開發技能

We need to translate the given text from English to Traditional Chinese. The text describes a skill for limit-order strategy trading on OKX Agentic Wallet. We must preserve the name "okx-dex-strategy" if it appears, but it does not appear in the text. The text includes terms like "OKX Agentic Wallet", "limit-order", "buy a dip", "take profit", "stop loss", "chase a high", "SA TEE upgrades", "okx-dex-swap", "market orders", "Agentic Wallet TEE". We should keep these as is or translate appropriately. For technical terms like "TEE" (Trusted Execution Environment), it's common to keep as TEE. "SA TEE upgrades" might be kept as is. The translation should be natural in Traditional Chinese. Let's translate sentence by sentence: "Limit-order strategy trading on OKX Agentic Wallet." -> "在 OKX Agentic Wallet 上進行限價單策略交易。" "Use this skill when the user wants to place a price-trig

We need to translate the given text from English to Traditional Chinese. The text is inside <text> tags. We must preserve the name "okx-dex-ws" if it appears, but it does not appear in the source text. So we just translate the text. The text includes some terms like 'onchainos ws', 'ws start', etc. These should be preserved as is, but the surrounding Chinese translation should be in Traditional Chinese. Also note the ellipsis at the end. We'll translate naturally. The text: "Use this skill when the user mentions 'onchainos ws', 'ws start', 'ws poll', 'ws stop', 'ws channels', 'ws session', 'ws channel-info', 'idle-timeout', 'idle timeout', 'WebSocket channels', 'WS频道', or asks about managing WebSocket sessions/会话管理. Also use when writing a custom WebSocket script/脚本/bot for real-time on-chain data. Covers: onchainos ws CLI commands (start/poll/stop/list/channels/channel

跨XLayer、Solana、Ethereum、Base、BSC、Arbitrum、Polygon及20多條鏈的鏈上交易閘道。可調用廣播預簽名/原始/已簽名交易、推送序列化交易上鏈、查詢當前Gas價格、估算Gas上限、在發送前模擬或試運行交易、追蹤已廣播訂單，或透過txHash或orderId檢查交易確認/待處理狀態。

監聽任務進展 / 幫我盯著任務 / 任務有動靜告訴我 / 歷史訊息 / 未讀訊息 / 未決策 / 待決策 / 繼續監聽 / task watch / user watch / monitor task progress / catch me up on tasks / outstanding decisions — OKX A2A

當使用者希望獲得關於啟動、貢獻、發展、治理、資助、保護或維持開源專案的指導，或詢問貢獻者入門、社群健康、維護者倦怠、行為準則、指標、法律基礎或開源專案採用的相關問題時使用。

全面的OpenTUI技能，用於構建終端使用者介面。涵蓋核心命令式API、React協調器及Solid協調器。適用於任何TUI開發任務，包括元件、佈局、鍵盤處理、動畫及測試。

We need to translate the given text from English to Traditional Chinese. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. The name "orca-cli" is to be preserved if it appears in the source text, but we should not include it unless it appears. The source text includes "orca-cli" as part of the list of phrases. So we keep "orca-cli" as is. Also "Orca" is a product name, so keep as "Orca". "CLI" is technical term, keep as "CLI". "worktrees", "folder contexts", "terminals", "repos", "automations", "worktree comments", "browser", "Orca app", "cardStatus", "codex/claude", "terminal", "full handoff", "handover", "agent" - these are technical terms or product names, so we should preserve them in English or translate? The instruction says "preserve product names, protocol names, URLs, numbers, and technical terms." So

Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator loops, or decomposing work across agents. Use `orca-cli` instead for full ownership handoffs, including requests phrased as "hand off", "handoff", "handover", "give this to another agent", or "another worktree" when the user did not explicitly ask to supervise, monitor, wait for results, or coordinate...

The Paperclip way of converting a plan into executable tasks. Use whenever you are asked to plan, scope, or break down work inside a Paperclip company. Industry-agnostic guidance on how to translate a plan into assigned issues with the right specialty, dependencies, and parallelization so Paperclip's executor can pick up the work — it does not prescribe a plan format. Pair with the `paperclip` skill, which covers the mechanics of writing the plan document and reassigning the issue.

在 Paperclip 中建立具治理意識的新代理人。當你需要檢視適配器配置選項、比較現有代理人配置、草擬新的代理人提示/配置，並提交僱用請求時使用。

優化網頁效能以加快載入速度並提升使用者體驗。當被要求「加快網站速度」、「優化效能」、「減少載入時間」、「解決載入緩慢」、「改善頁面速度」或「效能審核」時使用。

優化應用程式在前端、後端、查詢與資料庫的效能。適用於存在效能需求時、懷疑有效能衰退時、需要改善Core Web Vitals或載入時間時、需要修正N+1查詢模式時，或效能分析顯示瓶頸時。

將工作分解為有序的任務。當您有規格或明確需求，且需要將工作分解為可執行的任務時使用。當任務感覺過於龐大而難以開始、需要估算範圍，或可以平行進行工作時使用。

讓 Claude 能夠即時編寫並執行任何 Playwright 自動化操作——從簡單的頁面測試到複雜的多步驟流程。

在編寫 Playwright 測試、修復不穩定測試、除錯失敗、實作 Page Object Model、設定 CI/CD、最佳化效能、模擬 API、處理驗證或 OAuth、測試無障礙功能（axe-core）、檔案上傳/下載、日期/時間模擬、WebSocket、地理位置、權限、多分頁/彈出視窗流程、行動/響應式版面、觸控手勢、GraphQL、錯誤處理、離線模式、多人協作、第三方服務（付款、電子郵件驗證）等情境時使用。

