Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
text-summary
将长文本压缩为简洁摘要,支持多种语言
majiayu000/claude-skill-registry 163
-
Global Commenting
Write meaningful code comments that explain WHY rather than WHAT, focusing on business logic, non-obvious solutions, workarounds, and complex algorithms while keeping code self-documenting. Use this skill when adding comments to explain rationale, documenting complex business logic, explaining workarounds or temporary solutions, describing performance optimizations, writing function documentation (JSDoc, docstrings, XML docs), or reviewing code for appropriate commenting. Apply when working on any code file that contains logic requiring explanation, public API functions, complex algorithms, security-critical code, or architectural decisions. This skill ensures comments explain rationale not implementation (WHY not WHAT), self-documenting code through clear naming (refactor unclear code instead of commenting), concise and evergreen comments (no who/when dated comments - Git tracks this), links to external resources for context, proper function documentation format (JSDoc for TS/JS, docstrings for Python, XML docs for .NET), no TODO/FIXME in committed code (use issue tracking system instead and reference ticket), and deletion of dead commented-out code (Git history preserves it).
majiayu000/claude-skill-registry 163
-
concurrency-patterns
Implement thread-safe code, mutexes, semaphores, async/await patterns, and concurrent data structures. Use when handling parallel operations, race conditions, or building high-performance concurrent systems.
majiayu000/claude-skill-registry 163
-
Generating JJ Commit Messages
Generate descriptive commit messages for jujutsu repositories. Use when creating commits, describing changes, or when the user asks for commit message help. Follows conventional commit format and project conventions.
majiayu000/claude-skill-registry 163
-
unreal-engine-developer
Expert Unreal Engine 5 developer and technical artist for complete game development via agentic coding. Enables AI-driven control of Unreal Editor through MCP, Python scripting, Blueprints, and C++ for level design, asset management, gameplay programming, and visual development.
majiayu000/claude-skill-registry 163
-
dev-work-summary
Scan ~/dev recursively for git repos and report today's work with commits, branches, stats, and detailed change analysis. Use when user asks "what did I work on", "show my work", "daily summary", "what repos did I touch".
majiayu000/claude-skill-registry 163
-
video-concat
合并多个视频文件为一个视频。Use when user wants to 合并视频, 拼接视频, 视频合并, 视频拼接, 把视频合在一起, 连接视频, join videos, merge videos, combine videos, concatenate videos.
majiayu000/claude-skill-registry 163
-
infrastructure-engineer
Infrastructure, DevOps, and platform reliability
majiayu000/claude-skill-registry 163
-
maestro-delegation-advisor
Expert system for AgentMaestro that helps decide when and how to delegate tasks to specialized AI agents (Claude, Codex, Gemini). Use when you need to determine which agent is best suited for a task, or when a task should be broken down and delegated to multiple agents.
majiayu000/claude-skill-registry 163
-
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.
majiayu000/claude-skill-registry 163
-
continental-critical
Master Continental philosophy and Critical Theory. Use for: post-structuralism, deconstruction, Frankfurt School, hermeneutics, psychoanalysis. Triggers: 'Foucault', 'power/knowledge', 'deconstruction', 'Derrida', 'différance', 'critical theory', 'Frankfurt School', 'Adorno', 'Habermas', 'genealogy', 'discourse', 'Lacan', 'Deleuze', 'rhizome', 'biopolitics', 'ideology', 'alienation', 'reification', 'hermeneutics', 'Gadamer', 'post-structuralism', 'logocentrism'.
majiayu000/claude-skill-registry 163
-
testing-wpf
Create and maintain WPF UI tests and ViewModel tests for the .NET 8 widget host app. Use when setting up UI automation, testing MVVM logic, or building a test harness for widgets and the shell.
majiayu000/claude-skill-registry 163
-
typescript-reviewer
WHEN: TypeScript code review, type safety audit, tsconfig analysis, TS migration review
WHAT: Type safety checks + any usage audit + generic patterns + strict mode + compiler options analysis
WHEN NOT: React specific → nextjs-reviewer, Node.js backend → nodejs-reviewer, General code → code-reviewer
majiayu000/claude-skill-registry 163
-
chartjs-plugins
This skill should be used when the user asks "Chart.js plugins", "custom Chart.js plugin", "Chart.js plugin hooks", "beforeDraw plugin", "afterDraw plugin", "Chart.js plugin API", "register Chart.js plugin", "Chart.js plugin options", "Chart.js plugin lifecycle", "Chart.js plugin TypeScript", or needs help creating custom plugins for Chart.js v4.5.1.
majiayu000/claude-skill-registry 163
-
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When Claude needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket with proper context, or (5) Add information to an existing ticket. Searches Jira for similar issues, identifies duplicates, checks fix history, and helps create well-structured bug reports.
majiayu000/claude-skill-registry 163
-
google-drive-manager
Expert in Google Drive file management. Use when searching, copying, moving, uploading, downloading, sharing, or managing files and folders in Google Drive.
majiayu000/claude-skill-registry 163
-
url-readmode-markdown
Convert a web URL into reader-mode Markdown and save it as a .md file named after the content's topic/title. Use for tasks like extracting article text, cleaning noisy pages, and producing a readable Markdown file from a URL.
majiayu000/claude-skill-registry 163
-
harness-writing
Techniques for writing effective fuzzing harnesses across languages. Use when creating new fuzz targets or improving existing harness code.
majiayu000/claude-skill-registry 163
-
chrome-devtools-cli-usage
Complete guide for Chrome DevTools CLI - browser automation, debugging, performance analysis, network inspection. Use when automating Chrome, taking screenshots, analyzing performance, monitoring network/console, device emulation, or user mentions chrome-devtools, browser automation, puppeteer, debugging, performance testing, screenshot, network monitoring, console monitoring, or 크롬 개발자도구, 브라우저 자동화, 디버깅, 성능 분석.
majiayu000/claude-skill-registry 163
-
rce
远程代码执行漏洞检测与利用。当目标存在命令执行、代码执行、反序列化、模板注入、文件上传时使用。
majiayu000/claude-skill-registry 163
-
cloudflare-r2
Cloudflare R2 object storage - upload, download, list, delete files, presigned URLs. Trigger: When working with R2 storage, file uploads, object storage, presigned URLs.
majiayu000/claude-skill-registry 163
-
ice-scorer
Automatically score growth experiments using the ICE framework (Impact × Confidence × Ease). Use when the user creates a new experiment, mentions scoring or prioritization, or when analyzing experiment backlogs. Helps prioritize experiments by evaluating Impact (1-10), Confidence (1-10), and Ease (1-10).
majiayu000/claude-skill-registry 163
-
worktrunk
Guidance for Worktrunk, a CLI tool for managing git worktrees. Covers configuration (user config at ~/.config/worktrunk/config.toml and project hooks at .config/wt.toml), usage, and troubleshooting. Use for "setting up LLM", "configuring hooks", "automating tasks", or general worktrunk questions.
majiayu000/claude-skill-registry 163
-
tanaoroshi
セッションログから価値ある発見を抽出し、カテゴリ別に整理する。「棚卸し」「セッションログの整理」「発見をまとめて」などと言われたら実行。
majiayu000/claude-skill-registry 163