GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills，按职业与使用场景整理，复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196921
bmad-index-docs
Generates or updates an index.md to reference all docs in the folder. Use if user requests to create or update an index of all files in a specific folder
packaged-artifact-smoke
Use when you need to prove a BUILT deliverable actually works end-to-end, not just that its source tree is CI-green. Runs 3-5 golden journeys against the PACKAGED artifact (the built Electron binary via `_electron.launch`, or `pip install dist/*.whl` in a fresh venv then invoke the installed CLI), each ending in a DETERMINISTIC on-disk postcondition probe (ffprobe, or file existence + size).
bmad-help
Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.
mcp-fleet-curation
Use when plugins, skills, or MCP servers keep REAPPEARING after you disable them, when de-bloating the Claude Code catalogue, or when the per-turn tool/token count creeps back up. The permanent cure - disable at USER scope (claude plugin disable name@mkt --scope user), NOT the UI toggle (which writes project scope and returns when the cwd changes) - plus periodic mcp_doctor audit.
bmad-editorial-review-structure
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure
bmad-editorial-review-prose
Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the prose
workflow-authoring
Use when writing or debugging a saved Claude Code Workflow (a .js/.mjs orchestration script under ~/.claude/workflows that uses the injected agent/parallel/phase globals to fan out subagents). Covers the exact runtime API, the args-as-string gotcha, the banned Date.now() non-determinism, worktree isolation for file-mutating agents, one-level nesting, a schema on every fan-in, null-tolerant barriers via filter(Boolean), per-work-unit pipelines so one slow agent cannot deadlock the cohort, cache-cliff-aware fan-out, the typed Codex output-schema landmine when MCP tools are active, and the SDK context-editing / task-budgets / canUseTool notes. Also the map to the saved schema-typed gate Workflows plan-gate and design-gate and the mechanical plan-lint stage-0. Triggers include author a workflow, write a saved workflow, fan out subagents, my parallel workflow deadlocks, workflow returns empty, schema-typed reviewers, or codify a gate as a workflow. NOT for single ad-hoc Task subagents (spawn a Task directly) or for the metaswarm phase pipeline itself.
bmad-distillator
Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.
video-watermark-removal
Use when removing a static logo, watermark, or TV bug from a video seamlessly (so it is not noticeable it was ever there). PRIMARY method = ProPainter flow-guided temporal inpaint on a TIGHT logo-only mask (pulls REAL background pixels from neighbouring frames -> sharp, no soft haze), CHUNKED in time so it fits a small GPU and avoids OOM, with PER-FRAME presence gating so frames where the logo is occluded (e.g. a hook card) are left pristine. big-LAMA per-frame is the fast fallback but its fill is visibly SOFT. Plus the pitfalls that actually bite: tight logo-shaped mask not a generous box (oversized boxes smear faces), don't inpaint frames where the logo is absent, chunk long clips to bound RAM, retry transient WSL2 CUDA failures, run as a detached WSL daemon watched by a persistent Monitor, and PROVE clean with a logo-template NCC gate across the whole timeline (never claim done on a single-frame check). Includes a companion method for a FIXED-PATH animated overlay (fades or scrolls along a fixed screen path, identical across many clips) via cross-clip-average phase masks; still NOT for arbitrary moving watermarks or full-frame logos.
bmad-brainstorming
Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.
video-convert
Use when converting a video/audio file's FORMAT, CODEC, or CONTAINER in media-studio (mp4/mkv/mov/webm/gif, h264/h265/vp9/av1, or audio-only extraction to mp3/m4a/wav/flac/opus) — single file or batch, or normalizing a non-Chromium-playable source for playback (remux vs h264-720p proxy). Covers the real ffmpeg argv builder, codec/CRF/bitrate/pix_fmt choices, faststart, container<->codec legality, and the progress/seek/timebase pitfalls that actually bite. DO NOT use this skill for: cutting/trimming/splitting clips (use reframe-video-cutting), reframing 16:9->9:16 (use reframe), burning subtitles/captions, watermark/logo removal (use video-watermark-removal), or pure thumbnail/frame extraction. Also NOT a general 'run any ffmpeg command' helper — it documents media-studio's specific, frozen convert.* / media.* contracts.
bmad-advanced-elicitation
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
ui-ux-pro-max
Use when designing UI/UX for web or mobile apps and needing opinionated style, color palette, font pairing, or chart-type recommendations from a searchable database of 67 styles, 96 palettes, 57 font pairings, and 99 UX guidelines across 13 stacks ; do NOT use for code implementation or pixel-perfect Figma work ; returns ranked design recommendations.
bmad-cis-storytelling
Craft compelling narratives using story frameworks. Use when the user says "help me with storytelling" or "I want to create a narrative through storytelling"
bmad-cis-problem-solving
Apply systematic problem-solving methodologies to complex challenges. Use when the user says "guide me through structured problem solving" or "I want to crack this challenge with guided problem solving techniques"
ui-invariant-walk
Use when you want a property-based random-walk oracle that DRIVES a running web/Electron app and asserts UI invariants over a randomized command sequence — "no enabled button is a dead click" (an enabled, visible control must produce an observable state change) and "no route errors" (no navigation may reach an error route, throw an uncaught exception, or log a console error). Model-based testing via fast-check (`fc.commands` + `fc.asyncModelRun`) driving Playwright, with automatic shrinking to a minimal reproducing click/nav sequence. Ships as a SHADOW-mode advisory oracle (observe + log to a bounded rotating sink, never blocks CI or nags). Optionally deepen the existing Python Hypothesis suite with HypoFuzz nightly — but ONLY after verifying HypoFuzz's shifted license; the fast-check oracle ships regardless. NOT for pixel/design critique (use ui-audit), NOT for deterministic single-flow E2E (use Playwright directly).
bmad-cis-innovation-strategy
Identify disruption opportunities and architect business model innovation. Use when the user says "lets create an innovation strategy" or "I want to find disruption opportunities"
bmad-cis-design-thinking
Guide human-centered design processes using empathy-driven methodologies. Use when the user says "lets run design thinking" or "I want to apply design thinking"