Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
reverse-engineer-rpi
Reverse-engineer a product into a feature catalog, code map, and specs. Uses RPI-style loop with verification gates. Triggers: “reverse engineer”, “catalog features”, “feature inventory”, “code map”, “docs to code mapping”, “binary analysis”.
majiayu000/claude-skill-registry 163
-
radix-ui-design-system
Build accessible design systems with Radix UI primitives. Headless component customization, theming strategies, and compound component patterns for production-grade UI libraries.
majiayu000/claude-skill-registry 163
-
mac-maintenance-cleanup
macOS 系统深度清理和优化工作流。当用户需要以下操作时使用：(1) 清理系统缓存、日志和临时文件，(2) 卸载应用及其残留文件，(3) 分析磁盘空间使用情况，(4) 清理开发项目构建产物，(5) 系统优化和性能提升，(6) 任何关于 Mac 清理和维护的请求。提供交互式菜单、智能诊断和混合模式（指导+自动执行）。
majiayu000/claude-skill-registry 163
-
clean-code
Comprehensive clean code workflow that analyzes codebase, recommends best practices, and applies clean code principles for React, Next.js, and modern tooling.
majiayu000/claude-skill-registry 163
-
tdd-mode
Activate test-driven development mode. Expert in TDD methodology following Red-Green-Refactor cycle. Use when writing tests first, implementing features with TDD, or learning test-first development practices.
majiayu000/claude-skill-registry 163
-
deserialization-php
Exploit PHP deserialization vulnerabilities during authorized penetration testing.
majiayu000/claude-skill-registry 163
-
aitask-explore
Explore the codebase interactively, then create a task for implementation.
majiayu000/claude-skill-registry 163
-
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
majiayu000/claude-skill-registry 163
-
jira-evidence
Upload screenshots to GitHub pr-assets release, update PR description with evidence, upload attachments to JIRA, post wiki markup comment, and move ticket to Code Review. Reusable by any skill that captures screenshots and generates evidence/comment.txt + evidence/comment.md.
majiayu000/claude-skill-registry 163
-
learn-rule
Capture a correction or lesson as a persistent learning rule with category, mistake, and correction. Stores, categorises, and retrieves rules for future sessions. Use after mistakes or when the user says "remember this", "don't forget", "note this", or "learn from this".
majiayu000/claude-skill-registry 163
-
zinc-database
Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.
majiayu000/claude-skill-registry 163
-
imagemagick
Guide for using ImageMagick command-line tools to perform advanced image processing tasks including format conversion, resizing, cropping, effects, transformations, and batch operations. Use when manipulating images programmatically via shell commands.
majiayu000/claude-skill-registry 163
-
google-shopping-optimization
Optimize Google Shopping campaigns and product feeds for maximum visibility and ROAS. Feed optimization, bidding strategy, campaign structure, and Performance Max integration.
majiayu000/claude-skill-registry 163
-
database
Database development and operations workflow covering SQL, NoSQL, database design, migrations, optimization, and data engineering.
majiayu000/claude-skill-registry 163
-
writing-systems-papers
Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says "写系统论文", "systems paper structure", "OSDI paper", "SOSP paper", or wants fine-grained structural guidance for a systems conference submission.
majiayu000/claude-skill-registry 163
-
qms-audit-expert
ISO 13485 internal audit expertise for medical device QMS. Covers audit planning, execution, nonconformity classification, and CAPA verification. Use for internal audit planning, audit execution, finding classification, external audit preparation, or audit program management.
majiayu000/claude-skill-registry 163
-
testing-principles
Core testing principles for any language. Use when writing tests or reviewing test code without a language-specific testing skill loaded.
majiayu000/claude-skill-registry 163
-
code-review
Review code for bugs, security vulnerabilities, performance issues, and maintainability. Trigger with "review this code", "check this PR", "look at this diff", "is this code safe?", or when the user shares code and asks for feedback.
majiayu000/claude-skill-registry 163
-
ml-pipeline-workflow
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
majiayu000/claude-skill-registry 163
-
ticks
Work with Ticks issue tracker and AI agent runner. Use when managing tasks or issues with tk commands, running AI agents on epics, creating ticks from a SPEC.md, or working in a repo with a .tick directory. Triggers on phrases like create ticks, tk, run ticker, epic, close the task, plan this, break this down.
majiayu000/claude-skill-registry 163
-
commit
Create a git commit following the project's versioning guidelines with phase/task format. Use when user wants to commit changes or runs /commit.
majiayu000/claude-skill-registry 163
-
boost-modules
Create custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware.
majiayu000/claude-skill-registry 163
-
interpret-feedback
Interpret third-party feedback by running parallel internal and peer interpretations to surface intent, correctness concerns, and ambiguities. Use when the user asks to "interpret feedback", "interpret comments", "what does this feedback mean", "clarify reviewer intent", "understand this review", or "interpret these suggestions".
majiayu000/claude-skill-registry 163
-
domain-feature-design
Guides agents through proper domain/feature design following Organon methodology. Ensures RFCs contain both organon mutation plan (ETHOS.md, PHILOSOPHY.md content) AND technical implementation plan (architecture, API, phases). Prevents common mistake of writing only technical plan or only organon plan. Use when designing new domains, features, or significant capabilities that require organon evolution.
majiayu000/claude-skill-registry 163