Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
dynamic-res-scaler
Implement dynamic resolution scaling for React Three Fiber / Three.js by adjusting DPR based on measured FPS. Use when asked to add adaptive performance scaling, automatic DPR tuning, or a DynamicResScaler-style component in a R3F scene.
majiayu000/claude-skill-registry 163
-
github-issue-standard
Mandatory format standard for ALL GitHub issues created by SpecWeave with checkable acceptance criteria and proper metadata. Use when creating GitHub issues, formatting issue content, or ensuring consistent issue structure. Covers user stories, epics, features, and increments.
majiayu000/claude-skill-registry 163
-
security-shield
**SECURITY SHIELD**: '보안', '인증', '로그인', '비밀번호', 'JWT', '토큰', '암호화', '취약점', 'SQL 인젝션', 'XSS', '보안 검사' 요청 시 자동 발동. .env/auth/**/guard/** 파일 작업 시 자동 적용. 하드코딩 시크릿 탐지(40+ 패턴), OWASP Top 10 검증.
majiayu000/claude-skill-registry 163
-
gh-issue
Create a GitHub issue following project guidelines
majiayu000/claude-skill-registry 163
-
time
Time and timezone utilities for getting current time and converting between timezones. Use when: (1) Getting current time in any timezone, (2) Converting time between different timezones, (3) Working with IANA timezone names, (4) Scheduling across timezones, (5) Time-sensitive operations. Triggers: "what time is it", "current time", "convert time", "timezone", "time in [city]". Supports both MCP server and standalone CLI.
majiayu000/claude-skill-registry 163
-
emotional-design
Los tres niveles de procesamiento emocional de Don Norman. Use cuando diseñe para engagement, satisfacción del usuario, o diferenciación de producto.
majiayu000/claude-skill-registry 163
-
love-font
majiayu000/claude-skill-registry 163
-
observability-setup
Set up logging, metrics, health checks, and alerting. Creates observability infrastructure for production systems. Use when user says 'monitoring', 'observability', 'metrics', 'logging', 'alerts', or 'health check'.
majiayu000/claude-skill-registry 163
-
agent-tool-builder
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa
majiayu000/claude-skill-registry 163
-
design-handoff
Prepare designs for development handoff. Document specifications, interactions, and assets to enable efficient development and maintain design quality.
majiayu000/claude-skill-registry 163
-
umbraco-icons
Implement custom icons in Umbraco backoffice using official docs
majiayu000/claude-skill-registry 163
-
ln-774-healthcheck-setup
Configures health check endpoints for Kubernetes readiness/liveness/startup
majiayu000/claude-skill-registry 163
-
building-plugins
Expert at creating and managing Claude Code plugins that bundle agents, skills, commands, and hooks into cohesive packages. Auto-invokes when the user wants to create, structure, validate, or publish a complete plugin, or needs help with plugin architecture and best practices. Also auto-invokes proactively when Claude is about to create plugin directory structures, write plugin.json manifests, or implement tasks that involve bundling components into a plugin package.
majiayu000/claude-skill-registry 163
-
mermaid-tools
Extracts Mermaid diagrams from markdown files and generates high-quality PNG images using bundled scripts. Activates when working with Mermaid diagrams, converting diagrams to PNG, extracting diagrams from markdown, or processing markdown files with embedded Mermaid code.
majiayu000/claude-skill-registry 163
-
tailscale
Mesh VPN.
majiayu000/claude-skill-registry 163
-
ai-model-cloudbase
Complete guide for calling AI models with CloudBase - covers JS/Node SDK and WeChat Mini Program. Text generation, streaming, and image generation.
majiayu000/claude-skill-registry 163
-
ext-triage-java
Triage extension for Java findings during plan-finalize phase
majiayu000/claude-skill-registry 163
-
icp-creator
Create detailed Ideal Client Profile through guided interview. Use when the user needs to define their target audience, understand their customers' problems and language, or build an ICP for content targeting.
majiayu000/claude-skill-registry 163
-
mcp-server-instructions
Write effective MCP server instructions for tool compaction support. Use when creating or updating the `instructions` parameter in MaaSProtectedFastMCP server initialization. Helps LLMs understand when to search for tools, workflow patterns, and cross-feature relationships.
majiayu000/claude-skill-registry 163
-
finish-es_latam-audiobook
Финализация аудиокниги ru→es_latam. Проверяет что ВСЕ переводы готовы, генерирует TTS, комбинирует аудио, ищет фоновую картинку, создаёт видео. Использовать ТОЛЬКО после завершения claude-translation-pipeline-es_latam.
majiayu000/claude-skill-registry 163
-
derangement-crdt
Derangement-CRDT Skill
majiayu000/claude-skill-registry 163
-
labarchive-integration
Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.
majiayu000/claude-skill-registry 163
-
bug-health-inline
Inline orchestration workflow for automated bug detection and fixing. Provides step-by-step phases for bug-hunter detection, priority-based fixing with bug-fixer, and verification cycles.
majiayu000/claude-skill-registry 163
-
api-security-enforcer
Apply rate limiting, input validation, and injection defenses.
majiayu000/claude-skill-registry 163