Explore
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
LY-AI-coderliuy821
Local
MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
ly-ai-coder — 个人 AI 编程助手
SkillMIT★ 1Few starsNo key
开源大模型部署可行性鉴别工具 · 127 个开源模型动态评估 / 硬件自动检测 / 一键部署脚本（CLI/MCP/HTTP 三协议）· 每周自动从 HuggingFace API 补模型
SkillMIT★ 3Few starsNo key
Deterministic skill discovery and routing for AI coding agents. Indexes SKILL.md libraries to cheaply filter, rank, and recommend the minimal relevant skill set for tasks using structured intent, boun
SkillMITFew starsNo key
面向 DeepSeek Harness 的微信公众号内容全流程 Agent Skills，覆盖选题、写作、审稿、配图、排版、发布和复盘。
SkillMIT★ 2Few starsNo key
静默改代码，张嘴说人话 · Close your eyes, lean back, and let your AI agent code while you talk like a boss 🛋️
SkillMIT★ 1Few starsNo key
ToolUniverse with DeepSeek integration - An ecosystem for creating AI scientist systems from any large language model
SkillApache-2.0★ 1Few starsNo key
Local-first agent OS. Spawn persistent AI agents that collaborate, write code, and use tools autonomously. Multi-model (Claude, Codex, LM Studio). Config-driven with pre-built agent presets.
SkillMIT★ 5No key
给纯文本模型（DeepSeek 等）加免费视觉能力的自动降级路由（Agent-native）。免费，但永不限流。
SkillLink only★ 5
Build AI agents in Python — from a single assistant to hierarchical multi-agent systems.
SkillMIT★ 2Few starsNo key
Static compatibility checks for Agent Skills used with DeepSeek and DSH.
SkillMITFew starsNo key
麦门四重奏 McQuartet · 一个 Skill 装四个玩法：修行录 / 团餐指挥官 / 隐藏菜单实验室 / 每日运势签。基于麦当劳中国官方 MCP，187 个测试全绿，离线演示可一键复现。
SkillMIT★ 126No key
Adversarial eval harness for any LLM agent pipeline — Claude, OpenAI, or your own. CLI + REST API + MCP server for Cursor/Antigravity.
SkillLink only★ 1Few stars
自动采集超星学习通已完成作业，AI 生成逐题解析，输出 Word + Markdown 复习资料
SkillMIT★ 7No key
Mode-based local Skill environments for Codex, Claude Code, and DeepSeek Harness.
SkillMIT★ 5No key
面向控制理论科研的 AI Agent：论文检索 / 理论推导 / 仿真实验闭环，含工具调用、Docker 沙箱、上下文压缩与本地可观测性。
SkillMIT★ 8No key
CLI that audits AI agent traces for wasted tokens — measured in dollars, with copy-paste fixes. Langfuse, LangSmith, JSONL. MIT.
SkillMIT★ 4Few starsNo key
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opin
SkillMIT★ 524No key
Offload replaceable grunt work from your premium AI agent to cheap models via MCP. Keep your subscription on the main thread; billing is physically isolated. Auto-routing + savings ledger + one-comman
SkillMIT★ 1Few starsNo key
Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org
SkillApache-2.0★ 543No key
Academic Paper Search：中文科研用户的 Codex / Claude Code / DeepSeek Harness Skill + MCP；跨 CrossRef、PubMed、arXiv、OpenAlex、Europe PMC 检索去重，支持 MeSH、引用核验、引文图谱、试验检索与审计导出。
SkillMIT★ 350No key
Who stands behind it
