Agent Skills Hub

create-agent

Comprehensive guide for scaffold, configure, and structure gitagent projects. Manage agent.yaml, SOUL.md, RULES.md, and project directory layouts.

debug-hooks

Systematic debugging workflow for Claude Code hooks. Use to troubleshoot non-firing hooks, output errors, or unexpected behavioral issues.

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.

context-compression

Optimize agent performance and token usage through advanced context compression, structured summarization, and task-oriented state management for long-running sessions.

backend-development

Build, optimize, and maintain production-ready backend systems using Node.js, Python, Go, and Rust. Includes API design, database management, security, and DevOps best practices.

synapse

Autonomous pattern detection and skill recommendation engine that monitors project memory, logs, and task lists to evolve your AI agent's capabilities automatically.

copy-editing

Systematically improve marketing copy through a 7-pass editing framework to boost clarity, tone, and conversion impact.

vitest-runner

Automated Vitest management skill: handles test execution, coverage reporting, failure diagnosis, and configuration management for TypeScript/JavaScript projects.

paper-plan

Generate a structured academic paper outline from research narrative, experiment data, and review conclusions.

svelte-deployment

Expert SvelteKit deployment guidance covering production builds, static/node/cloudflare adapters, Vite configuration, and library authoring best practices.

muapi-logo-creator

Design professional-grade brand identities using geometric primitives, negative space, and flat vector-style aesthetics via AI-driven branding logic.

batch-coordinator

Validates and coordinates batch study guide operations, preventing errors by enforcing template compatibility, file availability, and source-only policies before agent execution.