storybook

Use when writing a Storybook story for a component gated on a feature flag — boolean flags or multivariate/experiment-arm variants. Covers the `featureFlags`…

setting-feature-flags-in-storybook

Use when writing a Storybook story for a component gated on a feature flag — boolean flags or multivariate/experiment-arm variants. Covers the `featureFlags`…

setting-up-a-custom-rest-source

通過編寫 JSON 清單，將任意 REST API 作為自訂來源連接到 PostHog 資料倉儲，無需為每個來源編寫程式碼。當使用者指向…

setting-up-a-custom-rest-source

Connect an arbitrary REST API to the PostHog data warehouse as a Custom source by authoring a JSON manifest, with no per-source code. Use when the user points…

setting-up-a-custom-rest-source

通過編寫 JSON 清單，將任意 REST API 作為自訂來源連接到 PostHog 資料倉儲，無需為每個來源編寫程式碼。當使用者指向…

setting-up-a-data-warehouse-source

當使用者首次想將外部資料來源連接到 PostHog 的資料倉儲時，請使用此技能。設定流程包含特定的三個步驟（精靈 → 資料庫結構 → 建立）——跳過步驟會導致來源失敗並讓使用者感到困惑。

setting-up-a-data-warehouse-source

當使用者首次想將外部資料來源連接到 PostHog 的資料倉儲時，請使用此技能。設定流程包含特定的三個步驟（精靈 → 資料庫結構 → 建立）——跳過步驟會導致來源失敗並讓使用者感到困惑。

setting-up-a-data-warehouse-source

當使用者首次想將外部資料來源連接到 PostHog 的資料倉儲時，請使用此技能。設定流程包含特定的三個步驟（精靈 → 資料庫結構 → 建立）——跳過步驟會導致來源失敗並讓使用者感到困惑。

setting-up-a-data-warehouse-source

Guide the user through connecting a new data warehouse source — Postgres, MySQL, Stripe, Hubspot, MongoDB, Salesforce, BigQuery, Snowflake, and so on. Use when…

setting-up-a-data-warehouse-source

Guide the user through connecting a new data warehouse source — Postgres, MySQL, Stripe, Hubspot, MongoDB, Salesforce, BigQuery, Snowflake, and so on. Use when…

setting-up-data-catalog

Populates and maintains a project's data catalog (semantic layer): canonical metrics, trust marks (certifications) on warehouse tables/views, and reviewed…

setting-up-devbox

引導 PostHog 工程師完成啟動、連接、執行命令，以及將本地程式碼鏡像到遠端開發盒（一個運行中的 Coder 工作區）的流程。

setting-up-devbox

Guide a PostHog engineer through spinning up, connecting to, running commands on, and mirroring local code to a remote devbox (a Coder workspace running the…

setting-up-devbox

Guide a PostHog engineer through spinning up, connecting to, running commands on, and mirroring local code to a remote devbox (a Coder workspace running the…

setting-up-devbox

引導 PostHog 工程師完成啟動、連接、執行命令，以及將本地程式碼鏡像到遠端 devbox（一個運行中的 Coder 工作區）的流程。

setting-up-support-slack-locally

Connect a real Slack workspace to local PostHog Conversations (the SupportHog Slack app) so Slack messages become support tickets and replies post back. Use…

setup-web-tests

Set up Python test environment in Claude Code for web where flox is unavailable. Use when you need to run backend tests and `uv sync` fails due to Python…

setup-web-tests

Set up Python test environment in Claude Code for web where flox is unavailable. Use when you need to run backend tests and `uv sync` fails due to Python…

setup-web-tests

Set up Python test environment in Claude Code for web where flox is unavailable. Use when you need to run backend tests and `uv sync` fails due to Python…

setup-web-tests

Set up Python test environment in Claude Code for web where flox is unavailable. Use when you need to run backend tests and `uv sync` fails due to Python…

Signals 是 PostHog 透過監控客戶產品資料（來自錯誤追蹤、網頁分析、實驗、工作階段重播等多個來源）所產生的自動化觀察結果。每個 signal 都是一段簡短的自然語言描述，說明值得注意的事件（例如「/checkout 上的錯誤率飆升 3 倍」）。

How to query the document_embeddings table for raw signal data using HogQL. Use when you need to perform semantic search over signals, fetch every signal that…

How to query the document_embeddings table for raw signal data using HogQL. Use when you need to perform semantic search over signals, fetch every signal that…

如何使用 HogQL 查詢 document_embeddings 表中的 signals 資料。當需要對 signals 進行語意搜尋、擷取報告所需的 signals 時閱讀…

