Deepgram技能

設定並使用 1Password CLI（op）。在安裝 CLI、啟用桌面應用程式整合、登入（單一或多帳戶）或…時使用。

當你需要透過 wsh 啟動並驅動其他 AI 代理（如 Claude Code、Aider、Codex 等）的終端介面時使用。範例：「執行多個…」

使用Deepgram的語音轉文字、文字轉語音、語音代理及音訊智能API進行建置。

Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks OpenClaw to add a note, list…

Manage Apple Reminders via the `remindctl` CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.

Create, search, and manage Bear notes via grizzly CLI.

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.

BluOS CLI (blu) for discovery, playback, grouping, and volume.

Use when you need to send or manage iMessages via BlueBubbles (recommended iMessage integration). Calls go through the generic message tool with…

Capture frames or clips from RTSP/ONVIF cameras.

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed…

當您需要在聯邦集群中跨多個wsh伺服器管理工作階段時使用。例如：「將構建任務分發到多台機器」、「建立…

Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.

在未擁有 wsh_* MCP 工具的情況下，進行任何 wsh 終端操作前必須執行此步驟。包含完整的 HTTP API 參考資料及可運作的 curl 範例、引導程式…

在任何 wsh 終端操作之前必須執行。包含完整的 MCP 工具參考以及 wsh_create_session、wsh_send_input、… 的引導序列。

使用 Deepgram Voice Agent API 設定撥打電話至 OpenClaw

Use when writing or reviewing C# code in this repo that enables Deepgram intelligence overlays on Speech-to-Text requests. Covers `PreRecordedSchema` analytics…

Use when writing or reviewing C# code in this repo that enables Deepgram intelligence overlays on Speech-to-Text requests. Covers `PreRecordedSchema` analytics…

在評估、擴展或撰寫用於對話式語音轉文字、Flux 風格即時轉錄，或輪流串流的 C# 程式碼時使用…

Use when evaluating, extending, or writing C# code for conversational speech-to-text, Flux-style real-time transcription, or turn-taking streaming in the…

Use when writing or reviewing C# code in this repo that calls Deepgram Management APIs for projects, models, keys, members, invitations, usage, balances, and…

在此儲存庫中撰寫或審查呼叫 Deepgram 管理 API（用於專案、模型、金鑰、成員、邀請、用量、餘額等）的 C# 程式碼時使用。

在編寫或審查此儲存庫中呼叫 Deepgram Speech-to-Text 進行預錄或即時轉錄的 C# 程式碼時使用。涵蓋…

Use when writing or reviewing C# code in this repo that calls Deepgram Speech-to-Text for prerecorded or live transcription. Covers…

Use when writing or reviewing C# code in this repo that calls Deepgram Text Intelligence / Read (`/read`) for sentiment, summarization, topic detection, and…

Use when writing or reviewing C# code in this repo that calls Deepgram Text Intelligence / Read (`/read`) for sentiment, summarization, topic detection, and…

Use when writing or reviewing C# code in this repo that calls Deepgram Text-to-Speech. Covers `ClientFactory.CreateSpeakRESTClient()` with `ToStream` /…

Use when writing or reviewing C# code in this repo that calls Deepgram Text-to-Speech. Covers `ClientFactory.CreateSpeakRESTClient()` with `ToStream` /…

Use when writing or reviewing C# code in this repo that builds an interactive Deepgram Voice Agent over WebSocket. Covers…

在此儲存庫中撰寫或審查透過 WebSocket 建立互動式 Deepgram 語音代理的 C# 程式碼時使用。涵蓋…

Use when writing or reviewing Go code in this repo that applies summaries, topics, intents, sentiment, language detection, diarization, redaction, or entity…

在此儲存庫中撰寫或審查 Go 程式碼時，用於應用摘要、主題、意圖、情感、語言偵測、說話者辨識、編輯或實體…

Use when planning or reviewing Go SDK work for Deepgram conversational STT / Flux v2. This repo does not currently ship a first-class v2 listen client, so…

在規劃或審查Deepgram對話式STT / Flux v2的Go SDK工作時使用。此儲存庫目前未提供一流的v2 listen客戶端，因此…

Use when writing or reviewing Go code in this repo that works with Deepgram management endpoints for projects, keys, members, scopes, invitations, usage,…

在此儲存庫中撰寫或審閱與 Deepgram 管理端點（用於專案、金鑰、成員、範圍、邀請、用量等）搭配運作的 Go 程式碼時使用。

Use when writing or reviewing Go code in this repo that transcribes prerecorded audio with Listen v1 REST or streams live audio with Listen v1 WebSockets.…

在此儲存庫中撰寫或審查使用 Listen v1 REST 轉錄預錄音訊，或使用 Listen v1 WebSockets 串流即時音訊的 Go 程式碼時使用。

Use when writing or reviewing Go code in this repo that sends text to Deepgram Read via the analyze client. Route speech/audio inputs to…

