Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
Convex Integration
Guidelines for integrating Convex real-time database into the RFP Discovery application
majiayu000/claude-skill-registry 163
-
recall-reasoning
Search past reasoning for relevant decisions and approaches
majiayu000/claude-skill-registry 163
-
motherduck-explore
Discover and explore databases, tables, columns, and data shares in MotherDuck. Use when you need to understand what data is available, preview table contents, or search the data catalog.
majiayu000/claude-skill-registry 163
-
shopify-apps
Expert patterns for Shopify app development including Remix/React Router apps, embedded apps with App Bridge, webhook handling, GraphQL Admin API, Polaris components, billing, and app extensions. Use when: shopify app, shopify, embedded app, polaris, app bridge.
majiayu000/claude-skill-registry 163
-
web3-testing
Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.
majiayu000/claude-skill-registry 163
-
x-integration
X (Twitter) integration for MatClaw. Post tweets, like, reply, retweet, and quote. Use for setup, testing, or troubleshooting X functionality. Triggers on "setup x", "x integration", "twitter", "post tweet", "tweet".
majiayu000/claude-skill-registry 163
-
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
majiayu000/claude-skill-registry 163
-
codealive-context-engine
Semantic code search and AI-powered codebase Q&A across indexed repositories. Use when understanding code beyond local files, exploring dependencies, discovering cross-project patterns, planning features, debugging, or onboarding. Queries like "How does X work?", "Show me Y patterns", "How is library Z used?". Provides search (fast, returns file locations and descriptions) and chat-with-codebase (slower, costs more, but returns synthesized answers).
majiayu000/claude-skill-registry 163
-
task-workflow
Shared implementation workflow for task-based skills. Handles status checks, assignment, environment setup, planning, implementation, review, and archival.
majiayu000/claude-skill-registry 163
-
add-cursor-pagination-tassadar2499-novatune
Add cursor-based pagination for list endpoints with stable ordering (project)
majiayu000/claude-skill-registry 163
-
spark-optimization
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
majiayu000/claude-skill-registry 163
-
bmad-testarch-automate
Expand test automation coverage for codebase. Use when user says "lets expand test coverage" or "I want to automate tests"
majiayu000/claude-skill-registry 163
-
loki
Query Loki API for cluster logs and debugging. Use when investigating application errors,
searching logs, debugging pod issues, or querying log patterns.
Use when: (1) Searching logs for errors or patterns, (2) Investigating pod or service issues via logs,
(3) Querying Kubernetes events, (4) Debugging Flux reconciliation or platform service failures,
(5) Running LogQL queries, (6) Checking log rates or volumes.
Triggers: "check logs", "search logs", "query loki", "logql", "show me logs",
"what happened in", "log errors", "find in logs", "tail logs", "kubernetes events",
"recent logs", "log query", "debug logs"
majiayu000/claude-skill-registry 163
-
document-work
Work documentation and pattern capture workflow. Use after completing significant
work to capture patterns, decisions, and learnings in project memory files
for future reference.
majiayu000/claude-skill-registry 163
-
add-electron-wrapper
Add Electron wrapper for NovaTune Player desktop app with secure token storage (project)
majiayu000/claude-skill-registry 163
-
nextjs-16-skill
majiayu000/claude-skill-registry 163
-
agent-governance
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when:
- Building AI agents that call external tools (APIs, databases, file systems)
- Implementing policy-based access controls for agent tool usage
- Adding semantic intent classification to detect dangerous prompts
- Creating trust scoring systems for multi-agent workflows
- Building audit trails for agent actions and decisions
- Enforcing rate limits, content filters, or tool restrictions on agents
- Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)
majiayu000/claude-skill-registry 163
-
filter-ai-relevant
DEPRECATED: This skill has been replaced by the analyze-article skill which provides more accurate AI-relevance filtering through LLM analysis rather than simple keyword matching.
majiayu000/claude-skill-registry 163
-
materials-and-fit
Materials and fit for the trades — how wood, metal, stone, fabric, and composite materials behave, how they move with humidity and temperature, and how "fit" between parts is achieved in the presence of material behavior. Covers moisture content, thermal expansion, grain and fiber direction, elastic and plastic deformation, corrosion and finish interaction, and the traditional allowances that experienced tradespeople build into their work. Use when specifying materials, diagnosing a failed fit, or teaching a learner why traditional allowances exist.
majiayu000/claude-skill-registry 163
-
dotfiles-development
Use when working in this dotfiles repository - modifying shell configs, SSH, neovim, or scripts. Covers symlink architecture, agent selection, and permission model.
majiayu000/claude-skill-registry 163
-
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. Use this skill when the user asks to create a poster, piece of art, design, graphics, or other static visual piece. Creates professional, museum-quality designs that replace placeholder images.
majiayu000/claude-skill-registry 163
-
draftable-automation
Automate Draftable tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
behavior-driven-testing
Systematic testing methodology for exhaustive branch coverage, edge case identification, and production bug prevention. Use when PR review reveals incomplete test coverage, when tests pass but users report bugs, when code changes break existing features, when verifying all branches and edge cases before merge, when analyzing "it works on my machine" issues, when planning test strategy for new features, or when debugging flaky tests and race conditions.
majiayu000/claude-skill-registry 163
-
add-audit-logging
Implement tamper-evident audit logging with hash chain verification for admin actions (project)
majiayu000/claude-skill-registry 163