Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Convert PDF, Office, HTML, data, media, ZIP to Markdown.
Critique a written proposal or design artifact via 5 philosophical personas in parallel, with consensus synthesis.
Parallel 3-reviewer code review: Security, Business-Logic, Architecture.
Analyze external repositories for adoptable ideas and patterns.
| SCOPE, GATHER, SYNTHESIZE, VALIDATE, DELIVER. Parallel research agents mandatory (min 3). Saves findings to research/{topic}/ for future reference. Use for "research pipeline", "formal research", "research with artifacts".
Security threat model: scan toolkit for attack surface, supply-chain risks.
Local security review of git changes: deterministic scan + Security reviewer over the diff. No API key, no SDK.
Playwright-based end-to-end testing workflow.
Run Vitest tests and parse results into actionable output.
4-phase code review: UNDERSTAND, VERIFY, ASSESS risks, DOCUMENT findings.
RED-GREEN-REFACTOR cycle with strict phase gates for TDD.
Structured multi-phase workflows: review, debug, refactor (tidy, clean up, untangle messy code without behaviour change), deploy, create, research.
Test agents via subagents: known inputs, captured outputs, verification.
Identify and fix testing mistakes: flaky, brittle, over-mocked tests.
Use when apple-release-engineer is about to build the signed distributable (TestFlight build / notarized DMG / internal package) from merged-to-main code (after apple code review + SIT Audit pass and merge, before apple-qa-engineer runs E2E/UAT). Provides the applicability gate, pre-flight checks, lane execution per channel, notarization, real-output smoke test, hand-off, and the release-report skeleton. Pairs with deployment.md §7 "Apple 发布" contract and slash /agf-apple-release.
Use when apple-dev has finished feature code + Unit tests (Swift Testing) and is about to enter code-review. Provides the Apple SIT scope (xcodebuild test + simulator per declared target), the AC-driven integration walk, APIProtocol-mock discipline, and evidence sink (progress/apple-dev.md). SIT is dev-owned; apple-code-reviewer audits the evidence.
Use when deploy-engineer is about to deploy the merged-to-main code to the isolated local UAT stack (after code review + SIT Audit pass and merge, before qa-engineer runs E2E/UAT). Provides the applicability gate, pre-flight checks, isolated compose bring-up (independent project name + port offset +900), in-container migration, real-output smoke test, hand-off, and the deploy-report skeleton. Pairs with deployment.md "UAT 环境部署" contract and slash /agf-deploy-uat.
Use when uiux-designer is about to produce a design spec (spec.md) or static HTML prototype, or frontend-dev is about to build UI from a design. Provides the anti-AI-slop design discipline layer — Brief Inference (Design Read), three aesthetic dials tuned for product UI, AI Tells blacklist with overrides, mechanically-checkable Pre-Flight. Sits above the token layer (DESIGN.md) and mechanical review (code-reviewer); does not redeclare tokens or guide non-shadcn design systems. Inspired by taste-skill, cropped for AGF product UI per ADR-013.
Deeply Understand (codemap) — 持久化代码图谱 + 变更影响分析 + 理解地图。接手遗留项目 Day-1 / PR 影响分析 / 解释陌生代码 / PRD·ADR 前现状理解时用。编排 tools/codemap/ 的 codemap CLI
Use when PL / tech-lead audits the content quality of AGF's own skills (`.claude/skills/agf-*/SKILL.md`). Provides the 5-dimension checklist (Actionability / Scope fit / Uniqueness vs CLAUDE.md+standards / Currency of pointers / Gate-binding validity), 5-verdict rubric (Keep/Improve/Update/Retire/Merge), reason-quality bar (反敷衍), and output skeleton. Triggered each MINOR release retro or manually.
Use when an execution-layer dev (frontend-dev / backend-dev / ai-agent-dev / ml-engineer / miniapp-dev) has finished feature code + Unit tests and is about to enter code-review. Provides the SIT scope, environment, AC-driven integration walk, and evidence sink (progress/<role>.md). SIT is now a dev-owned step, not a separate QA stage.
Use when product-lead is about to run a release retrospective after a successful MAJOR or MINOR release push (PATCH skipped). Provides applicability gate, pre-conditions, 7-step execution sequence, anti-patterns, and the verification gate before commit. Pairs with template docs/reviews/retro-_TEMPLATE.md and slash /agf-release-retro.
Use when wiring up or switching between China-domestic LLM providers (DeepSeek, Doubao/Volc Ark, Qwen/DashScope, MiniMax). Provides OpenAI-compatible adapter pattern, env-var contracts, fallback strategy, cost guardrails, and minimum verifications before declaring integration done.