在此儲存庫中撰寫或審查 Go 程式碼時使用，該程式碼透過分析客戶端將文字傳送至 Deepgram Read。將語音/音訊輸入路由至…

Use when writing or reviewing Go code in this repo that synthesizes audio with Speak v1 REST or Speak WebSockets. Route transcription work to…

在此儲存庫中編寫或審查使用 Speak v1 REST 或 Speak WebSockets 合成音訊的 Go 程式碼時使用。將轉錄工作導向…

Use when writing or reviewing Go code in this repo that runs a Deepgram Voice Agent session over WebSockets, including runtime settings, prompt updates, speak…

在此儲存庫中撰寫或審查透過 WebSocket 執行 Deepgram Voice Agent 工作階段的 Go 程式碼時使用，包括執行時期設定、提示更新、語音輸出……

Use when writing or reviewing Java code in this repo that enables Deepgram intelligence overlays on `/v1/listen` audio transcription - diarization, entity…

Use when writing or reviewing Java code in this repo that enables Deepgram intelligence overlays on `/v1/listen` audio transcription - diarization, entity…

Use when writing or reviewing Java code in this repo that calls Deepgram Conversational STT v2 / Flux over `/v2/listen`. Covers…

Use when writing or reviewing Java code in this repo that calls Deepgram Conversational STT v2 / Flux over `/v2/listen`. Covers…

Use when writing or reviewing Java code in this repo that calls Deepgram Management APIs for projects, project models, API keys, members, invites, usage, and…

在此儲存庫中編寫或審查Java程式碼時使用，該程式碼會呼叫Deepgram Management API以處理專案、專案模型、API金鑰、成員、邀請、使用量等。

Use when writing or reviewing Java code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live transcription. Covers…

Use when writing or reviewing Java code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live transcription. Covers…

Use when writing or reviewing Java code in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for text analysis. Covers…

Use when writing or reviewing Java code in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for text analysis. Covers…

Use when writing or reviewing Java code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via…

Use when writing or reviewing Java code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST via…

Use when writing or reviewing Java code in this repo that builds an interactive voice agent over `agent.deepgram.com/v1/agent/converse`. Covers…

Use when writing or reviewing Java code in this repo that builds an interactive voice agent over `agent.deepgram.com/v1/agent/converse`. Covers…

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents,…

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents,…

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming…

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming…

Use when regenerating this JavaScript/TypeScript SDK with Fern, editing `.fernignore`, preparing the repo for a generator release, reconciling hand-maintained…

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Management APIs for projects, API keys, members, invites, requests, usage,…

在此儲存庫中編寫或審查呼叫 Deepgram 管理 API（用於專案、API 金鑰、成員、邀請、請求、用量等）的 JavaScript/TypeScript 時使用。

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio…

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio…

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST…

在撰寫或審查此儲存庫中呼叫 Deepgram Text-to-S

Use when writing or reviewing JavaScript/TypeScript in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers…

Use when writing or reviewing JavaScript/TypeScript in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers…

Use when writing or reviewing Python code in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment,…

Use when writing or reviewing Python code in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment,…

Use when writing or reviewing Python code in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription.…

Use when writing or reviewing Python code in this repo that calls Deepgram Conversational STT v2 / Flux (`/v2/listen`) for turn-aware streaming transcription.…

Use when writing or reviewing Python code in this repo that calls Deepgram Management APIs - projects, API keys, members, invites, usage, billing, models, and…

在此儲存庫中撰寫或審查呼叫 Deepgram 管理 API（專案、API 金鑰、成員、邀請、用量、帳單、模型等）的 Python 程式碼時使用。

Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers…

Use when writing or reviewing Python code in this repo that calls Deepgram Speech-to-Text v1 (`/v1/listen`) for prerecorded or live audio transcription. Covers…

Use when writing or reviewing Python code in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for sentiment, summarization, topic detection,…

Use when writing or reviewing Python code in this repo that calls Deepgram Text Intelligence / Read (`/v1/read`) for sentiment, summarization, topic detection,…

Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST…

Use when writing or reviewing Python code in this repo that calls Deepgram Text-to-Speech v1 (`/v1/speak`) for audio synthesis. Covers one-shot REST…

Use when writing or reviewing Python code in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers…

Use when writing or reviewing Python code in this repo that builds an interactive voice agent via `agent.deepgram.com/v1/agent/converse`. Covers…

在從 Rust SDK 實現 Deepgram 音訊智能時使用，特別是當智能功能附加到 STT 選項和批次回應時…

Use when implementing Deepgram audio intelligence from the Rust SDK, especially when intelligence features are attached to STT Options and batch responses…

Use when implementing Deepgram Flux conversational STT from the Rust SDK, including flux_request APIs, turn events, FluxResponse handling, and turn-detection…

