Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Mine code MCP is a MCP for minecraft datapack/mod/ressource pack devs. It is for ai agents and provides them tools to access wikis, generators, latest bugfixes, and changelogs per update.
PythonGPL-3.0★ 15No key
A curated list of developer friendly, production ready instructions, chatmodes, prompts and toolkits for mastering GitHub Copilot.
SkillMIT★ 4Few starsNo key
Systemic and repo-local and cognitive memory for AI agents
SkillMIT★ 3Few starsNo key
Perpetual, self-correcting development loop for Claude Code: an RSI backlog loop + MAKER-style per-step error correction (decomposition + multi-agent voting, with your tests as the judge).
SkillMIT★ 2Few starsNo key
Methodology-driven Claude skill for security and code-quality audits, with threat modeling, false-positive verification and structured findings.
SkillApache-2.0★ 3Few starsNo key
Map-before-edit skill for auditable AI work on legacy codebases
SkillMIT★ 2Few starsNo key
Node.jsMIT★ 4Few starsNo key
Read-only WHOOP v2 API access for MCP clients — direct OAuth, local SQLite cache, CSV/JSONL/Parquet exports
PythonMITFew starsNeeds a key
AI 开发规范 Agent Skills(Java/Spring:开发流程/代码/注释/SQL/构建/测试/存量接入/兜底核对),单仓库一体化安装维护。A family of 8 SKILL.md agent skills for AI-driven Java/Spring development — install once, use everywhere.
SkillMIT★ 2Few starsNo key
Forge — 文档驱动的 AI 辅助开发框架 | Document-driven AI development framework with 16 Skills covering brainstorm → PRD → design → engineering → QA → review → ship → retrospective
SkillMIT★ 13No key
Forge — 文档驱动的 AI 辅助开发框架 | Document-driven AI development framework with 14 Skills covering brainstorm → PRD → design → engineering → QA → review → ship → retrospective
SkillMIT★ 13No key
X out the AI behavior you never want again - falsification-based CLAUDE.md/AGENTS.md compiler with evidence receipts
SkillMITFew starsNo key
SkillMIT★ 5No key
A command-line tool for managing Git worktrees with automation features.
SkillMIT★ 9No key
Adversarial multi-agent code review — a committee of specialist reviewers that catches what single-pass AI review misses.
SkillMIT★ 4Few starsNo key
Reflexive memory for AI agents — forgets, distills, and dreams. MCP server with 28 tools.
PythonMIT★ 5No key
Lightweight journal/memory plugin for Claude Code with zero ML dependencies. Features slash commands, proactive skills, and auto-capture hooks.
PythonMIT★ 6No key
MemRL: MCP Server for Self-Evolving Agents via Reinforcement Learning on Episodic Memory
Node.jsApache-2.0★ 6No key
Ultra Orchestration 是一套开源的 AI 工程编排技能体系。它将 OpenSpec 规格主线(Program → Milestone → Change → Slice)与 Ultra-Orchestrator 执行阶段(Intake → Plan → Dispatch → Execute → Review → QA → Deliver → Retro)结合,提升交付稳定性与可审计
SkillApache-2.0★ 6No key
High-performance persistent memory and knowledge engine for AI coding assistants via Model Context Protocol (MCP).
Node.jsApache-2.0★ 1Few starsNo key
Do Claude Code skills actually help? Benchmark AI coding agent skills, plugins & CLAUDE.md with and without them: pass rate, cost, false "done" claims, test tampering. Claude Code, OpenCode, Codex — a
Node.jsMIT★ 1Few starsNo key
Requirement-aligned development workflow for AI coding agents — a pre-coding alignment gate between PM and Developer. Zero external dependencies.
SkillMIT★ 2Few starsNo key
Reusable engineering skills and bounded review-fix loops for Codex and Agent Skills hosts.
SkillMIT★ 1Few starsNo key
AILinux TriForce control plane for multi-model AI, canonical MCP capabilities, federation and endpoint orchestration
SkillAGPL-3.0★ 1Few starsNo key
Who stands behind it