MCP servers and skills: search, filter by where they run, and compare.
Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect datasets, review experiments, query annotation configs, an
OfficialSkillApache-2.0★ 40k in collectionNo key
Get RED metrics + service maps + frontend RUM + AI/LLM monitoring out of Grafana Cloud — Application Observability (`traces_spanmetrics_*` from OTel traces, p50/p95/p99 latency, exemplar-to-trace, tra
OfficialSkillApache-2.0★ 285 in collectionNo key
Turn any public GitHub repository into professional, repository-native Agent Skills for ChatGPT and Claude - free, browser-first, no AI API required.
SkillMIT★ 9No key
Playwright-based testing and eval framework for MCP servers with LLM-as-a-judge
Node.jsMIT★ 19No 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
Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic scoring, pre-registered rubric.
SkillMIT★ 51No key
A local-first cognitive substrate for neurodivergent professionals. Gives Claude memory, a sense of time, a translator for corporate ambiguity, and a guardrail that refuses to amplify rumination, hype
SkillAGPL-3.0★ 17No key
A practical open-source roadmap to build production-grade AI agents, copilots, RAG systems, MCP tools, and agentic applications.
SkillMIT★ 4Few starsNo key
Persistent, semantic news intelligence layer for AI agents — built on GNews (106k+ monthly PyPI). Python lib + MCP server + Claude Code skill.
PythonMIT★ 8No key
Portable AI agent skill for generating cinematic, scroll-driven landing pages as single-file HTML.
SkillMIT★ 3Few starsNo key
HTML design artifact generator for Claude Code: deck, prototype, animation, wireframe, canvas
SkillMIT★ 6No key
Show your presentations with charts, diagrams, and code highlighting. Works with most AI coding tools (Claude Code, Codex, Cursor, AMP).
SkillMIT★ 3Few starsNo key
Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool
SkillApache-2.0★ 758No key
Frontend AI coding agent platform with CLI, VS Code extension, desktop app, MCP server, RAG planning, Skills, SDD guardrails, browser automation, and LoRA planner models | 面向前端工程的 AI Agent 平台，支持 CLI、V
Node.jsMIT★ 120No key
Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at 66% lower cost and up to 88% fewer tokens, plus a precision-
PythonMIT★ 59No key
把数据文件（CSV/Excel/JSON/TSV）变成会讲故事的分析报告的 skill（支持 Claude Code / Codex / WorkBuddy 三家编程智能体）：先跟你确认行业与报告受众，再清洗分析，产出单文件 HTML 交互报告——结论先行的六段式、每张图配解读、数据处理过程可追溯；不杜撰行业基准、相关不当因果、小样本不硬下结论
SkillMIT★ 20No key
Text-portable Agent Skill for FEM/CAE governance: GCI mesh-independence, V&V, execution-mode gates, and headless-vs-human claim discipline across Ansys, Abaqus, Nastran, OpenFOAM, COMSOL and more.
SkillApache-2.0★ 6No key
文质 Wenzhi · 「质胜文则野，文胜质则史」—— 演示策略先行的 AI Skill（Strategy → Presentation IR → Renderer），产出可运行、可分支深潜、可动态调整的演示应用。适配 Claude Code / Codex / OpenCode / Kimi Code。
SkillMIT★ 3Few starsNo key
自动化深度产品测评 Claude Code Skill：把 ~2 小时专家级产品调研压缩到 5–60 分钟，产出结构化 Markdown + HTML 报告。聚焦产品功能的可理解性与完整性(不评 UI 美学)，面向 SaaS / AI Agent / Web 产品。
SkillGPL-3.0★ 4Few starsNo key
Who stands behind it