使用Azure OpenAI的GPT Realtime Mini模型，通过WebSocket生成AI驱动的播客风格音频叙事。适用于构建文本转语音功能、音频叙事生成、从内容创建播客，或集成Azure OpenAI Realtime API以实现实时音频输出。涵盖从React前端到Python FastAPI后端的全栈实现，包括WebSocket流式传输。

強制採用實際可行、最簡單、最短、最精簡的懶人解法。模擬見多識廣的資深開發者：質疑任務是否真的需要存在（YAGNI），優先使用標準函式庫而非自訂程式碼，原生平台功能而非依賴套件，一行程式碼勝過五十行。支援強度等級：輕量、完整（預設）、極致。當使用者說出「ponytail」、「be lazy」、「lazy mode」、「simplest solution」、「minimal solution」、「yagni」、「do less」或...時啟用。

針對整個儲存庫進行過度工程審計。類似ponytail-review，但掃描整個程式碼庫而非差異：提供一份排名清單，列出應刪除、簡化或替換為標準庫/原生等效項目的內容。當使用者說「審計此程式碼庫」、「審計過度工程」、「我可以從此儲存庫刪除什麼」、「找出臃腫」、「ponytail-audit」或「/ponytail-audit」時使用。一次性報告，不套用修復。

Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". Use when the user says "ponytail debt", "/ponytail-debt", "what did ponytail defer", "list the shortcuts", "ponytail ledger", or "what did we mark to do later". One-shot report, changes nothing.

專注於過度工程的程式碼審查。找出可刪除的內容：重新發明的標準函式庫、不必要的依賴、推測性抽象、無用的靈活性。每個發現一行：位置、要刪除的內容、替代方案。當使用者說「審查過度工程」、「我們可以刪除什麼」、「這是否過度工程」、「簡化審查」或呼叫 /ponytail-review 時使用。與正確性導向的審查互補，此審查僅針對複雜性。

來自 Supabase 的 Postgres 效能優化與最佳實踐。在撰寫、審查或最佳化 Postgres 查詢、資料表設計或資料庫配置時，請使用此技能。

pr-to-video 工作流程 - 一個 GitHub 拉取請求（網址格式如 github.com/ / /pull/ 、或 / # 、或在已檢出儲存庫中的「this PR」）-> 擷取 PR 資訊（標題、內容、差異、提交、檔案、增減統計）-> narrator_scripts.json + 音訊（語音 + 背景音樂）+ section_plan.md -> 程式碼差異 / 前後對比 / 影響說明影片。輸入內容為程式碼變更。該網址為 PR 連結，非行銷網站（無需爬取）；非文字摘要，亦非產品網站。若輸入非 PR 內容（產品網站、一般網站、主題文字），...

生成一個靜態互動式 D3 拉取請求逐步導覽。當使用者想要可縮放的 PR 地圖、圖表/畫布 PR 導覽，或 PR 系統元件、資料流、程式碼相依性及使用者操作的替代視覺化時使用。

Prisma Compute deployment and hosting guide. Use whenever the user mentions Prisma Compute, `prisma.compute.ts`, `defineComputeConfig`, deploying or hosting a Prisma app, `@prisma/cli app deploy`, `compute:deploy`, `create-prisma --deploy`, `PRISMA_SERVICE_TOKEN`, `auth workspace`, Compute apps/deployments/build logs/domains, `@prisma/cli agent install`, localhost vs `0.0.0.0`, deploy port binding, or framework deploy readiness for Hono, Elysia, Next.js, TanStack Start, Astro, Nuxt, Svelte,...

用於查詢 Prometheus 及相容 PromQL 引擎（Thanos、Cortex、VictoriaMetrics、Grafana Mimir、Grafana Tempo…）的 CLI 工具 — 支援即時查詢、範圍查詢、指標探索（metrics/labels/meta 子命令）、輸出格式（table/csv/json/graph）。適用於執行 PromQL 查詢、排查具可觀測性軟體的性能問題、調查延遲/錯誤率/飽和度，或分析時間序列資料。

為你描述的UI元件建立多個真正不同的版本，並在視覺選取器後方渲染，讓你能夠即時切換瀏覽，選出最合適的那一個。僅在明確呼叫時執行；不會自行觸發。

建立一個可拋棄的原型，在確定設計前先完善構想。在兩個分支之間切換——一個可執行的終端應用程式，用於測試狀態或商業邏輯問題；或從同一路由切換多種截然不同的UI變體。當使用者想要製作原型、驗證資料模型或狀態機、模擬UI、探索設計選項，或說出「把這個做成原型」、「讓我玩玩看」、「試試幾種設計」時使用。

Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation in Python applications using Pydantic v2.

將 Python（Flask/Django/FastAPI）程式碼部署到 Azure App Service Linux。觸發時機：「Flask App Service」、「Django App Service」、「FastAPI App Service」、「deploy Python to App Service」。不適用於：Container Apps、Functions、非 Python、Terraform/Bicep/IaC、完整基礎架構 — 請使用 azure-prepare。

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D...