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。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 481501

nredd
nredd/pi-harness

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.

★ 2
nredd
nredd/pi-harness

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.

★ 2
nredd
nredd/pi-harness

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".

★ 2
ravnhq
ravnhq/ravn-core

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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).

★ 2
ravnhq
ravnhq/ravn-core

ship

Take a change from idea to a ready PR with passing CI, running research, grilling, design, verification, and the pr skill in sequence.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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."

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2