MCP servers and skills: search, filter by where they run, and compare.
Author verifiable eval records through a draft → review → revise → submit loop with server-enforced graders; compile to JSONL/CSV/Inspect/lm-eval via MCP. STDIO or Streamable HTTP.
Node.jsApache-2.0★ 1Few starsNo key
Catch when your agent skills, instructions, and rules stop triggering — or stop working.
SkillMIT★ 5No key
Agent Skill Evals helps you test agent skills with Promptfoo.
SkillMIT★ 3Few starsNo key
A Node.js package and GitHub Action for evaluating MCP (Model Context Protocol) tool implementations using LLM-based scoring. This helps ensure your MCP server's tools are working correctly and perfor
Node.jsMIT★ 134No key
Node.jsApache-2.0★ 113No key
A test runner for agentskills.io-style AI agent skills
SkillMIT★ 802No key
MCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.
Node.jsMIT★ 389No key
Capture live images from your webcam with a tool or resource request
Node.jsMIT★ 123No key
Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.
SkillMIT★ 1.1kNo key
Production patterns for agent orchestrators, harnesses, evals, MCP/A2A interoperability, memory, provider routing, and LLM usage metering.
Node.jsMIT★ 4Few starsNo key
everything-claude-code 中文翻译项目：完整的 Claude Code 配置集合（agents, skills, hooks, commands, rules, MCPs）。源自 Anthropic 黑客松获胜者的实战配置，助力中文工程师高效理解与使用 Claude Code。
Node.jsMIT★ 2.0kNo key
Composable Pi coding agent with MCP, LSP, agent chains, prompt presets, and local eval telemetry
Node.jsMIT★ 136No key
Playwright-based testing and eval framework for MCP servers with LLM-as-a-judge
Node.jsMIT★ 19No key
SQL editor/viewer for SQLite and PostgreSQL. Features an interactive Schema Visualizer, Context-Aware AI (Text-to-SQL), and transactional batch operations. Built with Electron and React.
Node.jsMIT★ 7No key
An MCP server that lets AI read, view and edit a live Adobe After Effects project — inspect comps, render frames, write keyframes and expressions, and build projects end to end. Works with Claude Code
Node.jsMIT★ 60No key
Build, validate, evaluate, and ship portable Agent Skills from a local CLI and TUI.
SkillMITFew starsNo key
Node.jsApache-2.0★ 13No key
"ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness check, penetration testin
Node.jsMIT★ 123No key
Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs
SkillMIT★ 81No key
Workbench for Agent Skills — lint, test, benchmark, and gate-install SKILL.md skills for Claude Code, Codex, Cursor, Gemini, and more
SkillMIT★ 2Few starsNo key
Blind A/B testing for AI agent skills, .cursorrules, CLAUDE.md, and system prompts. Detects placebo and harmful instructions.
SkillMIT★ 29No key
A minimal, explicit, provider-safe harness for the Pi coding agent
SkillMIT★ 15No key
Continuous, model-version-bound verification of agent skills: run a skill's eval suite with and without the skill, emit hash-verified dated receipts with confidence bands, and diff them into drift rep
SkillApache-2.0★ 2Few starsNo key
Who stands behind it