用 docx-js 写"阅读友好的中文 docx 报告"（决议书 / 评审报告 / 调研 / 分析 / 投标书等高密度报告型文档）。当用户要求把 markdown 内容转 docx 且抱怨"格式混乱 / 不专业 / 看不下去"时启用——pandoc 默认转换难以满足。提供：路径决策 / 设计 token / 可复用 helper 全套 / 11 个 pitfall / 生成-预览闭环。
Use whenever a user, product-lead, or qa-engineer wants to create a GitHub issue in the project repo — including phrases like "提一个 issue / 写一个 issue / 报 bug / 把这个开成 issue / gh issue / 上 GitHub / track 一下 / 立个 ticket". Provides the required-field skeleton, locked label set (type / area / epic / priority / severity / phase), gh CLI heredoc template, and the QA-auto-issue exception path. Replaces ad-hoc `gh issue create` calls with inconsistent titles / missing labels / freestyle bodies.
Use when tech-lead is about to record an architecture decision (new tech stack member, deviation from baseline, deployment / observability / auth scheme choice). Provides ADR structure, version-audit appendix format, and "what NOT to ADR" guidance. Replaces ad-hoc copy from ADR-000.
Use when wiring LLM features into the Apple client (macOS / iOS) — streaming chat via the FastAPI multi-LLM gateway, or on-device inference (Apple Foundation Models / Core ML). Provides the route decision (gateway vs on-device), streaming transport pattern, env/config contract, offline & cost guardrails, and minimum verifications before declaring the integration done.
Use when product-lead is about to formalize a feature into a change folder (the OpenSpec-style intake that replaces PRD as of v6.9.0). Provides the four-artifact structure (proposal / delta specs / design / tasks), the Requirement+Scenario delta format (ADDED/MODIFIED/REMOVED/RENAMED), the AC↔scenario mapping that keeps the AGF verification spine intact, the validate gate, and the archive-merge hand-off. Replaces agf-writing-prd (deprecated).
用 python-pptx 写"现代化中文制度 / 党政 / 企业宣贯 PPT"（含决议书提报、评审报告、管理办法、培训宣贯等 23 页量级 deck）。当用户要求程序化生成 PPT 且抱怨"老土 / 字体丑 / 表格乱 / 文字溢出 / 中文字体 fallback / 缺架构图"时启用——`python-pptx` 默认 API 一堆坑必须主动避开。提供：路径决策 / 设计 token / 12 个 helper 全套 / 7 个致丑反模式 / 12 个关键技巧 / LibreOffice 渲染验证闭环 / 跨平台中文字体生效 lxml 写法 / 配套 draw.io 画架构图选型（中文字体、配色、8 大坑、嵌入 PPT 链路）。
[DEPRECATED since v6.9.0 → removed in v7.0.0; use agf-writing-change instead] Legacy PRD intake. Use when product-lead is about to draft a PRD for a new feature. Provides the 10-section PRD structure, AC quality bar, must-have fields, and the verification gate before sign-off.
Use when qa-engineer (or miniapp-qa-engineer) is about to publish an E2E or UAT report. Provides the report skeleton, evidence-quality bar, verdict criteria, and hand-off rules. SIT is now dev-owned and lives in progress/<role>.md (see agf-running-sit-tests skill) — this skill does NOT cover SIT reports.
Operate iOS Simulators, Android Emulators, and connected mobile devices with Simvyn. Use for device discovery, app installation and launch, screenshots, logs, deep links, location simulation, app data inspection, device settings, and reusable device workflows through the Simvyn CLI or dashboard.
Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.
Geospatial query capabilities — geocoding, nearby search, routing, place details, elevation. Trigger when the user mentions locations, addresses, coordinates, navigation, "what's nearby", "how to get there", distance/duration, or any question that inherently involves geographic information — even if they don't explicitly say "map". Update when new tools are added or tool parameters change.
Workflow and tools for adding new entries from temp.md to the section files. Includes legend format, section reference, code tools, and common pitfalls. USE FOR: Adding new resources to the knowledge base. DO NOT USE FOR: Editing existing entries or restructuring sections.
Workflow for updating the popular LLM applications pool (section/x_llm_apps.md) using fetch_llm_apps.py. Covers full refresh, alternate exports, topic tuning, and common pitfalls. USE FOR: Refreshing the ranked GitHub applications list linked from applications.md. DO NOT USE FOR: Hand-curating application entries inside applications.md or adding GitHub star badges to the generated file.
Workflow for updating the LLM landscape paper pool (section/x_llm_papers.md) using fetch_llm_papers.py. Covers full re-fetch, resume from checkpoint, and adding new topics. USE FOR: Refreshing citation counts, expanding topic coverage. DO NOT USE FOR: Adding hand-curated entries to section files (use add-new-entry-from-temp-md), updating RAG/Agent citation sections in best_practices.md (use update-cite-count).
