Use when an LLM Wiki operation issue is a lint or health check. Audit for contradictions, orphans, weak provenance, broken links, missing concept pages, and index/log drift; return triage findings without auto-fixing.

Use when an LLM Wiki operation issue requests an index refresh. Rebuild `wiki/index.md` from the actual wiki tree, reconcile missing/deleted entries, and log counts without editing page bodies.

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

Use when writing or reviewing Go code in this repo that applies summaries, topics, intents, sentiment, language detection, diarization, redaction, or entity extraction to audio inputs through Listen v1 REST. Route plain transcription to deepgram-go-speech-to-text and plain-text Read requests to deepgram-go-text-intelligence.

Use when writing or reviewing JavaScript/TypeScript in this repo that calls Deepgram audio analytics overlays on `/v1/listen` - summarize, topics, intents, sentiment, diarize, redact, detect_language, and entity detection. Same endpoint as plain STT, different params. Covers REST via `client.listen.v1.media.transcribeUrl` / `transcribeFile` and the WebSocket-supported subset on `client.listen.v1.createConnection()` / `connect()`. Use `deepgram-js-speech-to-text` for plain transcription and `deepgram-js-text-intelligence` for analytics on already-transcribed text. Triggers include "audio intelligence", "summarize audio", "diarize", "sentiment from audio", "redact PII", and "detect language audio".

Generate configurable chat motion overlays from a transcript or screenshot, including plain bubble scenes, app-style chat containers, optional device frames, preset or uploaded avatars, nickname display rules, and transparent-video-ready Remotion bundles. Use when Codex needs to create reusable short-form chat clips for Douyin, demo videos, story reenactments, social-message proof scenes, or embeddable alpha overlays for Hyperframe and Remotion workflows.

Set up and run RuView mmWave / FMCW radar sensing — ESP32-C6 + Seeed MR60BHA2 (60 GHz, heart rate / breathing rate / presence) and HLK-LD2410 (24 GHz, presence + distance), plus mmWave↔WiFi-CSI sensor fusion (48-byte fused vitals, MR60BHA2/LD2410 auto-detect, v0.5.0+). Use when the deployment includes a millimetre-wave radar alongside or instead of WiFi CSI.

Upgrade browser versions (Chrome or Firefox) in the Flutter Web Engine and/or Framework tests. Use when asked to roll or upgrade Chrome or Firefox to a newer version.

Upgrades Flutter's Android SDK dependency to a new Android API version (or preview/canary release) in packages.txt, verifies CIPD tag uniqueness, and packages/uploads the binaries using create_cipd_packages.sh across macOS, Linux, and Windows. Use whenever a user wants to pick up a new version of Android or upload Android SDK packages to CIPD.

Choose Rust types for operating system paths across the Codex repository. Use when defining new path-bearing types or explicitly migrating existing ones.

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the privacy/cost/offline trade-offs. Based on Lesson 17 of AI Agents for Beginners. USE FOR: run an agent locally, offline agent, on-device agent, Foundry Local, Qwen function calling, local tool calling, local RAG, Chroma vector database, local MCP server, privacy-preserving agent, hybrid local and cloud agent, small language model agent, engineering assistant on my machine. DO NOT USE FOR: deploying agents to the cloud at scale (use deploying-scalable-agents / Lesson 16), building your first agent concept (Lesson 01), Foundry (cloud) hosted agents, GPU cluster / server-side inference provisioning.

Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API, switch from chat completions, openai responses, upgrade openai SDK, responses API migration, move from completions to responses, gpt-5 migration, azure openai python migration, chat completions to responses, AzureOpenAI to OpenAI client, python azure openai upgrade. DO NOT USE FOR: building new apps from scratch (start with responses directly), Node/TypeScript/C#/Java/Go migrations (this skill is Python-only), Azure infrastructure setup (use azure-prepare), deploying models (use microsoft-foundry).

Rebuild and restart the internal Storybook UI after changes to internal Storybook code (core, addons, frameworks, renderers, libs, etc.), then optionally display a UI review. Use after editing any package in the Storybook monorepo's code/ directory, or when the user asks to rebuild and/or restart Storybook.

审查 ant-design 测试用例是否值得保留。在用户要求验证测试 case、review 测试质量、判断测试是否合理、是否“用 A 证明 A”、是否重复、是否锁定实现细节，或决定测试应删除、保留还是改写时使用。

Help maintainers reply to Ant Design GitHub issues following official guidelines. Use this skill when the user asks to handle issues, reply to issues, process issues, check issues, or manage issues for ant-design/ant-design repository. Also use when the user mentions "issue" in the context of antd, Ant Design, or GitHub issue management. This skill provides guidelines for classifying issues (Bug vs Feature Request), handling dosubot replies, using proper labels, writing polite responses, and knowing when to close issues.

Create pull requests for ant-design using the repository's official PR templates. Use this skill when the user asks to create/open a PR, draft PR title/body, summarize branch changes for a PR, or otherwise prepare PR content. Judge by intent rather than fixed phrases; short colloquial requests still count if they are about creating a PR rather than discussing PR concepts.

Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions abandoned, unfinished, or old side projects, asks "what should I finish", wants to revive or resurrect a project, says "run the graveyard", wonders why they never finish anything, or is about to start a new project that sounds like one they already built. Runs entirely locally.

Automate shepherding, checking status, updating branches, and landing open PRs or approved third-party contributor PRs in the flutter/flutter repository using the gh CLI. When to use: - When you need to check the status of open PRs or shepherded third-party PRs. - When you need to update stale branches or apply the 'autosubmit' label to land approved PRs. When not to use: - Do not use for PRs that are not approved (unless they are your own and you want to check status). - Do not use for repositories other than flutter/flutter.