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
local-seo-manager
Manage local SEO for service-area businesses — appliance repair, HVAC, plumbing, cleaning, and any business that serves customers at their location. Use when the user wants to: audit Google Business Profile, generate neighborhood service area pages, check NAP consistency across directories, create LocalBusiness schema, or write review responses. Triggers: 'local SEO', 'Google Business Profile', 'GBP', 'service area page', 'NAP consistency', 'local citations', 'LocalBusiness schema', 'review responses', 'Google Maps ranking'. NOT for national SEO (use seo-audit). NOT for general schema (use schema-markup). NOT for AI answer-engine visibility (use aeo).
test-readability
Master writing readable tests: how to structure tests for clarity, name tests descriptively, and make tests self-documenting. Use when writing tests, reviewing test quality, or when tests are hard to understand. Triggers especially when user says "readable tests", "test structure", "test naming", "test organization", "self-documenting tests" or "clear tests".
tech-stack-detection
Systematically scans project config files to identify tech stack composition, version info, and engineering tooling. Should be used when the user needs to understand what technologies a project uses — onboarding, evaluating upgrade feasibility, or troubleshooting build issues. Distinguished from explore which investigates project structure and problems, this skill focuses on identifying technology stacks.
llm-wiki
Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
staged-code-review
Comprehensive pre-commit review of git staged changes. Performs tech-stack-aware code quality checks and generates conventional commit messages. Should be used when the user is about to commit code and wants a quality gate — catching debug leftovers, sensitive data, missing error handling before they enter the repository. Distinguished from frontend-code-review which reviews general code quality, this skill focuses specifically on git staged changes pre-commit.
setup-test-data
Master test data setup: creating meaningful test fixtures, test data factories, and managing test data lifecycle. Use when user needs test data, test fixtures, sample data for tests, or when tests are hard to maintain due to data setup. Triggers especially when user says "test fixtures", "test data", "setup test", "create test objects", or "sample data".
security-review
AI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, understanding component interactions, and catching vulnerabilities that pattern-matching tools miss. Use this skill when asked to scan code for security vulnerabilities, find bugs, check for SQL injection, XSS, command injection, exposed API keys, hardcoded secrets, insecure dependencies, access control issues, or any request like "is my code secure?", "review for security issues", "audit this codebase", or "check for vulnerabilities". Covers injection flaws, authentication and access control bugs, secrets exposure, weak cryptography, insecure dependencies, and business logic issues across JavaScript, TypeScript, Python, Java, PHP, Go, Ruby, and Rust.
safe-refactor
Chain-combined skill that ensures refactoring is done safely by combining refactor judgment, test coverage verification, and pre-commit review. Encapsulates the decision of WHEN to refactor, HOW to ensure safety, and WHAT verification is needed. Use when user mentions refactoring, code restructuring, improving code quality, or when they want to refactor without breaking behavior. Triggers especially when user says "should I refactor this?", "is it safe to refactor?", "how do I refactor without breaking things?", or "refactor my code".
litreview
Academic literature orientation skill that searches papers via free keyless APIs (PubMed E-utilities + OpenAlex) by default — with the Consensus MCP as an optional enhancement lane when connected — builds a strategic search plan using PICO (default) or SPIDER / Decomposition / hybrid as fallbacks, and synthesizes findings into a formatted Word (.docx) research guide. Grill-me intake (research question specificity + framework hint + tentative depth) before the recon search; a second forcing checkpoint after Phase 2 confirms framework + sub-areas + depth before searches consume budget. Configurable depth (5/10/20 queries) controls coverage vs. speed. Output is a 'launching pad' — an orientation guide that lets a researcher dive in confidently, not a finished review. Use when the user starts literature-oriented research (e.g., 'litreview on [topic]', 'literature review on [topic]', 'I'm starting a literature review on X', 'I'm writing a paper on X', 'help me research X', 'I'm doing research on X', 'can you help me research X'). Do NOT use for single one-off paper searches wanting a quick list — that's a plain PubMed/OpenAlex (or Consensus) query.
reproduce-bug
Master reliable bug reproduction: how to construct minimal reproduction cases, isolate conditions, and verify bugs consistently. Use when debugging, creating bug reports, or when a bug is hard to reproduce. Triggers especially when user says "reproduce bug", "can't reproduce", "minimal case", "bug report", or "isolating the bug".
refactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
linkedin-strategy
Use when someone needs a LinkedIn plan rather than a post — content pillars, positioning for a career change or consulting or thought leadership, a sustainable posting cadence, or a newsletter decision. Triggers on "what should I post about", "how often should I post", "LinkedIn content strategy", "should I start a LinkedIn newsletter", "grow my following", "90-day plan". Validates the positioning brief, sizes the week against real hours and refuses a plan that will not survive week five, and gates a newsletter against eligibility and a six-month cadence commitment.
read-test-coverage
Master reading test coverage reports: how to interpret coverage metrics, understand what they mean, and identify untested gaps. Use when analyzing code coverage, identifying test gaps, or when coverage numbers don't match expectations. Triggers especially when user says "test coverage", "coverage report", "interpret coverage", "untested code", or "what's not tested".
react-performance
Reviews and optimizes React component performance and correctness. Covers stale closures, unnecessary re-renders, useEffect cleanup, state design, debounce/throttle, and race conditions. Should be used when the user is concerned about React performance — slow renders, stale closure bugs, or optimizing useMemo/useCallback usage. Distinguished from frontend-code-review which covers general code quality, this skill focuses specifically on React performance and Hook-related issues.
linkedin-skills
Use when someone wants to grow an organic LinkedIn presence — a content strategy for a career change or consulting or thought leadership, a rewritten profile or headline, post drafts and hooks, a posting cadence or newsletter plan, connection notes and outreach, a commenting strategy, repurposing an article or talk into posts, or a read on why their reach dropped. Triggers on "grow my LinkedIn", "fix my headline", "write a LinkedIn post", "what should I post about", "LinkedIn strategy", "connection request", "my reach dropped". Forks context to route to one of five sub-skills, and refuses automation, scraping, pods, and bulk DMs before any drafting starts.
react-component-refactor
Analyzes React component structure, identifies reusable units, and refactors large or messy components into clean, well-organized code. Strictly maintains 1:1 logic equivalence — only structure changes, never behavior. Should be used when the user wants to refactor a React component — splitting a monolith, reorganizing a messy file, or restructuring for better maintainability. Distinguished from react-component-extraction which extracts specific reusable pieces, this skill restructures the entire component.
linkedin-profile
Use when someone wants their LinkedIn profile audited or rewritten — headline, About section, experience bullets, Featured, banner, recommendations — or says "fix my headline", "my profile gets views but nothing happens", "optimize my LinkedIn profile", "what should my About section say". Scores the headline on five dimensions, audits the whole profile 0-100 and ranks fixes by points per hour, and assembles an About section that survives the "…see more" fold.
react-component-extraction
Extracts reusable UI or stateful logic into independent components or custom Hooks. Analyzes context dependencies, evaluates extraction boundaries, and ensures zero breakage for existing callers. Should be used when the user wants to extract, split, or isolate a piece of React code — creating reusable components, custom Hooks, or separating concerns within a large component. Distinguished from react-component-refactor which restructures the entire component, this skill focuses on extracting specific reusable pieces.