Classification guidelines for entries in temp_entries.md. Each entry has a title containing the markdown file name and section name. USE FOR: Classifying new entries in temp_entries.md into *.md section files. DO NOT USE FOR: Adding entries to temp_entries.md or moving entries between sections.
Guidelines for updating citation counts for papers in the section files using the `update_citation_counts.py` tool. USE FOR: Updating citation counts for papers listed in the section files to keep information current. DO NOT USE FOR: 1) Adding new papers to the section files; 2) Classifying entries into sections.
| Analyzes and safely cleans up local Git branches. Categorizes branches by merge status, staleness, and remote tracking. Provides interactive selection with safety guards. Use when the user wants to clean up branches, delete old branches, organize Git branches, or asks about which branches can be safely deleted.
Evaluates agent skills against Anthropic's best practices. Use when asked to review, evaluate, assess, or audit a skill for quality. Analyzes SKILL.md structure, naming conventions, description quality, content organization, and identifies anti-patterns. Produces actionable improvement recommendations.
Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.
Update per-package CHANGELOG.md files for a Ratel release. Drafts entries with git-cliff (scoped per package), lets you curate, then writes the CHANGELOGs. Handles both RC entries and GA-graduation collapse (merging X.Y.Z-rc.* sections into a single X.Y.Z section). Invoke before tagging a release.
Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when building Speech Engine servers, WebSocket handlers, WebRTC browser clients, conversation token endpoints, interruption-aware streaming responses, or voice-enabled chat agents that connect developer-owned server logic to ElevenLabs speech-to-text and text-to-speech.
Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.
> Update ElevenLabs agent skills from a merged weekly changelog in elevenlabs-dx, then open a pull request in elevenlabs/skills. Trigger after a changelog merges to main on elevenlabs-dx, or when asked to update skills from changelog YYYY-MM-DD.
Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.
Guides users through setting up an ElevenLabs API key for ElevenLabs MCP tools. Use when the user needs to configure an ElevenLabs API key, when ElevenLabs tools fail due to missing API key, or when the user mentions needing access to ElevenLabs. First checks whether ELEVENLABS_API_KEY is already configured and valid, and only runs full setup when needed.
Build voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience.
Convert text to speech using ElevenLabs voice AI. Use when generating audio from text, creating voiceovers, building voice apps, or synthesizing speech in 70+ languages.
Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, generating audio textures, producing ambient sounds, cinematic impacts, UI sounds, or any audio that isn't speech. Supports looping, duration control, and prompt influence tuning.
Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio isolation) API. Use when cleaning up noisy recordings, removing music or background ambience from dialogue, isolating speech from field recordings, preparing audio for transcription, extracting vocals, or any "denoise / clean up / isolate voice" task.
Transform the voice in an audio recording into a different target voice while preserving emotion, timing, and delivery using the ElevenLabs Voice Changer (speech-to-speech) API. Use when converting one voice to another, changing the speaker/narrator of an existing recording, dubbing a voice-over in a different voice, creating character voices from a scratch performance, anonymizing a speaker, or any "voice conversion / voice transfer / speech-to-speech" task. Make sure to use this skill whenever the user mentions voice changing, voice conversion, speech-to-speech, swapping a voice in audio, re-voicing a clip, or applying a different voice to an existing recording — even if they don't explicitly say "voice changer".
面向真实业务决策的多平台事实核验 Skill。正式支持深知晓、深知晓（深度研究）、豆包、腾讯元宝、DeepSeek 和通义千问，按用户输入动态选择 N≥1 个平台。完整采集原回答、引用、截图与页面存证，拆解并对比关键事实，再按需使用可信搜索取得权威证据，交付四份独立报告和可追溯结论。基础采集与对比无需 API Key；可信搜索是权威核验阶段的可选增强。语义工作由 Codex、Claude Code、WorkBuddy 等当前运行载体完成，不调用外部大模型 API。
Use when working with Canton Network participants, DAML smart contracts, Splice applications, or debugging LF version and package ID issues.
Use when reading or writing Go files (.go, go.mod).
Use when automating iOS Simulator interactions, capturing screenshots/video, or inspecting accessibility via AXe CLI.
Use when reading or writing Python files (.py, pyproject.toml, requirements.txt).
Use when reading or writing React components (.tsx, .jsx files with React imports).
Use when writing or modifying Playwright tests (.spec.ts, .test.ts with @playwright/test imports).
Claude Skills — questions
Answers built from the skills we actually parsed.