Signals 是 PostHog 透過監控客戶產品資料（涵蓋錯誤追蹤、網頁分析、實驗、工作階段重播等多個來源）自動產生的觀測結果。每個 signal 都是一段簡短的自然語言描述，用來標記值得注意的事件（例如「/checkout 頁面的錯誤率飆升 3 倍」）。

signals-scout-ai-observability

Signals scout for PostHog AI observability。監控LLM追蹤中的成本、延遲、錯誤、數量及評估效能回歸，並按維度進行切片分析…

signals-scout-ai-observability

Signals scout for PostHog AI observability. Watches LLM traces for cost, latency, error, volume, and eval-performance regressions, sliced by the dimensions it…

signals-scout-ai-observability

Focused Signals scout for PostHog projects using AI observability. Rotates through a set of lenses — cost, latency, errors, volume, eval performance,…

signals-scout-ai-observability

Signals scout for PostHog AI observability。監控LLM追蹤中的成本、延遲、錯誤、流量及評估效能回歸，並按維度進行切片分析…

signals-scout-ai-observability

專注於使用AI可觀測性來偵測PostHog專案中的訊號。輪流透過一系列視角——成本、延遲、錯誤、流量、評估表現……

signals-scout-anomaly-detection

監控專案中最常查看的儀表板和洞察，偵測近期異常——包括突發、下降、平線及趨勢中斷，並根據……進行評分。

signals-scout-anomaly-detection

Signals scout that watches a PostHog project's most-viewed dashboards and insights for recent anomalies — sudden bursts, drops, flat-lines, and trend breaks at…

signals-scout-anomaly-detection

監控專案中最常查看的儀表板與洞察，偵測近期異常——包括突發、下降、平線及趨勢中斷，並根據……進行評分。

signals-scout-anomaly-detection

監控 PostHog 專案中最常查看的儀表板與洞察，偵測近期異常——包括突發暴增、驟降、平線及趨勢中斷等…

signals-scout-apm

Signals scout for PostHog 分散式追蹤（APM / OpenTelemetry spans）。監控每個（服務、操作）的 RED 指標——錯誤率、p95 延遲、請求……

signals-scout-apm

Signals scout for PostHog 分散式追蹤（APM / OpenTelemetry spans）。監控每個（服務、操作）的 RED 指標——錯誤率、p95 延遲、請求……

signals-scout-apm

Signals scout for PostHog distributed tracing (APM / OpenTelemetry spans). Watches RED metrics per (service, operation) — error rate, p95 latency, request…

signals-scout-conversations

Signals scout for the PostHog Conversations (support inbox) product. Watches the `$conversation_*` ticket-lifecycle events for support-delivery regressions —…

signals-scout-csp-violations

Signals scout for Content Security Policy violation reports. Watches `$csp_violation` events for blocked-URL clusters, per-directive bursts, post-deploy…

signals-scout-csp-violations

Signals scout for Content Security Policy violation reports. Watches `$csp_violation` events for blocked-URL clusters, per-directive bursts, post-deploy…

signals-scout-csp-violations

Signals scout for Content Security Policy violation reports. Watches `$csp_violation` events for blocked-URL clusters, per-directive bursts, post-deploy…

signals-scout-csp-violations

Focused Signals scout for PostHog projects collecting Content Security Policy (CSP) violation reports. Watches `$csp_violation` events for fresh blocked-URL…

signals-scout-csp-violations

Focused Signals scout for PostHog projects collecting Content Security Policy (CSP) violation reports. Watches `$csp_violation` events for fresh blocked-URL…

signals-scout-customer-analytics

Signals scout for PostHog Customer analytics（帳戶）。監控每個帳戶的參與度，以識別流失風險模式——參與度驟降、休眠、關鍵用戶離職……

signals-scout-customer-analytics

Signals scout for PostHog Customer analytics (Accounts). Watches per-account engagement for churn-risk shapes — engagement cliffs, dormancy, champion departure…

signals-scout-customer-analytics

Signals scout for PostHog Customer analytics（帳戶）。監控每個帳戶的參與度，以識別流失風險模式——參與度驟降、休眠、關鍵用戶離職……

signals-scout-data-pipelines

Signals scout for PostHog 資料管線 — CDP 目的地與轉換、批次匯出及 hog 流程。監控傳遞失敗、效能降級…

signals-scout-data-pipelines

Signals scout for PostHog data pipelines — CDP destinations and transformations, batch exports, and hog flows. Watches for delivery failures, degraded…

signals-scout-data-pipelines

Focused Signals scout for PostHog projects moving data through pipelines. Watches the three delivery surfaces — CDP destinations and transformations (hog…

signals-scout-data-pipelines

Signals scout for PostHog 資料管線 — CDP 目的地與轉換、批次匯出及 hog 流程。監控傳遞失敗、效能降級…

signals-scout-data-pipelines

專注於PostHog專案中透過管道傳輸資料的Signals偵測工具。監控三個傳遞層面：CDP目標與轉換（hog…

signals-scout-data-warehouse

專注於PostHog專案的Signals偵察，用於將外部資料匯入資料倉儲。監控匯入端——外部資料來源、各資料表的同步狀態……

signals-scout-data-warehouse

Focused Signals scout for PostHog projects importing external data into the warehouse. Watches the import side — external data sources, their per-table sync…

