Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
dramatic-2000ms-plus
Use when building extended animation sequences over 2000ms - cinematic intros, story sequences, premium experiences where animation IS the product
majiayu000/claude-skill-registry 163
-
basis
majiayu000/claude-skill-registry 163
-
youtube-transcribe
Download YouTube video transcripts with timestamps. Use when asked to transcribe a YouTube video, get transcript, or extract text from a video URL.
majiayu000/claude-skill-registry 163
-
autonomous-loop
Manages autonomous iterative development loops that repeat until completion. Use when asked to loop, iterate, keep going until done, work autonomously, run overnight, or continue until a condition is met. Supports checkpointing, cost tracking, and safety limits.
majiayu000/claude-skill-registry 163
-
skill-author
Guide for creating new Claude Code skills following best practices. Use when the user asks to create a new skill, agent capability, or wants to extend Claude's autonomous functionality.
majiayu000/claude-skill-registry 163
-
codex-safe-experiment
Use Codex CLI sandbox mode to try risky changes safely. Isolated experimentation with network disabled and directory restrictions.
majiayu000/claude-skill-registry 163
-
litestream
SQLite disaster recovery and streaming replication to cloud storage (S3, GCS, Azure, SFTP, NATS). Use this skill for configuring Litestream, deploying to cloud platforms, troubleshooting WAL replication issues, implementing point-in-time recovery, and setting up VFS read replicas.
majiayu000/claude-skill-registry 163
-
interface-builder-validator
Parse and validate XIB/Storyboard files for broken outlets, warnings, accessibility
majiayu000/claude-skill-registry 163
-
neovim-debugging
Debug Neovim/LazyVim configuration issues. Use when: user reports Neovim errors, keymaps not working, plugins failing, or config problems. Provides systematic diagnosis through hypothesis testing, not just checklists. Think like a detective narrowing down possibilities.
majiayu000/claude-skill-registry 163
-
trust-reliability
Use when creating animations that build user confidence, establish credibility, and communicate dependability.
majiayu000/claude-skill-registry 163
-
eval
EvalKit is a conversational evaluation framework for AI agents that guides you through creating robust evaluations using the Strands Evals SDK. Through natural conversation, you can plan evaluations, generate test data, execute evaluations, and analyze results.
majiayu000/claude-skill-registry 163
-
playwright-browser-select-option
To choose an option in a dropdown, select one or more values in a select element.
majiayu000/claude-skill-registry 163
-
differentiation-schemes
Select and apply numerical differentiation schemes for PDE/ODE discretization. Use when choosing finite difference/volume/spectral schemes, building stencils, handling boundaries, estimating truncation error, or analyzing dispersion and dissipation.
majiayu000/claude-skill-registry 163
-
plan-creating-project-plans
Comprehensive project planning standards for plans/ directory including folder structure (ideas.md, backlog/, in-progress/, done/), naming convention (YYYY-MM-DD__identifier/), file organization (README.md for small plans, multi-file for large), and Gherkin acceptance criteria. Essential for creating structured, executable project plans.
majiayu000/claude-skill-registry 163
-
testing-python
majiayu000/claude-skill-registry 163
-
game-analyzer
Analyze TraitorSim game logs, trust matrix evolution, voting patterns, mission outcomes, and emergent social behaviors. Use when examining game results, debugging gameplay issues, analyzing agent strategies, or when asked about game analysis, trust matrices, voting patterns, or emergent behaviors.
majiayu000/claude-skill-registry 163
-
resource-exhaustion-dos-ai-generated-code
Understand resource exhaustion and denial of service vulnerabilities in AI code including unbounded loops, missing rate limits, and uncontrolled resource consumption. Use this skill when you need to learn about DoS vulnerabilities in AI code, understand resource limits, recognize unbounded operations, or prevent resource exhaustion. Triggers include "resource exhaustion", "DoS vulnerabilities", "denial of service", "unbounded resources", "API cost protection", "memory exhaustion", "uncontrolled consumption", "rate limiting DoS".
majiayu000/claude-skill-registry 163
-
research-analyst
Conducts thorough landscape research, competitive analysis, best practices evaluation, and evidence-based recommendations. Expert in market research and trend analysis.
majiayu000/claude-skill-registry 163
-
security-review
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
majiayu000/claude-skill-registry 163
-
geocoder
Convert addresses to coordinates (geocoding) and coordinates to addresses (reverse geocoding). Use for location data enrichment or address validation.
majiayu000/claude-skill-registry 163
-
skill-reviewer-and-enhancer
This skill should be used when reviewing, auditing, or improving existing Claude Code skills to ensure they follow Anthropic best practices, have proper structure, use current domain-specific patterns, and include all necessary resources. It analyzes skill quality, identifies gaps, suggests improvements, and can automatically enhance skills with updated best practices. Trigger terms include review skill, audit skill, improve skill, enhance skill, update skill, check skill quality, skill best practices, fix skill, optimize skill, validate skill structure.
majiayu000/claude-skill-registry 163
-
react-async-patterns
Async/await correctness in React with Zustand. Use when debugging race conditions, missing awaits, floating promises, or async timing issues. Works for both React web and React Native.
majiayu000/claude-skill-registry 163
-
nix-devenv
Expert at creating Nix flakes with flake-parts for development environments. Invoked when users want to set up devShells, configure nix-direnv, create flake.nix files, or build reproducible development environments. Specializes in Python, Node.js, and Rust projects using the flake-parts modular architecture.
majiayu000/claude-skill-registry 163
-
wizard
Smart routing wizard for creating skills, agents, commands with complexity-based skill loading
majiayu000/claude-skill-registry 163