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 196852
ui-audit
Drive a running web or Electron app and emit a deterministic UI/UX + functional audit - a11y, contrast, spacing, tap targets, dead buttons, motion, visual regression (Track-A) - then a design-quality VERDICT (Track-B) where Claude reasons over the numbers + screenshot on the DESIGN-EVAL v1 rubric (0-4, critical-error override, weighted composite) against Refactoring-UI/HIG/Nielsen/WCAG. READ-ONLY.
two-tier-verify
Use when repeated code edits are triggering a full test-suite rerun each iteration and burning tokens/time, or before any commit. Splits verification into a cheap INNER loop per edit (only the affected/related tests plus type-check and lint on touched files) and a single OUTER loop at the commit boundary (full suite plus coverage plus held-out E2E/golden-journey plus a scoped mutation check). Gives concrete jest/vitest/playwright and pytest command recipes and the decision rule for which tier to run. NOT a replacement for the golden-journey done-signal (see seed-golden-journey); NOT for one-off single-file scripts where a full run is already trivial.
bmad-testarch-atdd
Generate failing acceptance tests using TDD cycle. Use when the user says "lets write acceptance tests" or "I want to do ATDD"
bmad-technical-research
Conduct technical research on technologies and architecture. Use when the user says they would like to do or produce a technical research report
triage-dispatch
Use when repairing an app with MULTIPLE bugs or broken user-journeys at once (not a single fix) - instead of edit-one-file / rerun-the-whole-suite / hope, first map the broken journeys with evidence, capture each REAL error, build a defect graph, then dispatch parallel bounded-scope fix agents and verify only impacted regions before an outer full+e2e+mutation gate.
bmad-teach-me-testing
Teach testing progressively through structured sessions. Use when user says "lets learn testing" or "I want to study test practices"
transpose-to-figma
Use when lifting a running or built UI back onto the Figma canvas (the G2 TRANSPOSE / Code-to-Canvas edge of the design-review loop) and you must pick the right code-to-Figma path - story.to.design for the component-system loop, the Figma MCP generate_figma_design for live/localhost screens, or html.to.design for an audit-only DOM record. NOT for Figma-to-code (use figma-implement-design).
bmad-tea
Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.
transcribe
Use when asked to transcribe speech to text from audio/video, with diarization to label speakers in recordings, interviews or meetings. Do NOT use for WORD-LEVEL caption or karaoke timing -- use reframe-transcribe.
bmad-sprint-status
Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status"
bmad-sprint-planning
Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan"
trail-of-bits-re
Use when you want the Trail of Bits security/RE skill packs — differential-review (security-focused review of a code CHANGE, folding in git history to catch vulnerabilities a diff introduced), variant-analysis (find the SAME bug class across a codebase / other repos by pattern), and yara-authoring (write high-quality YARA-X detection rules with linting and atom analysis). Also the map to the rest of the trailofbits/skills marketplace (dwarf-expert, firebase-apk-scanner, constant-time-analysis, static-analysis, insecure-defaults, sharp-edges, semgrep-rule-creator, and more). These are advisory prompt/skill packs — Claude reasons with them, nothing auto-blocks. Install selectively (cherry-pick, do not bulk-install all 40 — catalogue tax). CC BY-SA 4.0.
bmad-shard-doc
Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven.
tooluniverse
Use when routing ToolUniverse life-science questions to the right specialized skill or verifying scientific facts against real databases.
bmad-review-adversarial-general
Perform a Cynical Review and produce a findings report. Use when the user requests a critical review of something
to-prd
Use when the user wants a PRD synthesized from the current conversation and codebase context (not an interview) and fed into the build pipeline as tracked, agent-ready work. Triggers include "turn this into a PRD", "write the PRD", "make issues from this", "spec this out for the team".
bmad-retrospective
Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]"