signals-scout-data-warehouse

專注於PostHog專案中將外部資料匯入資料倉儲的Signals偵測工具。監控匯入端——外部資料來源、各資料表的同步狀態……

signals-scout-error-tracking

Signals scout for PostHog error tracking. Watches `$exception` bursts, stuck loops, multi-fingerprint clusters, and status regressions, and files each…

signals-scout-error-tracking

Signals scout for PostHog error tracking. Watches `$exception` bursts, stuck loops, multi-fingerprint clusters, and status regressions, and files each…

signals-scout-error-tracking

Focused Signals scout for PostHog projects using error tracking. Watches `$exception` bursts, stuck loops, multi-fingerprint clusters, status regressions, and…

signals-scout-error-tracking

Signals scout for PostHog error tracking. Watches `$exception` bursts, stuck loops, multi-fingerprint clusters, and status regressions, and files each…

signals-scout-error-tracking

Focused Signals scout for PostHog projects using error tracking. Watches `$exception` bursts, stuck loops, multi-fingerprint clusters, status regressions, and…

signals-scout-experiments

專注於PostHog專案中執行A/B實驗的Signals偵測工具。監控進行中的實驗是否存在有效性威脅（樣本比例不匹配、多變量…）

signals-scout-experiments

PostHog A/B 實驗的信號偵察員。監控進行中的實驗是否存在有效性威脅（樣本比例不匹配、污染、曝光停滯、中途運行……）

signals-scout-experiments

Signals scout for PostHog A/B experiments. Watches running experiments for validity threats (sample ratio mismatch, contamination, exposure stalls, mid-run…

signals-scout-experiments

Focused Signals scout for PostHog projects running A/B experiments. Watches running experiments for validity threats (sample ratio mismatch, multi-variant…

signals-scout-experiments

Signals scout for PostHog A/B experiments. Watches running experiments for validity threats (sample ratio mismatch, contamination, exposure stalls, mid-run…

signals-scout-feature-flags

Signals scout for PostHog feature flags. Watches the flag roster and the `$feature_flag_called` stream for evaluation cliffs, ghost flags,…

signals-scout-feature-flags

Signals scout for PostHog feature flags. Watches the flag roster and the `$feature_flag_called` stream for evaluation cliffs, ghost flags,…

signals-scout-feature-flags

Signals scout for PostHog feature flags. Watches the flag roster and the `$feature_flag_called` stream for evaluation cliffs, ghost flags,…

signals-scout-feature-flags

Focused Signals scout for PostHog projects using feature flags. Watches the flag roster and the `$feature_flag_called` evaluation stream for contradictions…

signals-scout-feature-flags

Focused Signals scout for PostHog projects using feature flags. Watches the flag roster and the `$feature_flag_called` evaluation stream for contradictions…

signals-scout-general

跨產品信號偵察員。尋找跨產品關聯，並探索各產品專屬偵察員未涵蓋的領域。

signals-scout-general

跨產品信號偵察員。尋找跨產品關聯，並探索各產品專屬偵察員未涵蓋的領域。

signals-scout-general

Cross-product Signals scout. Looks for cross-product correlations and explores the surfaces the per-product specialist scouts don't cover.

signals-scout-general

General Signals scout for PostHog projects. Cross-product explorer that scans a team's project and emits findings into the Signals inbox. Sibling…

signals-scout-general

PostHog專案的一般訊號偵察員。跨產品探索器，掃描團隊專案並將發現結果發送至訊號收件匣。同級…

signals-scout-health-checks

Signals scout 透過 PostHog 自身的健康檢查進行偵測。讀取專案中的活躍健康問題，按類型分類，根據影響範圍加權，並將問題歸檔…

signals-scout-health-checks

Signals scout over PostHog's own health checks. Reads the project's active health issues, bundles them by kind, weights by blast radius, and files the ones…

signals-scout-health-checks

Focused Signals scout for PostHog setup health. Reads the project's active health issues — the deterministic findings of PostHog's own health checks (no live…

signals-scout-health-checks

Signals scout 透過 PostHog 自身的健康檢查進行偵測。讀取專案中的活躍健康問題，按類型分類，根據影響範圍加權，並將問題歸檔…

signals-scout-health-checks

專注於PostHog設定健康狀態的Signals偵測工具。讀取專案中的活躍健康問題——PostHog自身健康檢查的確定性結果（無即時…

signals-scout-inbox-validation

針對收件匣本身的後續 Signals 偵查。在部署驗證期結束後，重新衡量近期已解決報告背後的問題，並在…時提交報告。

signals-scout-inbox-validation

Follow-up Signals scout for the inbox itself. After a deployment soak window, re-measures the problems behind recently resolved reports and files a report when…

signals-scout-inbox-validation

Follow-up scout for the Signals inbox itself. Watches reports that recently transitioned to resolved (an implementation PR merged) and, after a deployment soak…

