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
security-best-practices
Perform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.
sarif-parsing
Parses and processes SARIF files from static analysis tools like CodeQL, Semgrep, or other scanners. Triggers on "parse sarif", "read scan results", "aggregate findings", "deduplicate alerts", or "process sarif output". Handles filtering, deduplication, format conversion, and CI/CD integration of SARIF data. Does NOT run scans — use the Semgrep or CodeQL skills for that.
runpodctl
Runpod CLI to manage your GPU workloads.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
request-classifier
Classify any user request into a structured format for prompt generation. Use this skill whenever you need to understand what type of task a request represents, determine complexity, decide whether planning is needed, or route a request to the right skills and agent strategy. Trigger on: any request that needs to be analyzed before generating a Claude Code prompt, when someone says 'classify this', 'what kind of task is this', when the prompt-generator or prompt-router skills need input classification, or when deciding between solo agent vs subagent vs tmux team execution.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
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.
pydantic-models-py
Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants. Use when defining API request/response schemas, database models, or data validation in Python applications using Pydantic v2.
prompt-router
Route a classified request to the right skills, agent strategy, Context7 directives, and output format. Use this skill whenever you need to decide which skills to load for a task, choose between solo agent vs subagent dispatch vs tmux agent team, determine if Context7 library docs are needed, or select the right output format for a prompt. Trigger on: any request that has been classified and needs routing, when someone asks 'what skills should I use for this', 'should I use subagents', 'do I need tmux mode', or any prompt generation workflow that needs skill selection and strategy planning.
prompt-generator
Generate optimized Claude Code prompts for any request. This is the main entry point for the prompt generation system. Use this skill whenever you need to create a prompt for a Claude Code session, generate a session prompt pack, prepare a multi-session plan, or translate a natural language request into a structured, actionable Claude Code prompt. Trigger on: 'generate a prompt for', 'create a prompt', 'help me write a prompt', 'what prompt should I use', '/generate-prompt', any use of the generate-prompt slash command, or when you want to ensure a Claude Code session starts with the right skills, context, glossary, and verification checklist loaded. Also trigger when someone wants to create session prompts similar to the S4-S9 pipeline prompt packs.
prompt-agent
Security audit enforcement for AI agents. Automated security scans and health verification.
playwright-skill
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
openclaw-audit-watchdog
Automated daily security audits for OpenClaw agents with email reporting. Runs deep audits and sends formatted reports.
next-best-practices
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
multi-agent-patterns
This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.
modern-python
Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/black.
langgraph-persistence
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.
langgraph-human-in-the-loop
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.