Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
fal-audio
Text-to-speech and speech-to-text using fal.ai audio models
majiayu000/claude-skill-registry 163
-
setup
This skill should be used when user encounters "Tavily MCP error", "Tavily API key invalid", "web search not working", "Tavily failed", or needs help configuring Tavily integration.
majiayu000/claude-skill-registry 163
-
narrative-designer
Story systems and dialogue architect - Masters GDD-aligned narrative design, branching dialogue, lore architecture, and environmental storytelling across all game engines
majiayu000/claude-skill-registry 163
-
stress-testing
Test system behavior under extreme load conditions to identify breaking points, capacity limits, and failure modes. Use for stress test, capacity testing, breaking point analysis, spike test, and system limits validation.
majiayu000/claude-skill-registry 163
-
stitch-orchestrator
Master entry point for all Stitch design workflows. Routes from user request → design spec → prompt assembly → screen generation → iteration (edit, variants, design systems) → design system extraction → framework conversion (Next.js, Svelte, HTML, React Native, or SwiftUI) → optional quality pass.
majiayu000/claude-skill-registry 163
-
evaluation
Build evaluation frameworks for agent systems
majiayu000/claude-skill-registry 163
-
energy-procurement
Codified expertise for electricity and gas procurement, tariff optimisation, demand charge management, renewable PPA evaluation, and multi-facility energy cost management.
majiayu000/claude-skill-registry 163
-
Commit Message
Generate commit messages following conventional commits with scope detection
majiayu000/claude-skill-registry 163
-
orthogonal-prediction-market-odds
Get prediction market odds and prices from Polymarket and Kalshi
majiayu000/claude-skill-registry 163
-
llm-engineering
Patterns for building LLM applications - prompt engineering, RAG pipelines, cost optimization, multi-model routing, and evaluation. Auto-triggers when working with AI/LLM code.
majiayu000/claude-skill-registry 163
-
langchain-middleware
INVOKE THIS SKILL when you need human-in-the-loop approval, custom middleware, or structured output. Covers HumanInTheLoopMiddleware for human approval of dangerous tool calls, creating custom middleware with hooks, Command resume patterns, and structured output with Pydantic/Zod.
majiayu000/claude-skill-registry 163
-
database-design
Database design principles and decision-making. Schema design, indexing strategy, ORM selection, serverless databases.
majiayu000/claude-skill-registry 163
-
data-ontologist
This skill should be used when the user mentions "database design", "schema design", "graph database", "document database", "polyglot persistence", "data modeling", "Neo4j", "Supabase", "PostgreSQL", "MongoDB", discusses database architecture, choosing databases, or integrating multiple databases. Addresses when to use relational vs graph vs document databases and integration patterns.
majiayu000/claude-skill-registry 163
-
apify-influencer-discovery
Find and evaluate influencers for brand partnerships, verify authenticity, and track collaboration performance across Instagram, Facebook, YouTube, and TikTok.
majiayu000/claude-skill-registry 163
-
architect
Architectural refactoring - analyze codebase structure, detect architectural smells (god modules, circular deps, coupling), propose restructuring plan, safely move/rename files with git history, update imports, simplify architecture. Use when asked to "restructure", "reorganize", "simplify architecture", "move files", "split module", "fix structure", "reduce coupling", "reorganize folders", "clean up architecture", "refactor structure", "restructurer", "reorganiser", "simplifier".
majiayu000/claude-skill-registry 163
-
contested-claims-in-nutrition
A survey of the best-known active scientific controversies in nutrition — saturated fat and cardiovascular disease, dietary cholesterol, low-carb vs low-fat, ultra-processed foods, red meat and cancer, salt and blood pressure, and the replication status of popular single-nutrient claims. Use when a question asks whether a widely reported nutritional claim is settled, or when the department needs to distinguish "contested but plausible" from "settled" from "disproven."
majiayu000/claude-skill-registry 163
-
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".
majiayu000/claude-skill-registry 163
-
add-background-service
Create BackgroundService implementations for scheduled or polling tasks (project)
majiayu000/claude-skill-registry 163
-
Global Coding Style
Python coding style and formatting standards for stock_picker_bot using Ruff, PEP 8, and type hints. Ensures consistent code quality across FastAPI endpoints, SQLAlchemy models, and data processing logic.
majiayu000/claude-skill-registry 163
-
ml-model-retrainer
Automated pipeline for retraining ML models with new construction data. Monitor model drift, trigger retraining, and validate model performance.
majiayu000/claude-skill-registry 163
-
webmcp-setup
Set up a WebMCP project — enable Chrome flags, install MCP-B polyfill, scaffold tool registration, and configure development environment. Use when starting a new WebMCP-enabled website from scratch.
majiayu000/claude-skill-registry 163
-
resolve-review
Fetch PR review comments, run intent validation (ACCEPT/REJECT/DISCUSS) before applying fixes, and post inline replies. MCP-only — used exclusively by recipe orchestration via run_skill after review_pr reports changes_requested or needs_human verdict.
majiayu000/claude-skill-registry 163
-
pdf-handling
Extract PDFs to text and images before reading
majiayu000/claude-skill-registry 163
-
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
majiayu000/claude-skill-registry 163