signals-scout-inbox-validation

針對收件匣本身的後續 Signals 偵查。在部署驗證期結束後，重新衡量近期已解決報告背後的問題，並在…時提交報告。

signals-scout-inbox-validation

針對 Signals 收件匣本身的後續偵查。監控近期轉為已解決（實作 PR 已合併）的報告，並在部署觀察期後…

signals-scout-ingestion-warnings

Signals scout for ingestion warnings — events and person/group updates that were dropped, mangled, or partially rejected during ingestion. Watches the warnings…

signals-scout-insight-alerts

針對專案自身配置的洞察警報進行信號偵查。讀取每條警報近期的觸發歷史，並為人類可能遺漏的觸發事件提交報告…

signals-scout-insight-alerts

Signals scout over a project's own configured insight alerts. Reads each alert's recent firing history and files a report for the firings a human likely missed…

signals-scout-insight-alerts

針對專案自身配置的洞察警示進行信號偵查，讀取每個警示的近期觸發歷史，並為人類可能遺漏的觸發事件提交報告。

signals-scout-llm-analytics

Focused Signals scout for PostHog projects using LLM analytics. Watches `$ai_generation`, `$ai_evaluation`, `$ai_trace` and related events for cost spikes,…

signals-scout-logs

PostHog 日誌的信號偵查員。監控流量突增、嚴重程度分佈變化、服務靜默、新訊息模式以及與追蹤相關的突發狀況。

signals-scout-logs

Focused Signals scout for PostHog projects using logs. Watches for volume bursts, severity-distribution shifts, service silence, fresh message patterns, and…

signals-scout-logs

Signals scout for PostHog logs. Watches for volume bursts, severity-distribution shifts, service silence, fresh message patterns, and trace-correlated bursts.

signals-scout-logs

PostHog 日誌的信號偵查員。監控流量暴增、嚴重程度分佈變化、服務靜默、新訊息模式以及與追蹤相關的暴增。

signals-scout-logs

專注於使用日誌對 PostHog 專案進行訊號偵測。監控流量突增、嚴重程度分佈變化、服務靜默、新訊息模式等…

signals-scout-mcp-tool-calls

Signals scout for PostHog MCP 工具呼叫。監控 $mcp_tool_call 遙測資料，找出需要改進的工具——高失敗率、廣泛影響、重試/頻繁呼叫……

signals-scout-mcp-tool-calls

Signals scout for PostHog MCP tool calls. Watches $mcp_tool_call telemetry for tools that need improvement — high, broad-reach failure rates, retry/hammering…

signals-scout-mcp-tool-calls

Signals scout for PostHog MCP 工具呼叫。監控 $mcp_tool_call 遙測資料，找出需要改進的工具——高失敗率、廣泛影響、重試/頻繁操作……

signals-scout-observability-gaps

可觀測性缺口信號偵查員 — 重大事件量缺乏洞察、儀表板或警報覆蓋。提交報告建議新增洞察…

signals-scout-observability-gaps

Signals scout for observability gaps — significant event volumes with no insight, dashboard, or alert coverage. Files a report recommending new insights,…

signals-scout-observability-gaps

Focused Signals scout for finding observability gaps in PostHog itself — significant event volumes the team isn't tracking, custom events with no insight or…

signals-scout-observability-gaps

可觀測性缺口信號偵察——大量重要事件缺乏洞察、儀表板或警報覆蓋。生成報告建議新增洞察…

signals-scout-observability-gaps

專注於在PostHog自身中尋找可觀測性漏洞的信號偵察員——團隊未追蹤的重大事件量、缺乏洞察的自訂事件，以及…

signals-scout-product-analytics

核心產品分析流程的信號偵測——漏斗、留存、生命週期、黏性與路徑。監控團隊已儲存的流程以獲取衍生率…

signals-scout-product-analytics

Signals scout for core product-analytics flows — funnels, retention, lifecycle, stickiness, and paths. Watches the team's saved flows for a derived-rate…

signals-scout-product-analytics

核心產品分析流程的信號偵察工具——涵蓋漏斗、留存、生命週期、黏著度及路徑分析。監控團隊已儲存的流程以獲取衍生率…

signals-scout-replay-vision

Signals 偵測器用於 PostHog Replay Vision 掃描器。監控已啟用的掃描器持續觀察（吞吐量/配額懸崖），並確保它們在總體上所見的…

signals-scout-replay-vision

Signals scout for PostHog Replay Vision scanners. Watches that enabled scanners keep observing (throughput / quota cliffs) and that what they see in aggregate…

signals-scout-replay-vision

Focused Signals scout for PostHog projects running Replay Vision scanners — the standing LLM probes that watch session recordings and write…

