Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
pypi-readme-creator
When creating a README for a Python package. When preparing a package for PyPI publication. When README renders incorrectly on PyPI. When choosing between README.md and README.rst. When running twine check and seeing rendering errors. When configuring readme field in pyproject.toml.
majiayu000/claude-skill-registry 163
-
feedback-triage
Use when receiving UAT feedback, bug reports, user testing results, stakeholder feedback, QA findings, or any batch of issues to investigate. Investigates each item BEFORE creating issues, classifies by type and priority, creates well-formed GitHub issues with proper project board integration.
majiayu000/claude-skill-registry 163
-
error-message-design
ユーザーフレンドリーなエラーメッセージの設計を専門とするスキル。
エラーコード体系、多言語対応（i18n）、アクション指向のメッセージ設計を提供。
Anchors:
- The Pragmatic Programmer / 適用: 実践的改善 / 目的: 品質維持
- Nielsen Norman Group UX Guidelines / 適用: エラーメッセージ設計 / 目的: ユーザビリティ向上
Trigger:
Use when designing error messages, creating error code systems, implementing i18n for errors, or building user-friendly error responses.
error message, error code, i18n, user-friendly, validation error, API error response
majiayu000/claude-skill-registry 163
-
tailwind-styling
Tailwind CSS styling patterns, dark theme implementation, and theme management for this project. Use when styling components, implementing UI changes, or working with the design system.
majiayu000/claude-skill-registry 163
-
sequential-thinking
Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis needing course correction, problems with unclear scope, multi-step solutions, and hypothesis-driven work.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
mcp-server-reviewing
Audits MCP servers for security vulnerabilities, missing validation, error handling issues, and production readiness. Use when reviewing MCP PRs or auditing server quality.
majiayu000/claude-skill-registry 163
-
full-workflow
Complete testing workflow from site discovery to test automation with Qase integration. Use when user wants end-to-end testing setup for a website. Triggers on "test this site", "create test suite for", "help me test", "full testing workflow", "automate testing for".
majiayu000/claude-skill-registry 163
-
config-hardening
Harden configuration and defaults for safer deployment. Use when a mid-level developer needs to reduce misconfig risks.
majiayu000/claude-skill-registry 163
-
rust-zero-cost
零成本抽象与泛型专家。处理泛型, trait, monomorphization, static dispatch, dynamic dispatch, impl Trait, dyn Trait, 泛型, 特征, 单态化, 零成本抽象
majiayu000/claude-skill-registry 163
-
convex-security-check
Quick security audit checklist covering authentication, function exposure, argument validation, row-level access control, and environment variable handling
majiayu000/claude-skill-registry 163
-
matlab-test-generator
Create comprehensive MATLAB unit tests using the MATLAB Testing Framework. Use when generating test files, test cases, unit tests, test suites, or when the user requests testing for MATLAB code, functions, or classes.
majiayu000/claude-skill-registry 163
-
generating-conventional-commits
Generates conventional commit messages using AI. It analyzes code changes and suggests a commit message adhering to the conventional commits specification. Use this skill when you need help writing clear, standardized commit messages, especially after making code changes and preparing to commit. Trigger with terms like "create commit", "generate commit message", or "write commit".
majiayu000/claude-skill-registry 163
-
dag-scope-enforcer
Runtime enforcement of file system boundaries and tool access restrictions. Blocks unauthorized operations and logs violations. Activate on 'enforce scope', 'access control', 'boundary enforcement', 'tool restrictions', 'runtime security'. NOT for validation (use dag-permission-validator) or isolation management (use dag-isolation-manager).
majiayu000/claude-skill-registry 163
-
gui-tools
Provides guidance for installing, configuring, and choosing Git graphical interface clients (GitKraken, Sourcetree, GitHub Desktop) across platforms. Compares features, licensing, and workflows. Troubleshoots graphical tool configuration and setup issues. Use when installing Git graphical clients, setting up Git visualization tools, configuring graphical commit tools, choosing between options, or troubleshooting configuration. Covers Windows, macOS, and Linux. All tools are optional and based on user preference.
majiayu000/claude-skill-registry 163
-
db-schema-manager
Manages all database table schemas for the AI Trading System.
Use when: creating tables, validating data before insert/update,
checking schema compatibility, generating migrations, or when user
mentions database schema, table structure, column definitions,
data validation, or schema mismatch.
majiayu000/claude-skill-registry 163
-
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
majiayu000/claude-skill-registry 163
-
using-life-os
Entry point skill - introduces available Life OS skills, provides command reference, and guides users through the system
majiayu000/claude-skill-registry 163
-
api-investigator
note.com APIの調査を支援します。mitmproxyとPlaywrightを使用してHTTPトラフィックをキャプチャ・分析し、API動作を解明します。
majiayu000/claude-skill-registry 163
-
heroui-component
Scaffolds new HeroUI v3 React components using compound component patterns. Enforces named exports, onPress handlers, and direct imports from @heroui/react. Use when creating new UI components.
majiayu000/claude-skill-registry 163
-
tdd-london-chicago
Apply London (mock-based) and Chicago (state-based) TDD schools. Use when practicing test-driven development or choosing testing style for your context.
majiayu000/claude-skill-registry 163
-
cloudflare-hono
Wire Cloudflare Workers Env typings into Hono apps. Use when working in Cloudflare Workers + Hono, when the user mentions wrangler types, worker-configuration.d.ts, or typing Bindings/Env in Hono.
majiayu000/claude-skill-registry 163
-
bedrock-agents
Amazon Bedrock Agents for building autonomous AI agents with foundation model orchestration, action groups, knowledge bases, and session management. Use when creating AI agents, orchestrating multi-step workflows, integrating tools with LLMs, building conversational agents, implementing RAG patterns, managing agent sessions, deploying production agents, or connecting knowledge bases to agents.
majiayu000/claude-skill-registry 163
-
py-start-local
Start Flask server locally for development. Runs server in foreground or background with nohup. Use when starting local Python server for testing or development.
majiayu000/claude-skill-registry 163