MCP servers and skills: search, filter by where they run, and compare.
A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models and returns a structured synthesis, as a
Node.jsMIT★ 71No key
MCP server for orchestrating parallel Claude Code worker swarms with protocol-based behavioral governance, persistent state, and real-time monitoring dashboard
Node.jsMIT★ 117No key
Unlock rapid and reliable testing with framework, developed using Cypress and JavaScript. Designed to scale effortlessly, it is suitable for projects of any size.
SkillMIT★ 6No key
DeepSeek-native terminal coding agent — Grok-class speed + Reasonix cache discipline + Deep Code V4 surface
SkillApache-2.0★ 8No key
MCP server providing Playwright test generation wizard with intelligent prompts and best practices
Node.jsMIT★ 7No key
Skill that parse spec task.md and executes waves in parallel using git worktrees and sub-agent
SkillMIT★ 8No key
CLIC (Agentic CLI like ClaudeCode) — Command Line Intelligence Companion
SkillMIT★ 1Few starsNo key
Claude Code plugin — automates the full dev cycle (spec → plan → implement → review → clean) with adaptive skill orchestration, critic loops, 12 agents, and intent-based evaluation. Zero dependencies.
SkillMIT★ 7No key
MCP server + Hermes plugin for delegating coding tasks to Claude Code CLI sub-agents
Node.jsMIT★ 6No key
JSON-driven E2E test runner with parallel execution, Chrome pool, and Claude Code MCP integration
Node.jsApache-2.0★ 7No key
Claude Code skill for fast running agent team (swarm) of 4 agent with model setup
SkillMIT★ 2Few starsNo key
Autonomous coding agent — queue tasks, schedule jobs, and let Claude Code execute them in isolated git worktrees while you sleep
Node.jsMIT★ 6No key
Multi-Model Fusion Engine — Adaptive multi-model orchestrator that decomposes, routes, executes in parallel, and synthesizes results from multiple GLM models via z-ai-web-dev-sdk
SkillMIT★ 5No key
Agile planning + execution for AI coding agents: grill the idea, plan with OKRs, adversarial critic panel with kill authority, cheap-model story cards, parallel wave execution. MIT, no token, ever.
SkillMIT★ 3Few starsNo key
Generate a proficiency badge for your Claude Code usage — rule-based scoring engine with 53 pattern-matching rules across 5 CCA-aligned domains, auto-updating SVG badge via GitHub Gist
Node.jsApache-2.0★ 6No key
Run parallel Claude Code agents with real-time terminal UI
SkillMIT★ 5No key
Background automation daemon with skill engine, task scheduler, MCP server, and Claude Code bridge. Built with Bun.
Node.jsMITFew starsNo key
A.E.S - Bizzy: Multi-agent orchestration platform for Claude Code featuring tiered installation manifests, specialized AI agents, hooks, and skills
SkillMITFew starsNo key
Hypothesis-driven debugging with hybrid dual-track parallel execution (Claude + GPT 5.2) - A Claude Code skill
SkillLink only★ 3Few stars
Autonomous context-engineered development system. 5 agents, 17 commands, SQLite brain. 70-90% fewer tokens. Works with Claude Code, Cursor, Codex, Gemini, Windsurf + 9 more.
Node.jsMIT★ 5No key
Tetrad is a high-performance MCP (Model Context Protocol) server written in Rust that orchestrates three AI-powered CLI code evaluation tools (Codex, Gemini CLI, Qwen) to validate all code produced by
Node.jsMIT★ 1Few starsNo key
The deepest planning + most disciplined execution skills for Claude Code. Multi-agent debate. Mandatory TDD. Browser-automated QA.
SkillMITFew starsNo key
Cheaper and better Greptile alternative runs on your own github actions.
Node.jsMIT★ 117No key
How to use pstack without Cursor: universal workflow for Claude Code (pstack-claude), Pi (pi-pstack), Codex, & Gemini. Zero dependencies, v0.15.0+.
SkillMIT★ 16No key
Who stands behind it
