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 481501
get-it-merged
Land a requested set of open PRs as a dependency-aware merge train: the parent reviews, arms protected auto-merge, watches each terminal outcome with a native monitor, and advances until the list is merged or genuinely blocked. Use when multiple PRs are open in one repo and the user wants them merged.
coding-like-redd
Redd's Python and Rust coding standards -- tooling (uv/ruff/ty; cargo/clippy/nextest), code style rules, error/logging/subprocess conventions, and required-project-file templates (including Makefiles). Load whenever writing, reviewing, editing, or scaffolding Python or Rust code, or asked about Redd's coding standards, in ANY project.
code-review
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 read-only `code-reviewer` sub-agents through the configured review route 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".
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Queries every available evidence MCP in parallel and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
typescript-best-practices
TypeScript type-safety rules: discriminated unions, branded types, no `as`, exhaustive switches, schema-derived types. Use when writing, editing, or reviewing TypeScript.
show-me-your-work
Keep a reviewable decision trail for unattended or multi-phase work: a TSV log with one row per decision (what, why, evidence, result).
ship
Take a change from idea to a ready PR with passing CI, running research, grilling, design, verification, and the pr skill in sequence.
session-pickup
Resume unfinished work from a handoff note or prior coding-agent session. Use before reading a supplied handoff, even when its next action is only an inspection or report. Also use to pick up, continue where you left off, or take over from a transcript, agent URL, or pushed branch. Use pause-safely to write a handoff.
review-and-simplify
Review the current branch or a GitHub PR with risk-tiered specialist subagents, judge their findings, apply safe simplifications to your own branch, and post to the PR on request.
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
principle-type-system-discipline
Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, exhaust variants, derive from authoritative schemas.
principle-separate-before-serializing-shared-state
Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.
principle-prove-it-works
Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or "it compiles."
principle-make-operations-idempotent
Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
principle-guard-the-context-window
Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
principle-fix-root-causes
Apply when choosing where to fix a bug. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.
principle-explain-the-number
Apply before you trust, report, or act on a measured number (speedup, regression, throughput, latency, eval result). Find what limits it, and rule out that it measured something other than the work you think.