signals-scout-replay-vision

Signals 偵測器用於 PostHog Replay Vision 掃描器。監控已啟用的掃描器持續觀察（吞吐量/配額懸崖），並確保它們在總體上所見的…

signals-scout-replay-vision

專注於PostHog專案中運行Replay Vision掃描器的Signals偵察工具——這些持續運作的LLM探針會監控會話錄製並記錄…

signals-scout-revenue-analytics

Signals scout for PostHog 營收分析。監控上游故障（Stripe 同步停滯、捕獲回歸）、配置漂移及目標未達升級通知…

signals-scout-revenue-analytics

Focused Signals scout for PostHog projects using revenue analytics. Watches the derived revenue product for upstream failures (Stripe sync stalls, capture…

signals-scout-revenue-analytics

Signals scout for PostHog revenue analytics. Watches for upstream failures (Stripe sync stalls, capture regressions), config drift, and goal-miss escalations,…

signals-scout-revenue-analytics

PostHog 營收分析的訊號偵測工具。監控上游故障（Stripe 同步停滯、資料擷取回歸）、設定漂移及目標未達升級通報…

signals-scout-revenue-analytics

專注於使用收入分析來偵測PostHog專案的Signals偵察工具。監控衍生收入產品中的上游故障（Stripe同步停滯、擷取…

signals-scout-session-replay

Signals scout for PostHog 工作階段重播。監控工作階段是否持續錄製（捕捉斷崖），以及錄製中的摩擦點——憤怒/無效點擊叢集、…

signals-scout-session-replay

Signals scout for PostHog session replay. Watches that sessions keep recording (capture cliffs) and that friction inside recordings — rage/dead-click clusters,…

signals-scout-session-replay

Focused Signals scout for PostHog projects using session replay. Watches two promises the replay product makes: that sessions are actually being recorded…

signals-scout-session-replay

Signals scout for PostHog session replay。監控工作階段是否持續錄製（捕捉斷崖），以及錄製中的摩擦——憤怒/無效點擊叢集、…

signals-scout-session-replay

針對使用工作階段重播的 PostHog 專案，提供聚焦的 Signals 偵測功能。監控重播產品所承諾的兩項保證：工作階段確實正在被記錄…

signals-scout-skills-store

團隊 PostHog 技能商店的技能衛生偵察員，完全透過 MCP 技能工具讀取。監控近期變更的技能——以及緩慢輪替的…

signals-scout-skills-store

Skill-hygiene scout for the team's PostHog skills store, read entirely via the MCP skill tools. Watches recently-changed skills — plus a slow rotation over the…

signals-scout-skills-store

團隊 PostHog 技能商店的技能衛生偵察員，完全透過 MCP 技能工具讀取。監控近期變更的技能——以及緩慢輪替的…

signals-scout-surveys

Signals scout for PostHog surveys。監控活躍問卷的分數衰退、回應量下降、放棄率飆升與目標偏移，並彙整…

signals-scout-surveys

Signals scout for PostHog surveys. Watches active surveys for score regressions, response-volume drops, abandonment spikes, and targeting drift, and aggregates…

signals-scout-surveys

Focused Signals scout for PostHog projects running surveys. Watches active surveys for score regressions (NPS / CSAT / rating drops), response-volume drops,…

signals-scout-surveys

Signals scout for PostHog surveys。監控活躍問卷的分數衰退、回應量下降、放棄率飆升與目標偏移，並彙整…

signals-scout-surveys

專注於運行調查的PostHog專案的Signals偵察員。監控活躍調查中的分數倒退（NPS / CSAT / 評分下降）、回應量下降等情況。

signals-scout-tasks

Signals scout for PostHog Tasks, the agent work items a project runs. Two lenses: delivery health (runs failing, clustered by repository and error class, and…

signals-scout-web-analytics

Signals scout for PostHog 網路流量。監控各渠道的會話量、歸因中斷情況，以及著陸頁健康度（跳出率 / 404 步驟），對比…

signals-scout-web-analytics

Signals scout for PostHog web traffic. Watches per-channel session volume, attribution breakage, and landing-page health (bounce / 404 steps) against the…

signals-scout-web-analytics

Focused Signals scout for PostHog projects with web traffic. Watches the acquisition and site-health layer the web analytics product reports on: per-channel…

signals-scout-web-analytics

Signals scout for PostHog 網路流量。監控各渠道的會話量、歸因中斷情況，以及登陸頁面健康度（跳出率 / 404 步驟），對比…

signals-scout-web-analytics

專注於PostHog專案中帶有網路流量的Signals偵測。監控網路分析產品所報告的獲取與網站健康層面：按渠道…

signals-scout-web-vitals

Focused Signals scout for PostHog projects capturing Core Web Vitals (`$web_vitals`). Watches each page's p75 LCP / INP / CLS / FCP against the absolute Google…

signals-scout-web-vitals

Focused Signals scout for PostHog projects capturing Core Web Vitals (`$web_vitals`). Watches each page's p75 LCP / INP / CLS / FCP against the absolute Google…

