Agent Skills Hub

bmad-planner

Interactive tool for generating Business, Model, Architecture, and Design (BMAD) planning documentation for feature development.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

github-project-management

AI-driven GitHub project management using swarm coordination, automated issue triage, project board synchronization, and intelligent task decomposition for efficient development workflows.

update-llm-model-list

Audit and synchronize the supported LLM model list in assets.py against the authoritative litellm registry.

next-upgrade

Upgrade Next.js projects to the latest version using official migration guides and automated codemods.

agent-architecture

Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.

test-skill

A testing fixture for validating AI agent skill configurations and detecting rule violations.

claude-copilot

Analyze markdown documentation files to ensure compliance with predefined AI token budgets and optimize content for efficient AI ingestion.

mcp-server

Guide for integrating and managing custom Model Context Protocol (MCP) servers within the Cursor IDE environment.

eslint-checker

Automated ESLint executor for static analysis, code quality enforcement, and safe auto-fixing of JavaScript and TypeScript projects.

kreuzberg

High-performance document intelligence library for extracting text, tables, code, and metadata from 91+ file formats, with OCR and LLM-ready output.

Git Rebase Assistant

A specialized Git assistant for executing safe interactive rebases, managing commit history, and resolving merge conflicts with automated safety backups.