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
heartbeat
暂无简介
find-session
Find opencode sessions by name or content across ALL project directories, bypassing the cwd scoping of session_list/session_search. Use when looking for a session that was started in a different folder.
evolve
Self-improvement loop for opencode configuration. Analyzes session history, queues candidate learnings, lints them, promotes high-confidence rules, and tracks rule effectiveness via Reflexion-style feedback. Use when you want the agent setup to learn from accumulated experience.
browser-harness
暂无简介
auto-dev
Autonomous PR development methodology. Use ONLY when the user explicitly invokes /auto-dev or explicitly asks to load this skill — never auto-activate. Reviews every PR twice, monitors all CI pipelines in background, replies to and resolves every review comment from any reviewer (automated systems like CodeRabbit and human reviewers alike), merges PRs (apps or infra) when green, then monitors post-merge and deployment pipelines, iterating on failures.
arch-decision
Run a structured 7-stage architecture decision loop on any technical choice — vendor evaluation, build-vs-buy, infra strategy, schema change, ADR. Produces a scored decision memo with a binary verifier verdict. Good triggers include "should we use X or Y", "help me think through our options", "we need to decide", "evaluate approach", "technical trade-off", "which is better for our stack", "options for", "design decision", "ADR", "architecture decision".
ai-champions
Read Simon's latest AI Champions weekly task from
agent-directory
Discover and invoke any of 69 specialist agents. All agents are latent (not loaded at startup) and activated on demand via the pimp router. Use this skill before delegating any specialised task.
docs
暂无简介
grilling
Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
grill-me
A relentless interview to sharpen a plan or design.
vue-best-practices
Vue 3 and Vue.js best practices for TypeScript, vue-tsc, and Volar. This skill should be used when writing, reviewing, or refactoring Vue components to ensure correct typing patterns. Triggers on tasks involving Vue components, props extraction, wrapper components, template type checking, or Volar configuration.
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
tech-spec
Write a typed call-stack architecture handoff.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
plannotator-visual-explainer
Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to nicobailon/visual-explainer.
plannotator-review
Open Plannotator's browser-based code review UI for the current worktree, another directory, or a pull request URL, then act on the feedback that comes back.