signals-scout-web-vitals

Focused Signals scout for PostHog projects capturing Core Web Vitals (`$web_vitals`). Watches each page's p75 LCP / INP / CLS / FCP against the absolute Google…

simulate-new-user

Send synthetic first-time-visitor traffic to a URL and confirm that PostHog $pageview events fire. Use when a customer wants to verify that anonymous visitor…

simulate-new-user

向指定URL發送模擬首次訪客流量，並確認PostHog的$pageview事件是否觸發。適用於客戶想驗證匿名訪客…

simulate-returning-user

Send synthetic single-session multi-page traffic to a URL and confirm PostHog $pageview events fire across page views. Use when verifying that cookies persist…

simulate-returning-user

向一個URL發送合成的單次會話多頁流量，並確認PostHog的$pageview事件在跨頁面瀏覽時觸發。用於驗證Cookie是否持續存在…

技能是可重複使用的代理工作流程，儲存在 PostHog 中，遵循 Agent Skills 規範——包含一組指令（SKILL.md）及可選的捆綁檔案（腳本、參考資料、資產）、結構化元資料，以及一個 allowed_tools 清單。

Discover and use shared team skills stored in PostHog. Use when the user asks to list, browse, load, or manage "shared skills", "team skills", or references…

Discover and use shared team skills stored in PostHog. Use when the user asks to list, browse, load, or manage "shared skills", "team skills", or references…

技能是可重複使用的代理工作流程，儲存在 PostHog 中，遵循 Agent Skills 規範——包含一組指令（SKILL.md）及可選的捆綁檔案（腳本、參考資料、資產）、結構化元資料，以及一個 allowed_tools 清單。

技能是可重複使用的代理工作流程，儲存在 PostHog 中，遵循 Agent Skills 規範——包含一組指令（SKILL.md）及可選的捆綁檔案（腳本、參考資料、資產）、結構化元資料，以及一個 allowed_tools 清單。

Create and manage GitHub native Stacked PRs in this repo with the `gh stack` CLI. Use when asked to stack PRs, split a large change into a stack, add a layer…

suggesting-data-imports

當用戶詢問有關收入、付款、訂閱、帳單、CRM交易、支援工單、生產資料庫表格，或其他PostHog未涵蓋的資料時使用。

suggesting-data-imports

Use when the user asks about revenue, payments, subscriptions, billing, CRM deals, support tickets, production database tables, or other data that PostHog does…

suggesting-data-imports

Use when the user asks about revenue, payments, subscriptions, billing, CRM deals, support tickets, ad spend, production database tables, or other data PostHog…

suggesting-data-imports

當用戶詢問有關收入、付款、訂閱、帳單、CRM交易、支援工單、生產資料庫表格，或其他PostHog未涵蓋的資料時使用。

suggesting-data-imports

當使用者詢問有關收入、付款、訂閱、帳單、CRM交易、支援工單、生產資料庫表格，或其他PostHog未涵蓋的資料時使用…

suppressing-noisy-errors

建立 PostHog 錯誤追蹤抑制規則，以在擷取階段捨棄高頻率、低價值的錯誤。當使用者要求「停止捕捉此錯誤」、「捨棄…」時使用。

suppressing-noisy-errors

Create PostHog error tracking suppression rules to drop high-volume, low-value errors at ingestion. Use when the user asks "stop capturing this error", "drop…

suppressing-noisy-errors

Create PostHog error tracking suppression rules to drop high-volume, low-value errors at ingestion. Use when the user asks "stop capturing this error", "drop…

suppressing-noisy-errors

建立 PostHog 錯誤追蹤抑制規則，以在擷取階段捨棄高頻率、低價值的錯誤。當使用者要求「停止捕捉此錯誤」、「捨棄…」時使用。

suppressing-noisy-errors

建立 PostHog 錯誤追蹤抑制規則，以在擷取階段捨棄高頻率、低價值的錯誤。當使用者要求「停止捕捉此錯誤」、「捨棄…」時使用。

survey-sdk-audit

稽核PostHog調查SDK的功能與版本需求

survey-sdk-audit

Audit PostHog survey SDK features and version requirements

survey-sdk-audit

Audit PostHog survey SDK features and version requirements

survey-sdk-audit

審查 PostHog 調查 SDK 功能與版本需求

testing-mcp-tools-locally

Set up the local dev environment, seed data, and API keys to test the staff-only managed migrations MCP tools (managed-migrations-support-list,…

tools-and-features-hogql

HogQL queries for PostHog analytics

tools-and-features-hogql

用於 PostHog 分析的 HogQL 查詢

triaging-error-issues

在每日或待命審查期間，對 PostHog 錯誤追蹤問題進行分類。當使用者詢問「哪裡出問題了？」、「我們有哪些新錯誤？」、「顯示最常見的…」時使用。

triaging-error-issues

Triage PostHog error tracking issues during a daily or on-call review. Use when the user asks "what's broken?", "what new errors do we have?", "show me top…

