AI Skill Hub 强烈推荐:我的克劳德 是一款优质的MCP工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
我的克劳德 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
我的克劳德 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/sehoon787/my-claude
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"-----": {
"command": "npx",
"args": ["-y", "my-claude"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 我的克劳德 执行以下任务... Claude: [自动调用 我的克劳德 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"_____": {
"command": "npx",
"args": ["-y", "my-claude"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
English | 한국어 | 日本語 | 中文 | Deutsch | Français
Looking for Codex CLI? → my-codex — same orchestration in native TOML format
---
| Category | Count | Source |
|---|---|---|
| **Agents** (always loaded) | 32 | Boss 1 + OMO 9 + OMC 19 + Vendored 3 |
| **Skills** | 139 | ECC 79 · gstack 27 · OMC 16 · Superpowers 13 · Core 4 |
| **Rules** | 54 files / 9 sets | ECC 53 (common + 8 language dirs) + Core 1 |
| **MCP Servers** | 3 | Context7, Exa, grep.app |
| **Hooks** | 8 files / 8 events | Delegation guard, telemetry, verification, vault |
| **LSP Servers** | 2 | typescript (typescript-language-server), python (pyright-langserver) |
| **Named Workflows** | 2 | code-review-fanout, upstream-audit |
| **Upstream submodules** | 4 | ecc, omc, gstack, superpowers |
| **CLI Tools** | 5 | omc, omo, ast-grep, comment-checker, codeburn |
Every agent, skill, and rule above is allowlisted in scripts/skill-allowlists.sh and tracked in the install manifest. Anthropic's official document skills (pdf, docx, …) are added separately via claude plugin add anthropics/skills and are deliberately not manifest-tracked.
<details> <summary><strong>Core Agent — Boss meta-orchestrator (1)</strong></summary>
| Agent | Model | Role | Source |
|---|---|---|---|
| Boss | Fable | Dynamic runtime discovery → capability matching → optimal routing. Never writes code. | my-claude |
</details>
<details> <summary><strong>OMO Agents — Sub-orchestrators and specialists (9)</strong></summary>
| Agent | Model | Role | Source |
|---|---|---|---|
| Sisyphus | Opus | Intent classification → specialist delegation → verification | [oh-my-openagent](https://github.com/code-yeongyu/oh-my-openagent) |
| Hephaestus | Opus | Autonomous explore → plan → execute → verify | oh-my-openagent |
| Atlas | Opus | Task decomposition + 4-stage QA verification | oh-my-openagent |
| Oracle | Opus | Strategic technical consulting (read-only) | oh-my-openagent |
| Metis | Opus | Intent analysis, ambiguity detection | oh-my-openagent |
| Momus | Opus | Plan feasibility review | oh-my-openagent |
| Prometheus | Opus | Interview-based detailed planning | oh-my-openagent |
| Librarian | Sonnet | Open-source documentation search via MCP | oh-my-openagent |
| Multimodal-Looker | Sonnet | Image/screenshot/diagram analysis | oh-my-openagent |
</details>
<details> <summary><strong>OMC Agents — Specialist workers (19)</strong></summary>
| Agent | Role | Source |
|---|---|---|
| analyst | Pre-analysis before planning | [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) |
| architect | System design and architecture | oh-my-claudecode |
| code-reviewer | Focused code review | oh-my-claudecode |
| code-simplifier | Code simplification and cleanup | oh-my-claudecode |
| critic | Critical analysis, alternative proposals | oh-my-claudecode |
| debugger | Focused debugging | oh-my-claudecode |
| designer | UI/UX design guidance | oh-my-claudecode |
| document-specialist | Documentation writing | oh-my-claudecode |
| executor | Task execution | oh-my-claudecode |
| explore | Codebase exploration | oh-my-claudecode |
| git-master | Git workflow management | oh-my-claudecode |
| planner | Rapid planning | oh-my-claudecode |
| qa-tester | Quality assurance testing | oh-my-claudecode |
| scientist | Research and experimentation | oh-my-claudecode |
| security-reviewer | Security review | oh-my-claudecode |
| test-engineer | Test writing and maintenance | oh-my-claudecode |
| tracer | Execution tracing and analysis | oh-my-claudecode |
| verifier | Final verification | oh-my-claudecode |
| writer | Content and documentation | oh-my-claudecode |
</details>
<details> <summary><strong>Vendored Agents — AI and infrastructure specialists (3)</strong></summary>
Snapshotted from agency-agents (MIT) on 2026-07-27, when that submodule was removed. Only the engineering agents with no equivalent elsewhere in the stack were kept; each file carries its upstream attribution header.
| Agent | Role | Source |
|---|---|---|
| AI Engineer | AI/ML engineering, model integration, data pipelines | agency-agents (vendored) |
| DevOps Automator | Infrastructure automation, CI/CD, cloud operations | agency-agents (vendored) |
| Multi-Agent Systems Architect | Agent topology, context management, failure recovery | agency-agents (vendored) |
</details>
<details> <summary><strong>Skills — 139 from 5 sources</strong></summary>
Each source is allowlisted in scripts/skill-allowlists.sh — anything not listed there is never installed.
