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
create-skill
Create or revise portable agent skills with clear triggers, focused instructions, and self-contained resources. Use when creating, modifying, refactoring, or deduplicating a skill or its SKILL.md, or authoring skill evaluations and benchmarks.
commit
Create a well-formed git commit from current changes using session history for rationale and summary. Use when asked to commit, save, or push current changes.
codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
code-simplify
Use when asked to refactor or simplify code.
code-review
Strict review of a PR, diff, commit range, branch, staged/unstaged changes, or AI patch. Finds only high-confidence issues introduced or exposed by the reviewed change.
code-review-biaxis
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes - Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
code-modernization
Modernize legacy codebases with a guided, stepwise process that produces an executive brief
caveman
Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".
release
Publish releases when requested by the user.
todo
Add, complete, or view items in the brain/todos.md backlog. Use when you discover work outside your current task scope or the user says "todo", "add a todo", "mark done", "what's on the backlog", "show todos", "list tasks", "check off", or wants to manage their task list.
todo-refine
Sharpen todo items in brain/todos.md into precise, actionable prompts via targeted questioning. Use after brain/todos.md is modified or when the user asks to "refine", "refine todos", or "clarify todos".
ruminate
Mine past conversations for uncaptured patterns, corrections, and knowledge. Cross-references with existing brain content. Triggers on "ruminate", "mine my history", "what have I been working on", "review past sessions", "extract learnings".
reflect
Reflect on the conversation and update the brain. Use immediately when the user adds or clarifies constraints, preferences, or quality standards, even when phrased as a new instruction rather than a correction. Also use after mistakes, failures, user corrections, user steering, negative reviews, discovered workarounds, understanding gaps, and at session wrap-up. Review may conclude no write is needed. Use when the user says "reflect", "remember this".
meditate
Audit and evolve the brain vault - prune outdated content, discover cross-cutting principles, review skills for structural encoding opportunities. Triggers on "meditate", "audit the brain", "prune brain", "review skills", "consolidate notes", "prune notes".
brain
Read/write brain files at brain/. Use when modifying any file in brain/. Use for any task that persists knowledge - reflection, planning, or direct edits. Use after debugging sessions, mistakes, corrections, architectural decisions, or any insight worth preserving across sessions. Use when the user says 'add to brain', 'remember this', or 'write a note'.
brain-install
Install a portable brain vault, six local brain skills, and optional repository hooks, migrating existing guidance when present.
architecture-design-contest
Generate multiple competing architecture designs for a feature, compare their trade-offs, and recommend or synthesize the best direction before implementation. Use this whenever the user wants architecture options, says "design it twice", asks for alternatives before coding, wants an RFC-level design review, or is unsure which approach to choose. Prefer this skill over jumping straight into implementation when the real need is exploring and comparing viable designs.
agents-md-install
Install, audit, or update root and nested AGENTS.md files and task-specific reference docs in a project.