在從 Rust SDK 實作 Deepgram Flux 對話式語音轉文字時使用，包括 flux_request API、輪次事件、FluxResponse 處理以及輪次偵測…

Use when implementing Deepgram project, key, member, scope, billing, invitation, or usage operations from the Rust SDK, including manage feature flags and the…

在實作 Deepgram 專案、金鑰、成員、範圍、帳單、邀請或用量操作時使用，來自 Rust SDK，包括管理功能旗標及…

Use when implementing Deepgram speech-to-text in the Rust SDK, including prerecorded REST transcription, live WebSocket streaming, listen feature flags,…

在 Rust SDK 中實作 Deepgram 語音轉文字時使用，包括預錄 REST 轉錄、即時 WebSocket 串流、監聽功能標誌等。

Use when a user asks for Deepgram text intelligence from Rust. Route to raw HTTP guidance because this crate does not currently expose a dedicated /v1/read…

當使用者要求從 Rust 取得 Deepgram 文字智慧時使用。由於此 crate 目前未提供專用的 /v1/read… 端點，請導向原始 HTTP 指引。

Use when implementing Deepgram text-to-speech in the Rust SDK, including Aura model selection, speak feature flags, output file or byte-stream handling, and…

在 Rust SDK 中實作 Deepgram 文字轉語音時使用，包括 Aura 模型選擇、speak 功能標誌、輸出檔案或位元組串流處理，以及…

找到適合您使用Deepgram建置的正確文件。

當你需要透過wsh以命令與回應互動的方式驅動CLI程式時使用。例如：「執行建置命令並檢查輸出」、「與……互動」

Control Eight Sleep pods (status, temperature, alarms, schedules).

展示如何使用Deepgram與熱門平台、框架及生態系統的實作範例。

Gemini CLI for one-shot Q&A, summaries, and generation.

在需要即時建立動態、互動式終端體驗時使用。範例：「在終端機中建立即時儀表板」、「建立互動式…」

Search GIF providers with CLI/TUI, download results, and extract stills/sheets.

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.

Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for…

Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening,…

CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple…

iMessage/SMS CLI for listing chats, history, watch, and sending.

當你需要透過 wsh 以互動方式管理多台伺服器上的基礎設施時使用——包括部署應用程式、配置服務、管理套件等。

當你需要暫時攔截人類的鍵盤輸入時使用。例如：「在執行指令前先詢問使用者是否同意」、「建立一個選擇…」

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type…

Merge a GitHub PR via squash after /preparepr. Use when asked to merge a ready PR. Do not push to main or modify code. Ensure the PR ends in MERGED state and…

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown.…

在需要觀察、監控或對人類終端活動做出反應時使用。例如：「監控終端是否有錯誤」、「觀察用戶正在做什麼並…」

當你需要透過 wsh 伺服器模式協調多個並行終端工作階段時使用。範例：「在多個專案中平行執行建置」、「追蹤…

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Notion API for creating and managing pages, databases, and blocks.

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Local speech-to-text with the Whisper CLI (no API key).

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Control Philips Hue lights/scenes via the OpenHue CLI.

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Foodora-only CLI for checking past orders and active order status (Deliveroo WIP).

Capture and automate macOS UI with the Peekaboo CLI.

Prepare a GitHub PR for merge by rebasing onto main, fixing review findings, running gates, committing fixes, and pushing to the PR head branch. Use after…

由代理維護的微型食譜，展示如何在每種支援的語言中使用每個 Deepgram SDK 功能。每個食譜都是一個聚焦、可執行的程式碼片段，而非完整的應用程式。

Review-only GitHub pull request analysis with the gh CLI. Use when asked to review a PR, provide structured feedback, or assess readiness to land. Do not…

ElevenLabs text-to-speech with mac-style say UX.

Search and analyze your own session logs (older/parent conversations) using jq.

您正在為用戶設定 Deepgram MCP 整合。請遵循以下步驟：

Local text-to-speech via sherpa-onnx (offline, no cloud)

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

Use when you need to control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.

Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.

Control Sonos speakers (discover/status/play/volume/group).

Terminal Spotify playback/search via spogo (preferred) or spotify_player.

複製一個可運作的示範專案，然後開始建置。每個 starter 都是最小可執行的應用程式，方便您擴展。

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

替換為技能描述及其使用時機。

Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks…

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

Manage Trello boards, lists, and cards via the Trello REST API.

當你需要透過 wsh 操作全螢幕終端應用程式（TUI）時使用。例如：「導航 vim 編輯檔案」、「使用 lazygit 進行暫存與提交…」

Extract frames or short clips from videos using ffmpeg.

在需要透過終端機以視覺方式與人類溝通時使用。例如：「顯示狀態面板」、「顯示覆蓋通知」、「建立一個…」

Start voice calls via the OpenClaw voice-call plugin.

Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).

Get current weather and forecasts (no API key required).