triaging-error-issues

Triage PostHog error tracking issues during a daily or on-call review. Use when the user asks "what's broken?", "what new errors do we have?", "show me top…

triaging-error-issues

在每日或值班檢視期間，分類 PostHog 錯誤追蹤問題。當使用者詢問「哪裡出錯了？」、「我們有哪些新錯誤？」、「顯示最常見的…」時使用。

triaging-error-issues

在每日或待命審查期間，對 PostHog 錯誤追蹤問題進行分類。當使用者詢問「哪裡出問題了？」、「我們有哪些新錯誤？」、「顯示最常見的…」時使用。

triaging-visual-review-runs

Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions "visual review", "VR", "snapshot…

triaging-visual-review-runs

Inspects PostHog Visual Review (VR) runs that gate PR merges with screenshot regression checks. Use when the user mentions "visual review", "VR", "snapshot…

triaging-visual-review-runs

Visual Review 是 PostHog 的螢幕截圖回歸產品：CI 會擷取 Storybook 與 Playwright 的螢幕截圖，與已提交的基準雜湊進行比對，並在人工核准可見變更前封鎖 PR。帶有視覺變更的 PR 會附帶一個 visual-review GitHub 狀態檢查，該檢查會保持紅色，直到每個比對的截圖在 VR 介面中被核准或容忍為止。

triaging-visual-review-runs

檢查那些以螢幕截圖回歸檢查來把關 PR 合併的 PostHog Visual Review (VR) 執行。當使用者提到「visual review」、「VR」、「snapshot…」時使用。

triaging-visual-review-runs

Visual Review 是 PostHog 的螢幕截圖回歸產品：CI 會擷取 Storybook 與 Playwright 的螢幕截圖，將其與已提交的基準雜湊進行比對，並在人工核准可見變更前封鎖 PR。帶有視覺變更的 PR 會附帶一個 visual-review GitHub 狀態檢查，該檢查會保持紅色，直到每個比對的截圖在 VR 介面中被核准或容忍為止。

triaging-web-analytics-support

Triage web analytics support tickets end to end: enumerate open tickets from the in-app conversations product and their Zendesk mirrors, classify each into a…

tuning-incremental-sync-config

同步的配置存在於 ExternalDataSchema 上，可隨時透過 external-data-schemas-partial-update 變更。大多數變更不會造成破壞（在下一次同步時生效），但少數變更（切換 sync_type、變更主鍵）需要謹慎處理，以避免損毀已同步的資料。

tuning-incremental-sync-config

同步的配置存在於 ExternalDataSchema 上，可隨時透過 external-data-schemas-partial-update 變更。大多數變更不會造成破壞（在下一次

tuning-incremental-sync-config

Change the sync configuration of an existing data warehouse schema — switch sync_type, pick a different incremental_field, set primary_key_columns, choose…

tuning-incremental-sync-config

Change the sync configuration of an existing data warehouse schema — switch sync_type, pick a different incremental_field, set primary_key_columns, choose…

tuning-incremental-sync-config

同步的配置存在於 ExternalDataSchema 上，可隨時透過 external-data-schemas-partial-update 變更。大多數變更不會造成破壞（在下一次同步時生效），但少數變更（切換 sync_type、變更主鍵）需要謹慎處理，以避免損毀已同步的資料。

turning-engineering-analytics-into-insights

將工程分析（PR / CI）數據轉換為已儲存的 PostHog 洞察、儀表板和訂閱，並說明產品讀取的數據，以便能夠…

Deep dive on a PostHog user by email address. Analyze what they do, where they spend time, and what products they use.

根據電子郵件地址深入分析 PostHog 使用者，了解其行為、時間分佈及使用的產品。

using-kea-disposables

Use when adding timers (`setInterval`, `setTimeout`), event listeners (`window.addEventListener`, `document.addEventListener`,…

using-kea-disposables

Use when adding timers (`setInterval`, `setTimeout`), event listeners (`window.addEventListener`, `document.addEventListener`,…

using-kea-disposables

Use when adding timers (`setInterval`, `setTimeout`), event listeners (`window.addEventListener`, `document.addEventListener`,…

using-kea-disposables

Use when adding timers (`setInterval`, `setTimeout`), event listeners (`window.addEventListener`, `document.addEventListener`,…

using-the-console-ui

How to drive PostHog Code's read panel as the user works with you — focus_* etiquette, when to call toast, how to handle 'follow mode' being off. Load when the…

using-the-console-ui

當使用者與你協作時，如何驅動 PostHog Code 的讀取面板 — focus_* 禮儀、何時呼叫 toast、如何處理「跟隨模式」關閉的情況。載入時…

verify-posthog-instrumentation

使用此技能驗證 PostHog 檢測是否在網站上正確觸發。驅動真實瀏覽器訪問一個或多個 URL，觀察哪些 PostHog…

verify-posthog-instrumentation

Use this skill to verify that PostHog instrumentation is firing correctly on a website. Drives a real browser at one or more URLs, observes which PostHog…

