Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
debug-detective
Systematic debugging approach for ANY codebase, ANY language, ANY bug type. Use when facing unexpected behavior, crashes, performance issues, or intermittent problems.
majiayu000/claude-skill-registry 163
-
Backend API
Design and implement RESTful API endpoints following REST principles with clear resource-based URLs and appropriate HTTP methods. Use this skill when creating or modifying API routes, endpoints, controllers, or API handlers. When working with HTTP request/response handling, API versioning, rate limiting, or status code management. When designing URL structures, query parameters, or nested resource endpoints. When implementing API middleware, authentication endpoints, or any server-side API logic in route files, controller files, or API configuration files.
majiayu000/claude-skill-registry 163
-
languages-frameworks
Expert guidance on 9 programming languages and 10+ frameworks. Compare, select, and master language ecosystems.
majiayu000/claude-skill-registry 163
-
ccpm-mcp-management
majiayu000/claude-skill-registry 163
-
claude-skillkit
Professional skill creation with research-driven workflow and automated validation.
USE WHEN: Creating new skills, validating existing skills, deciding between Skills vs Subagents, migrating documents to skills, or running individual validation tools.
PRIMARY TRIGGERS: "create skill" = Full creation (12 steps with research + execution planning) "validate skill" = Validation workflow (steps 3-8) "Skills vs Subagents" = Decision workflow (step 0) "convert doc to skill" = Migration workflow "estimate tokens" = Token optimization "security scan" = Security audit
WORKFLOW COMPLIANCE: Structured workflows with validation checkpoints. Research phase (Step 1c-1d) ensures skills based on proven approaches.
DIFFERENTIATOR: Research-driven creation. Web search (3-5 queries) before building. Multi-proposal generation. 9 automation scripts. Quality 9.0+/10.
REUSED: Anthropic's init_skill.py and package_skill.py (production-tested).
majiayu000/claude-skill-registry 163
-
setup-rules
Set up Claude Code rules in a project by symlinking from the rbw-claude-code templates. Use this skill when users want to add Python coding standards, anti-slop rules, or other shared rules to their projects.
majiayu000/claude-skill-registry 163
-
rails-query-optimization
Optimize ActiveRecord queries to prevent N+1 queries and improve performance. Use when experiencing slow queries, optimizing database access, or implementing eager loading strategies.
majiayu000/claude-skill-registry 163
-
editor-ui-infrastructure
Guide proper usage of Editor UI infrastructure including Drawers (ButtonDrawer, ModalDrawer, TableDrawer, etc.), Elements (drag-drop targets, ComponentSelector), FieldEditors, and EditorUIConstants. Use when implementing editor panels, component editors, or any ImGui UI code to ensure consistency and code reuse.
majiayu000/claude-skill-registry 163
-
metadata-optimizer
分析和优化 Next.js 项目的元数据，包括 title、description、Open Graph、Twitter Cards。自动检测 App Router 或 Pages Router，提供长度建议、关键词优化和最佳实践指导。支持中英文双语 SEO 分析。
majiayu000/claude-skill-registry 163
-
validation-frameworks
Problem and solution validation methodologies, assumption testing, and MVP validation experiments
majiayu000/claude-skill-registry 163
-
rust-systems
Rust systems programming patterns and style guide for building reliable systems software. This skill should be used when writing Rust code, especially for systems programming, CLI tools, or performance-critical applications. Covers project organization with Cargo workspaces, module structure, naming conventions (RFC 430), type/trait patterns (Option, builders, associated types), and error handling with thiserror/anyhow.
majiayu000/claude-skill-registry 163
-
create-prompt
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
majiayu000/claude-skill-registry 163
-
constraints-physics
Implements constraint-based physics systems including all constraint types, ragdoll systems, custom physics, and network ownership. Use when building mechanical systems, ragdolls, rope physics, or any physics-driven gameplay.
majiayu000/claude-skill-registry 163
-
doherty-threshold
Mantén tiempos de respuesta bajo 400ms para mantener la atención del usuario. Use cuando optimice performance, diseñe feedback de carga, o evalúe latencia percibida.
majiayu000/claude-skill-registry 163
-
report-standards-analysis
Specialized skill for analyzing institutional and commercial space standards to identify gaps and opportunities for LORS.
majiayu000/claude-skill-registry 163
-
defining-product-vision
Define or refresh a product vision and produce a shareable Product Vision Pack (vision statement, narrative, pillars, strategic choices, rollout). Use for product vision, vision statement, product direction, long-term product strategy.
majiayu000/claude-skill-registry 163
-
ask-user
Pattern for effectively interacting with users to gather information or get decisions. Use when you need user input.
majiayu000/claude-skill-registry 163
-
mcaf-architecture-overview
Create or update `docs/Architecture/Overview.md` (architecture diagrams): maintain Mermaid diagrams for system/modules, interfaces/contracts, and key classes/types; document dependency rules; link to ADRs/features. Use when onboarding, refactoring, or adding modules/boundaries.
majiayu000/claude-skill-registry 163
-
better-auth-python
Better Auth JWT verification for Python/FastAPI backends. Use when integrating Python APIs with a Better Auth TypeScript server via JWT tokens. Covers JWKS verification, FastAPI dependencies, SQLModel/SQLAlchemy integration, and protected routes.
majiayu000/claude-skill-registry 163
-
plr-thread-coloring
PLR (Parallel/Leading-tone/Relative) transitions for thread coloring. One-hot keyspace reduction to GF(3) trits for behavior indexing. Grows perception/action information field capacity through efficient user illusion.
majiayu000/claude-skill-registry 163
-
cc-debugging
Guide systematic debugging using scientific method: STABILIZE -> HYPOTHESIZE -> EXPERIMENT -> FIX -> TEST -> SEARCH. Two modes: CHECKER audits debugging approach (outputs status table with violations/warnings), APPLIER guides when stuck (outputs stabilization strategy, hypothesis formation, fix verification). Use when encountering ANY bug, error, test failure, crash, wrong output, flaky behavior, race condition, regression, timeout, hang, or code behavior differing from intent. Triggers on: debug, fix, broken, failing, investigate, figure out why, not working, it doesn't work, something's wrong.
majiayu000/claude-skill-registry 163
-
brain-dump-ingestion
Process unstructured brain dumps, transcripts, and stream-of-consciousness notes into structured knowledge base content. Use when converting raw ideas, meeting notes, or recorded thoughts into organized documentation.
majiayu000/claude-skill-registry 163
-
safe-refactoring
Change code structure without changing behavior, with zero tolerance for behavioral changes
majiayu000/claude-skill-registry 163
-
ios-patterns
iOS-specific patterns for Swift and SwiftUI. Use when building iOS applications.
majiayu000/claude-skill-registry 163