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
expert-super-duper-review
Expert-level review, then brainstorm and fix in an isolated git worktree
expert-super-duper-cat-review
Expert-level review with subagents, then brainstorm and fix in an isolated git worktree with subagents
expert-super-cat-review
Expert-level review with subagents, then brainstorm and fix with subagents
expert-review
Expert-level multi-language code review, simplification, debugging, and security audit
expert-final-review
Final pre-merge gate — verify all PR peer feedback is addressed, then run a full /expert-review
expert-duper-tdd-review
Expert-level review, then fix using TDD in an isolated git worktree
expert-duper-tdd-cat-review
Expert-level review with subagents, then fix using TDD in an isolated git worktree with subagents
expert-cat-review
Expert-level review with each phase dispatched as a parallel subagent
duper
Isolated git worktree workflow (alias for /using-git-worktrees)
duper-tdd
TDD workflow using an isolated git worktree
duper-tdd-cat
TDD workflow using an isolated git worktree with subagent-driven-development
draft-cmt-msg-4-below
draft a commit message for the below changes
cost_
Extract and log cost data for the current session.
cost-opt
Compact cost logs, recalibrate the pricing table in ~/.claude/extract_cost.py and statusline-command.sh against platform.claude.com/cost extracts, and surface optimization suggestions.
continue
retry last operation attempted before the user interrupted the process, or otherwise continue last attempted tool use
checkpoint-save
Use when pausing work that will be resumed later, when switching contexts, or when the user asks to save a checkpoint. Creates a CHECKPOINT.md that captures full resumption context.
checkpoint-resume
Use when resuming paused work, starting a session where a CHECKPOINT.md exists, or when the user says "continue from checkpoint", "resume", or "pick up where we left off"
check-yourself
Use when a discrete task boundary is crossed in multi-step work — step completion, subagent dispatch return, Skill-tool invocation return, /proceed gate passed, test-run completion, or file-write to a durable artifact (spec, plan, SKILL.md). Do not substitute an in-place TaskList update for this skill.