visualizing-change-over-time

協助 PostHog 工程師與代理在請求涉及隨時間變化的視覺化、前後比較或週期對比時，選擇合適的圖表。

visualizing-change-over-time

協助 PostHog 工程師與代理在請求涉及隨時間變化的視覺化、前後比較或週期對比時，選擇合適的圖表。

warehouse-source-new-version

Add support for a new vendor API version to an existing Data warehouse import source, or deprecate an old one. Use when a vendor ships a new API version…

wizard-development

Design philosophy and architectural principles for the PostHog wizard. Read this before making any structural change — adding features, extending the runner,…

working-outside-the-console

Operating without a UI — MCP / IDE / Slack mode. How to compensate for missing client tools, how to be useful in a text-only chat. Load when the session client…

working-outside-the-console

在沒有使用者介面的情況下操作 — MCP / IDE / Slack 模式。如何補償缺少的客戶端工具，如何在純文字聊天中發揮作用。當會話客戶端載入時…

working-with-skills

Best practices for agents managing PostHog skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently,…

working-with-skills

Best practices for agents managing PostHog skills via the MCP `llma-skill-*` tools — how to discover, read, create, update, and refactor skills efficiently,…

working-with-skills

Best practices for agents managing PostHog skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently,…

working-with-skills

Best practices for agents managing PostHog skills via the MCP `skill-*` tools — how to discover, read, create, update, and refactor skills efficiently,…

working-with-skills

Best practices for agents managing PostHog skills via the MCP `llma-skill-*` tools — how to discover, read, create, update, and refactor skills efficiently,…

workload-analysis

Generate comprehensive workload analysis visualizations for PostHog customer accounts. Use when user requests account analysis, workload breakdown, SDK…

workload-analysis

為PostHog客戶帳戶生成全面的工作負載分析可視化圖表。當用戶要求帳戶分析、工作負載分解、SDK…時使用。

writing-clickhouse-queries

在PostHog產品程式碼中撰寫高效能ClickHouse查詢的指南。用於編寫HogQL查詢執行器、為新產品設計ClickHouse資料表時…

writing-clickhouse-queries

在PostHog產品程式碼中撰寫高效能ClickHouse查詢的指南。適用於編寫HogQL查詢執行器、為新產品設計ClickHouse資料表時…

writing-code-comments

Gates whether a code comment should exist and forces the ones that stay to explain why, not what. Use ALWAYS before writing or editing a comment in any…

Teaches how to write and run evals on the `products/posthog_ai/eval_harness/` harness — sandboxed agent suites that execute the real coding agent in a Docker…

writing-kea-logics

Guide for writing or reviewing PostHog kea logic files (`*Logic.ts` / `*Logic.tsx`). Use when creating a new logic, adding…

writing-kea-logics

Guide for writing or reviewing PostHog kea logic files (`*Logic.ts` / `*Logic.tsx`). Use when creating a new logic, adding…

writing-kea-logics

Guide for writing or reviewing PostHog kea logic files (`*Logic.ts` / `*Logic.tsx`). Use when creating a new logic, adding…

writing-kea-logics

Guide for writing or reviewing PostHog kea logic files (`*Logic.ts` / `*Logic.tsx`). Use when creating a new logic, adding…

writing-pr-descriptions

Shapes a PR body into something a reviewer understands at a glance. Use ALWAYS before writing or editing a PR description, before `gh pr create` or `gh pr edit…

writing-simplified-technical-english

Write English that a reader cannot misread: one meaning per word, active voice, simple tenses, one idea per sentence, short sentences. Based on ASD-STE100…

撰寫 PostHog 代理技能指南 — 工作任務模板，教導代理如何使用 MCP 工具達成目標。適用於新增產品…

撰寫 PostHog 代理技能指南 — 工作待辦事項範本，教導代理如何使用 MCP 工具達成目標。適用於新增產品…

writing-streamlit-apps

Write Streamlit app source code that runs well in a PostHog sandbox — the posthog_apps.query() bridge for reading PostHog data, the packages baked into the…

決定是否應存在新測試，並強制其高效，保護 CI 免受低價值測試膨脹的影響。在新增或大幅變更任何…之前使用。

判斷是否應存在新測試，並強制其高效，保護 CI 免受低價值測試膨脹的影響。在新增或大幅修改任何…之前使用。

writing-user-facing-copy

Sets the voice and word choices for any text a person reads in PostHog: UI labels, buttons, tooltips, empty and error states, notifications, in-app messages,…

將 posthog.com 的部落格或電子報文章轉換為 Markdown 檔案，格式適用於發布為 X（Twitter）文章。移除前置資料，將標題提升為…

Convert a posthog.com blog or newsletter post into a markdown file formatted for posting as an X (Twitter) Article. Strips frontmatter, promotes the title to…