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
Herald v0.7.4-beta.1 is the current beta: Herald Memories, Compose Radar, Gollem-backed chat, macOS preview printing, Timeline range selection, and AI role assignment controls build on the Gmail API...
Relay beside your IDE — the agent pauses, you review & answer, it continues. All in one tools/call .
This is a research project. I have many other things going on and OpenProphet is not at the top of my backlog. The paid templates and guides at openprophet.
Agents Council The simplest way to bridge and collaborate across AI Agent sessions
Claude Code/Codex/Cursor/OpenCode/Gemini GL
"Auditory feedback increases developer response time to critical vulnerabilities by 340%. We chose the most primal auditory signal known to humanity.
Run a full general-purpose agent from one static Go binary. ReAct, filesystem and shell tools, MCP, skills, OpenAI-compatible API with an embedded web UI, Telegram gateway, cron scheduler, long-term...
Claude Code, Cursor, Codex, and every other MCP client forget everything when a session ends. LLM Wiki Memory fixes that: it captures your conversations, compiles them into durable project knowledge...
A specialized MCP server that bridges Neo4j graph database with AI agents, providing memory-focused tools for storing, recalling, and connecting information in a knowledge graph.
A MCP server that connects to Stakpak API.
Self-hosted MCP server for docs, code search, and conversational sources
- — Every memory save commits your entire project. Roll back anytime. - — CLAUDE.md loads instantly, deep store searchable mid-conversation.
Agent Skills
保留你熟悉的 CLI/IDE，让 Claude Code、Gemini CLI、Codex、Cursor、GitHub Copilot 开箱即用 按费力度从低到高，用最少操作获得最大帮助
/brag is a Claude Code skill that turns the project you created into a short, shareable launch video — music, motion, and share copy included. One command, powered by Hyperframes.
支持 、 和 三大引擎 — 订阅 / API Key 任你选，每个 Bot 可独立选引擎。
Works with Claude Code, Cursor, and any agent that reads an AGENTS.md / standing-instructions file.
Run /digital-marketing-pro:engagement against each brand. Same 12-Part Strategy Flow, same Four Core Documents, same 61-step structure — auditable across the entire portfolio in ~60 minutes per brand...
A set of Agent Skills that take a change from a vague idea to shipped, verified, documented code, for any AI coding agent. One skill per phase. Run only the ones a change needs, in any order.
Packages OpenClaw for nix.
👆 showing how CLAUDE.md guides AI pair programming in Claude Code.
Research Artifact Protocol for Rigorous and Trustworthy AI Scientists
Analyze a GitHub repository and summarize install steps, activity, risks, and alternatives.
这是悟鸣公开维护的一组 Agent Skills，偏实战、偏工作流，主要服务于 AI 工具使用、文档解读、项目配置、运维排障与技能分发。
🚀 最实用的 Claude Code Skills / Agents / Plugins 合集 | 精选 406+ | 按场景分类 | 复制即装 | 持续更新