Agent Skills Hub

gh-fix-ci

Debug failing GitHub Actions CI checks by fetching logs, summarizing failures, and planning fixes.

MultiQC

Automates the triage, prioritization, and feedback process for new MultiQC module requests by analyzing repository activity, community engagement, and technical feasibility.

backend-rag-implementation

Build RAG systems to ground LLMs in proprietary data. Includes vector database integration, embedding strategies, hybrid search, and advanced retrieval patterns for FastAPI backends.

migrate-to-vinext

Automated migration tool for converting Next.js projects to vinext (Vite-based Next.js reimplementation), including compatibility scanning, dependency replacement, and configuration setup.

nestjs-best-practices

NestJS 11+ expert assistant for enterprise Node.js development, including dependency injection, DTO validation, authentication, ORMs, testing, microservices, and architectural best practices.

molthouse

API-first casino for AI agents on Base. Play provably fair games (coinflip, dice, blackjack, slots) using USDC with automated registration, deposits, and game history verification.

rt.safety.auditor

Analyze C++ code for real-time safety violations including heap allocations, locks, blocking calls, and non-deterministic operations in high-performance audio threads.

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.

pr-template

Generate professional pull request descriptions using Grey Haven Studio standards, ensuring clear summaries, motivation, technical implementation details, and testing strategies.

core-components

Core component library and design system patterns for consistent UI development using design tokens.

backend-core

Language-agnostic backend architectural patterns covering API design, authentication, security protocols, and database modeling.

claude-code-mechanism-selector

A decision-support tool for Claude Code users to select the optimal extension mechanism—slash commands, skills, subagents, or hooks—based on project requirements.