Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
Local-first RAG MCP server in Python: hybrid search (semantic + BM25 keyword boost) over your own documents. 11 MCP tools + CLI, markitdown ingestion for 12 formats, multilingual embeddings, LanceDB.
VV knowledge layer for AI agents — MCP server exposing Visualize Value frameworks, voice, and content
Token-efficient code intelligence MCP server for AI coding agents.
Maybe the headless Ghidra MCP you are looking for.
MCP server for build123d to improve AI cognition when creating 3D CAD models
Keeping up with AI trends is exhausting. Claude doesn't know what happened after its training cutoff. Ask it "what's hot in AI right now?" and you get stale answers.
A lightweight, zero-footprint TypeScript MCP server that lets AI assistants drive the Godot 4.x game engine.
Stdio MCP server for sandboxed file access — read files, search content, safely edit with checksums, and manage file structure.
Install and configure MCP servers across all major AI clients with one command.
基于 的增强版本，通过**显著减少对 Figma API 的请求次数，从而缓解速率限制问题，提升稳定性与响应速度。
MCP server de dados do agronegocio brasileiro: cotacoes (boi, soja, milho, leite) e conversoes
Stdio MCP server to build, run and read reports for JMeter test plans
Agent Skills
We are moving from "prompt as text" to . Each skill acts like a lightweight, containerized application for AI work: a stable interface, opinionated workflow, and bundled resources that can be...
A behavioral governance framework for GitHub Copilot agents — skills.md and instructions to make AI coding agents think like senior engineers.
漫画风格图解生成器 Skill | 10+ 动漫风格（哆啦A梦/火影/海贼王/龙珠）| 兼容 Cursor / Claude Code / OpenClaw | 附图解 OpenClaw 示例漫画
Security skills for AI coding assistants and agentic systems
If you'd like to support these efforts consider becoming a paying Patreon member ❤️ You'll even get access to up to date lessons and other perks: patreon.com/TheHotwireClub
Official Sketch Plugin directory
Process skills that give a Reasonix coding agent the disciplines of a careful engineer: write the test first, debug from evidence, plan before coding, verify before claiming done.
*Tuned for (1M-token MSA context, native multimodal input) and (Agents Window, canvases, Design Mode, /worktree, /best-of-n, Await, MCP Apps). Written to stay useful across model changes.*
"一器而工聚焉者，车为多。" ——《考工记》 两千年前，造一辆马车是最复杂的系统工程：**承载乘者，辕定方向，辐传动力，軎辖为约束——每个构件各司其职，合而为一，车方能行。 今天，构建一个 AI Agent 亦是如此：对话循环为**，工具系统为**，权限管线为**，而将这一切承载于其上、使智能体真正运转的运行时框架—— Agent Harness——正是那个**。
🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
cv4pve-cli is to Proxmox VE what kubectl is to Kubernetes — a remote-first CLI with context switching, direct API access, and aliases for common operations.
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA