Vibestack 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
Vibestack 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。
Vibestack 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/timurgaleev/vibestack
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"vibestack": {
"command": "npx",
"args": ["-y", "vibestack"]
}
}
}
# 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 Vibestack 执行以下任务... Claude: [自动调用 Vibestack 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": {
"vibestack": {
"command": "npx",
"args": ["-y", "vibestack"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
53 opinionated AI coding workflows. One install. Works in Claude Code, Cursor, and Kiro.
vibestack is a portable skill pack for AI coding agents. Slash commands like /office-hours, /ship, /investigate, /tdd, /review install once and work across every agent that supports the Agent Skills open standard — Claude Code, Cursor, Kiro, and a growing list of others. Same SKILL.md source, three folders, no vendor lock-in.
---
53 skills in nine categories. Full reference: docs/skills.md.
./install # Interactive: asks per target (recommended)
./install --target=all # All three, non-interactive
./install --target=claude # Claude Code only
./install --target=cursor,kiro # Pick a subset
./install --yes # All three, skip prompts (CI-friendly)
./install --dry-run # Preview every output, write nothing
vibestack works with any agent that implements the Agent Skills standard. v1.4 ships native install paths for three:
| Agent | Install path | Status |
|---|---|---|
| **Claude Code** | ~/.claude/skills/ | Full feature support |
| **Cursor** | ~/.cursor/skills/ | Full feature, soft-tier safety hooks |
| **Kiro** | ~/.kiro/skills/ | Full feature, soft-tier safety hooks |
Codex CLI, Gemini CLI, OpenCode, Antigravity, and Windsurf also support the spec via .agents/skills/ — adding them as native targets is tracked for v1.5+.
| Path | What lands there | Type |
|---|---|---|
~/.<agent>/skills/<each-skill>/ | One directory per skill (53) per chosen target. Contains a regular SKILL.md plus symlinks to sub-docs and hook scripts. | regular file + symlinks |
~/.vibestack/bin/ | vibe-config, vibe-slug, vibe-learnings-log, vibe-learnings-search, vibe-render-skill, vibe-skill-track | copies |
~/.vibestack/projects/ | Per-project state (learnings, design docs, test plans). Created empty. | directory |
~/.vibestack/analytics/ | Local-only analytics. Created empty. | directory |
./install is idempotent — re-runs produce identical bytes. To remove everything, see Uninstall.
~/.claude/skills/vibestack/uninstall # Claude only
~/.claude/skills/vibestack/uninstall --target=all # All three
~/.claude/skills/vibestack/uninstall --target=cursor # Cursor only
~/.claude/skills/vibestack/uninstall --target=all --delete-state # Full wipe
Mirrors ./install's --target= semantics. Removes the rendered SKILL.md file, .vibe-render.json sidecar, bin/sub-doc symlinks, and the per-skill directory (if empty) for each chosen target. Removes the vibe-* binaries from ~/.vibestack/bin/. Asks before deleting ~/.vibestack/ (your local learnings, analytics, project state) — keeps it by default. Pass --delete-state for a non-interactive full state wipe.
---
| Command | What it does |
|---|---|
/codex | Second-opinion AI reviewer via OpenAI Codex — review (pass/fail gate), challenge, or consult |
/claude | Independent second opinion from a nested Claude instance — review, challenge, or consult |
/make-pdf | Generate professional PDFs from markdown, code, or HTML — cover page, TOC, watermark support |
/setup-deploy | Configure deployment settings (platform, URL, health check) for /land-and-deploy |
/benchmark-models | Compare AI model outputs side-by-side across providers to find the best fit |
/browse | Fast headless browser: navigate, interact, screenshot, diff, assert element states |
/open-browser | Launch AI-controlled visible Chromium with real-time sidebar activity feed |
/pair-agent | Pair a remote AI agent with your browser session over a secure tunnel |
/setup-browser-cookies | Import cookies from your real browser into the headless browse session |
/setup-memory | Set up secondbrain persistent memory as an MCP tool |
| vibestack | awesome-cursor-rules / awesome-claude-prompts | Anthropic skill marketplace | One-off .cursorrules files | |
|---|---|---|---|---|
| Multi-agent (CC + Cursor + Kiro) | ✓ | — | — | — |
| Opinionated workflows (not just rules) | ✓ | — | ✓ | — |
| Slash command invocation | ✓ | ✓ | ✓ | — |
| Versioned + testable installs | ✓ | — | ✓ | — |
| No vendor lock-in | ✓ | ✓ | — | ✓ |
| Local state, no telemetry | ✓ | ✓ | — | ✓ |
---
| Command | What it does |
|---|---|
/qa | QA test a feature and fix bugs found (iterative test-fix-verify) |
/qa-only | QA audit report only — finds bugs, does not fix them |
/canary | Canary deploy health check — compare error rates and latency |
/land-and-deploy | Merge PR, monitor CI, verify production health after deploy |
Vibestack是一个有潜力的MCP工具
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。
经综合评估,Vibestack 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | vibestack |
| 原始描述 | 开源MCP工具:vibestack is a portable skill pack for AI coding agents. Slash commands like /of。⭐13 · Shell |
| Topics | ai-agentsmcpshell |
| GitHub | https://github.com/timurgaleev/vibestack |
| License | MIT |
| 语言 | Shell |
收录时间:2026-05-28 · 更新时间:2026-05-30 · 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