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
linkedin-engagement
Use when someone wants to grow reach through comments, replies, groups, or outreach on LinkedIn — a commenting roster, a connection request note, a DM or InMail, a networking plan, or a check on whether their outreach volume is safe. Triggers on "who should I engage with", "write a connection request", "cold DM", "LinkedIn outreach", "networking strategy", "how many invites can I send". Builds a weekly comment roster inside a real time budget, assembles one message at a time and refuses templates, and caps volume against LinkedIn's limits. Nothing is ever sent.
pre-commit-review
Chain-combined skill that merges git-commit behavior with code-review judgment to create intelligent pre-commit workflow. Encapsulates the decision of WHEN to require review before commit, WHAT to check in pre-commit review, and HOW to structure commit workflow. Use when user mentions pre-commit review, commit with review, pre-commit checks, or when they want to establish commit quality gates. Triggers especially when user says "should I review before commit?", "what should I check before committing?", "commit workflow", or when they're unsure whether their commit is ready.
linkedin-content
Use when someone wants to write, edit, or lint a LinkedIn post — a story, how-to, opinion piece, carousel script, video script, or poll — or wants an article, talk, or transcript repurposed into posts. Triggers on "write a LinkedIn post", "is this hook any good", "review my post", "turn this into LinkedIn posts", "carousel", "what format should this be". Lints posts 0-100 on mechanics, hook, integrity, and accessibility; picks the format the material actually supports; and splits long sources into standalone units with a reuse ledger.
intelligent-test-creation
Chain-combined skill for creating comprehensive, intelligent tests by combining test-think (what to test), generate-mock (mocking strategy), and setup-test-data (test fixtures). Use when user needs to write tests, wants intelligent test coverage, or when they're unsure what tests to write for a feature. Triggers especially when user says "write tests for this", "how to test this", "test coverage", "what tests do I need", or "generate test cases".
linkedin-analytics
Use when someone wants to understand their own LinkedIn numbers — which posts worked, why reach dropped, whether a pattern is real, or how to test a hypothesis. Triggers on "why did my reach drop", "what's working on my LinkedIn", "analyze my posts", "do carousels do better for me", "should I test this", "LinkedIn analytics". Reads your own exported post data, reports medians and outlier bands, tests candidate patterns against a permutation null, and sizes a real experiment — refusing to conclude anything below 10 posts.
inspect-state
Master runtime state inspection: how to examine variable values, object state, and data structures during execution. Use when debugging, understanding variable contents, or when code behavior is unexpected. Triggers especially when user says "inspect variable", "check state", "what's in this object", "variable value", "runtime inspection" or "debug state".
git-stash-management
Master git stash: when to stash, how to organize stashes, naming strategies, and recovery patterns. Use when user mentions git stash, stashing changes, saving work in progress, or when they have uncommitted changes they need to set aside. Triggers especially when user says "should I stash this?", "git stash", "save my changes", "switch branches with uncommitted work", or "recover stash".
launch-strategy
When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' 'product update,' 'GTM plan,' 'launch checklist,' or 'launch momentum.' This skill covers phased launches, channel strategy, and ongoing launch momentum.
git-rebase-safety
Master safe rebasing: when to use rebase vs merge, how to handle conflicts, and how to ensure history integrity. Use when user mentions rebasing, git rebase, rebase conflicts, rebase vs merge, or when they're unsure about rebasing strategy. Triggers especially when user says "should I rebase?", "rebase vs merge", "how to resolve rebase conflicts", or "is it safe to rebase?".
latency-critical-systems
Optimize and verify latency-sensitive systems — realtime dashboards, market data feeds, streaming agents, execution gateways, queues, and caches — by tracking p50/p95/p99 latency, freshness age, and queue depth, mapping hot paths, and running live readbacks. Use when p95 latency, throughput, or data freshness matters.
git-merge-resolution
Master git merge conflict resolution: when to merge vs rebase, conflict handling strategies, and maintaining clean merge history. Use when user encounters merge conflicts, git merge issues, or when they need to combine branch histories. Triggers especially when user says "merge conflict", "resolve conflicts", "git merge", "merge strategy", or "conflicts in git".
git-history-rewrite
Master git history manipulation: when modifying history is safe, git reset/rebase alternatives, and maintaining history integrity. Use when user mentions git history, rewriting commits, git reset, amending commits, or when they want to clean up commit history. Triggers especially when user says "clean up history", "rewrite git history", "git reset", "amend commit", or "squash commits".
git-commit
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
git-branch-strategy
Master Git branching decisions: when to create branches, naming conventions, branch lifecycle management, and cleanup strategies. Use when user mentions branching, branch names, git workflow, branch management, or when they're unsure about which branch to create or how to organize branches. Triggers especially when user says "should I create a branch?", "what should I name this branch?", "branch naming convention", "how to organize branches", or "when to create a branch".
generate-mock
Master the art of creating effective mocks: when to mock, what to mock, and how to avoid over-mocking. This skill encapsulates the judgment of mock strategy, mock depth, and maintaining test reliability. Use when user mentions mocking, mocks, test doubles, stubbing, or when they're unsure about mock strategy. Triggers especially when user says "should I mock this?", "how to mock", "mock strategy", "too many mocks", or "test mocks".
frontend-staged-bundle-review
Reviews staged git changes from a bundle size perspective. Analyzes change intent and provides optimization recommendations for React/Vue/Taro/Next.js projects. Should be used when the user is concerned about bundle size, code bloat, or package weight — before committing or evaluating new dependencies. Distinguished from frontend-code-review which focuses on code quality, this skill focuses specifically on bundle size impact analysis.
frontend-code-review
Comprehensive frontend code quality audit covering ESLint, robustness, side effects, and performance for React/Vue/Taro projects. Should be used when the user needs a thorough code quality check — before committing, during PR review, after refactoring, or when inheriting someone else's code. Distinguished from staged-code-review which focuses on git staged changes pre-commit, this skill focuses on general frontend code quality auditing.
landing
Generates a premium single-page HTML landing page with 3D CSS animations, GSAP scroll effects, and mouse-parallax depth. Forcing intake (product + elevator pitch, audience register, brand overrides, tone) locks down positioning before any copy or markup is written, so the page reflects the actual product rather than generic boilerplate. Use whenever the user says 'landing for X', 'create a landing page', 'build a landing page', 'make a landing page for X', 'I need a web page for Y', or provides product/service details and wants a polished website. Also triggers on 'promotional page', 'product page', 'one-pager', 'web presence', 'sales page'. Outputs a single self-contained HTML file (Claude Code) or HTML artifact (Claude.ai). Supports configurable brand colors via CSS custom property overrides.