| Source | Count | Key Skills |
|---|---|---|
| [everything-claude-code](https://github.com/affaan-m/everything-claude-code) | 79 | coding-standards, react-patterns, fastapi-patterns, agent-architecture-audit, e2e-testing |
| [gstack](https://github.com/garrytan/gstack) | 27 | /qa, /review, /ship, /cso, /investigate, /office-hours |
| [oh-my-claudecode](https://github.com/Yeachan-Heo/oh-my-claudecode) | 16 | autopilot, ralph, team, ultrawork, ralplan, omc-reference |
| [superpowers](https://github.com/obra/superpowers) | 13 | brainstorming, systematic-debugging, test-driven-development, writing-plans |
| [my-claude Core](https://github.com/sehoon787/my-claude) | 4 | boss-advanced, boss-briefing, briefing-vault, gstack-sprint |
</details>
<details> <summary><strong>MCP Servers (3) + Hooks (8)</strong></summary>
MCP Servers
| Server | Purpose | Cost |
|---|---|---|
| <img src="https://context7.com/favicon.ico" width="16" height="16" align="center"/> [Context7](https://mcp.context7.com) | Real-time library documentation | Free |
| <img src="https://exa.ai/images/favicon-32x32.png" width="16" height="16" align="center"/> [Exa](https://mcp.exa.ai) | Semantic web search | Free 1k req/month |
| <img src="https://www.google.com/s2/favicons?domain=grep.app&sz=32" width="16" height="16" align="center"/> [grep.app](https://mcp.grep.app) | GitHub code search | Free |
Behavioral Hooks
| Hook | Event | Behavior |
|---|---|---|
| Session Setup | SessionStart | Auto-detects missing tools + injects Briefing Vault context |
| Delegation Guard | PreToolUse | Blocks Boss from directly modifying files |
| Agent Telemetry | PostToolUse | Logs agent usage to agent-usage.jsonl |
| Subagent Verifier | SubagentStop | Forces independent verification + logs to Briefing Vault |
| Completion Check | Stop | Runs profile fallback + guards /boss-briefing execution |
| Teammate Idle Guide | TeammateIdle | Prompts leader on idle teammates |
| Task Quality Gate | TaskCompleted | Verifies deliverable quality |
| Vault Reminder | UserPromptSubmit | Suggests /boss-briefing after 5+ messages |
</details>
<details> <summary><strong>LSP Servers (2)</strong></summary>
The plugin declares two language servers in .lsp.json. Claude Code starts them on demand, so agents get diagnostics and code navigation instantly instead of paying for a build round-trip.
| Server | Command | Extensions |
|---|---|---|
| typescript | typescript-language-server --stdio | .ts .tsx .js .jsx .mjs .cjs |
| python | pyright-langserver --stdio | .py |
install.sh installs both binaries non-fatally — if one is unavailable, only that server is disabled and the rest of the install continues.
</details>
---
git clone --depth 1 https://github.com/sehoon787/my-claude.git /tmp/my-claude bash /tmp/my-claude/install.sh rm -rf /tmp/my-claude ```
For end-to-end feature implementation, Boss orchestrates a structured sprint:
Phase 1: DESIGN Phase 2: EXECUTE Phase 3: REVIEW
(interactive) (autonomous) (interactive)
───────────────────── ───────────────────── ─────────────────────
User decides scope ralph runs execution Compare vs design doc
Engineering review Auto code review Present comparison table
Confirm "design done" Architect verification User: approve / improve
Deterministic multi-agent workflows. install.sh copies them to ~/.claude/workflows/, so they run from any project through the Workflow tool — not just from this repo.
| Workflow | What It Does | Invocation |
|---|---|---|
| **code-review-fanout** | Four dimension reviewers (correctness, security, performance, tests) fan out in parallel, then every finding is adversarially verified before it is reported | Workflow({name: "code-review-fanout"}) — args: the review target (branch, commit range, paths). Defaults to the working-tree diff |
| **upstream-audit** | One analyst per upstream — pin delta vs origin, allowlist fit, new overlaps, security signals, health — followed by a synthesized action list | Workflow({name: "upstream-audit"}) — for quarterly or pre-sync audits |
---
高质量的MCP工具,值得关注
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,我的克劳德 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | my-claude |
| 原始描述 | 开源MCP工具:All-in-one agent harness for Claude Code — Boss meta-orchestrator, 200+ agents, 。⭐11 · JavaScript |
| Topics | agent-harnessai-agentsjavascript |
| GitHub | https://github.com/sehoon787/my-claude |
| License | MIT |
| 语言 | JavaScript |
收录时间:2026-06-28 · 更新时间:2026-07-03 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端