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
check
Orchestrate verification ACROSS a chain of work — the multi-round, multi-tier audit loop that drives findings to zero. Distinct from /verify:complete (one phase's exit gate): /check escalates verify:* tiers and relays remediation to /work until a sprint/epic/change converges clean. Invoke to converge-verify a body of work, not to gate a single phase.
chain
Convergence-state model for multi-round orchestration loops. Defines context/CHAIN.json — the baton /scope (plan-converge) and /check (verify-converge) pass between rounds: progress metric, tier-ladder climb, stall detection, exit + escalation rules. A reference, not an executor.
capture
Turn signals surfaced during work into tracked issues. Park discoveries and keep moving; convert audit/session findings to issues; block, triage, and roll up into epics — the human side of the self-improvement loop.
caveman
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
ponytail
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
caveman
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
copier-conflict-fixture
framework version two
copier-conflict-fixture
framework version two
copier-conflict-fixture
framework version one
copier-conflict-fixture
framework version one
project-owned
暂无简介
test-skill
A test skill for validating skillpush functionality
secret-skill
A skill with secrets
long-desc
This is a description that is intentionally quite long to trigger the warning about potential truncation in large skill collections and registries where space is at a premium
bad-skill
暂无简介
Bad Name With Spaces
This name is not a valid slug
radxa-doc
Use when you need to query locally deployed Radxa product documentation to confirm hardware details, interfaces, or board-specific technical information before coding or troubleshooting.
mdmaker-deploy
Use when you need to deploy, build, or update the local MDMaker-based Radxa documentation mirror under ~/.openclaw/MDMaker.