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
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
retro
Run the sprint boundary's cross-story review and retrospective, and propose AGENTS.md learnings as a diff.
pm
Explicit entry point for /bstack:pm. Use only when the user invokes /bstack:pm or asks by name for the bstack PM; it starts the project-manager skill's procedure on their request. For any other software-delivery request, use the project-manager skill instead.
board
Use when the user invokes /bstack:board or asks for a board meeting, a stakeholder review, a 0-10 score of the project's status, or several models' joint judgement on a question about the project. User-invoked, advisory and costly under T3 Code; never start it on your own.
valid-minimal
A minimal valid skill used as a parser fixture.
valid-links
A valid skill that links to a bundled reference file.
valid-folded
A valid skill whose description is a folded block scalar spanning multiple lines, to make sure the parser does not call it empty.
unterminated
暂无简介
missing-desc
暂无简介
invalid-no-frontmatter
暂无简介
broken-link
Links to a file that does not exist.
a-different-name
Name does not match the parent directory.
bad-meta
metadata is a scalar, not a map.
release-lanorme
Use when cutting, shipping, releasing, or publishing a new LaNorme version (a "0.x.y" bump, a tag, a PyPI release). Runs every release gate (unit tests, the dogfood, generated docs in sync), records a eval audit (precision/recall/F1 per scored rule plus end-to-end performance, stamped with the version and hardware) to evals/results/, bumps the version, tags, and creates the GitHub Release that auto-publishes to PyPI and deploys the versioned docs.
merge-ready
Decide whether a change is ready to merge, and review it to that bar. Use when reviewing a pull request or deciding whether to merge a branch, to check that the change does what it claims, is DRY, clean, idiomatic and maintainable, has a solid test base that would actually catch a regression, holds up on performance, and ships with the right docs.
docs-audit
Audit the LaNorme docs for accuracy, currency, no-archeology, clarity, and coverage, then fix what it finds. Use before a release or after changing the CLI, the rules, or any Markdown doc, or when asked whether the docs are solid, current, or up to date. It runs the docs-audit workflow, which checks every documented flag, rule code, config key, and output example against the real tool, flags changelog-style narration outside CHANGELOG and any bluff, and lists undocumented surface.
stacked
Decompose LARGE, complex, or risky changes into a stack of small, dependent, independently reviewable units. Use only when the change is genuinely big: multiple architectural layers with functionally distinct concerns (models + storage + logic + API + UI), or a diff too large to review as one unit. Trigger on "stacked" / "stacked PRs" / "stack this" / how to break down a large change — or when a "build X" / "refactor W" request is clearly multi-layer and large. Do NOT use for small or moderate changes: bug fixes, tweaks, config, single-file or single-layer changes belong on ONE branch as ONE change — a stack of tiny branches adds overhead without value.
manifest
Use when starting a non-trivial feature, migration, refactor, or multi-step task in ANY repo. Creates and continuously maintains a living markdown manifest at `<repo-root>/tasks/<slug>/manifest.md` (inside the repo being worked on — NEVER the skill dir or ~/) capturing the problem, decisions, exploration results, plan, open questions, test + rollout plans, and final review. Trigger on "build X", "add X", "migrate X", "refactor X", tasks needing 3+ steps, or whenever a plan-before-code loop would help. NOT for single-line fixes, obvious bugs, or one-shot questions.
kagaz
Kagaz (कागज़) — a personal design system for all frontend and document work — editorial-technical-archival, serif display + mono metadata on warm paper tones with a single rust accent. Use for ANY frontend, UI, web page, landing page, dashboard, artifact, component, mockup, poster, slide deck, report, or PDF/document design, for HTML→PDF conversion, and for any "make this look good" / "style this" / "make slides" / "turn this into a PDF" request — even when no design preference is mentioned. Overrides generic AI defaults (Inter-on-white, purple gradients, cool grays). Ships an HTML-to-PDF converter with visual QA and on-brand SVG charts.