振动技能AI智能体框架
经 AI Skill Hub 精选评估，振动技能AI智能体框架 获评「推荐使用」。已获得 2.1k 颗 GitHub Star，这款AI工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 7.8 分，适合有一定技术背景的用户使用。
**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。
**安装与环境准备**
振动技能AI智能体框架 依赖 Python 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 Python 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。
**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 振动技能AI智能体框架 的版本更新，及时通知重要功能变化。
振动技能AI智能体框架 是一款基于 Python 开发的开源工具，专注于 智能体框架、Prompt模板、代理技能 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
振动技能AI智能体框架 是一款基于 Python 开发的开源工具，专注于 智能体框架、Prompt模板、代理技能 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
# 方式一：pip 安装（推荐）
pip install vibe-skills
# 方式二：虚拟环境安装（推荐生产环境）
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install vibe-skills
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/foryourhealth111-pixel/Vibe-Skills
cd Vibe-Skills
pip install -e .
# 验证安装
python -c "import vibe_skills; print('安装成功')"
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 命令行使用
vibe-skills --help
# 基本用法
vibe-skills input_file -o output_file
# Python 代码中调用
import vibe_skills
# 示例
result = vibe_skills.process("input")
print(result)
# vibe-skills 配置文件示例（config.yml） app: name: "vibe-skills" debug: false log_level: "INFO" # 运行时指定配置文件 vibe-skills --config config.yml # 或通过环境变量配置 export VIBE_SKILLS_API_KEY="your-key" export VIBE_SKILLS_OUTPUT_DIR="./output"
简介
<br/>
<a href="https://github.com/foryourhealth111-pixel/Vibe-Skills"> <img src="https://readme-typing-svg.demolab.com?font=Fira+Code&weight=700&size=45&pause=1000&color=7B61FF¢er=true&vCenter=true&width=700&height=100&lines=Vibe+Skills;Super+Skill+Harness;Agent+Orchestration+Layer" alt="VibeSkills Typing Logo" /> </a>
<br/>
<img src="./logo.png" width="260px" alt="VibeSkills Logo"/>
<br/><br/>
🧠 Requirements, Planning & Product Management
When this gets used: when the task is still fuzzy and the first job is to decide what problem is actually being solved before anyone starts coding.
Why similar skills coexist: they handle different stages of the same path. One clarifies the ask, another writes the spec, another turns that spec into a plan, and another breaks the plan into tasks.
How you usually meet them: early in a project, before a large change, or whenever a request is too vague to execute safely.
Representative entries: brainstorming, speckit-clarify, writing-plans, speckit-specify
---
🔌 External Integrations, Automation & Deployment
When this gets used: when the task depends on browsers, web content, design surfaces, external services, CI, or deployment.
Why similar skills coexist: browser interaction, content extraction, external service adapters, and deployment automation are related, but they solve different surface-level problems. playwright and scrapling, for example, both touch the web, but one is better for browser behavior and the other for fetching or extracting content efficiently.
How you usually meet them: when the work cannot stay inside the model alone and needs to touch the outside world.
Representative entries: playwright, scrapling, mcp-integration, aios-devops
---
Taken together, these categories are meant to cover different task types, different workflow stages, and different output surfaces. Similar skills usually coexist for predictable reasons: stage differences, domain specialization, host adaptation, or format-specific delivery.
</details>
<br/>
---
⚙️ Installation & Skills Management
Install first, learn the internals later. The public install path now has two clear choices: prompt-based install and command install.
Use the prompt path if you want the assistant to handle host roots and checks. Use the command path if you already know the terminal flow and want to run the commands yourself. Both paths install the same public vibe / vibe-upgrade entries.
Option 1: Prompt-Based Install (Recommended)
This is the shortest path. Choose three things, then copy one prompt into the AI app you use:
1. Pick your host: codex, claude-code, cursor, windsurf, openclaw, or opencode. 2. Pick your action: install for a first install, update if VibeSkills is already installed. 3. Pick your version: full is the recommended default; minimal is the smaller framework-only path. 4. Open the install entry: Prompt-based install (recommended) 5. Copy the matching prompt into your AI app and let it run the install and check steps.
The prompt asks the assistant to confirm host and public version first, then run the install and checks. It does not ask you to paste secrets, URLs, or model names into chat.
Option 2: Command Install
If you prefer to run commands directly, open:
Command install is useful when:
- you already know the target host root, such as
~/.codexfor Codex - you want to control the
install/checksequence yourself - you are validating install behavior in CI, a test machine, or an isolated target
The common shape is:
bash ./install.sh --host <host> --profile full
bash ./check.sh --host <host> --profile fullSee the command reference for Windows / PowerShell variants.
What install will not ask you to configure
The public install flow currently focuses on local installation, vibe discoverability, MCP auto-provision attempts, and base checks. Built-in online enhancement features are treated as not publicly configurable for now, so install docs do not guide normal users through provider, credential, or model setup for that path.
🚀 Getting Started
If VibeSkills is already installed, start with one invocation.
⚠️ Invocation note: VibeSkills uses a Skills-format runtime. Invoke it through your host's Skills entrypoint, not as a standalone CLI program.
<br/>
| Host Environment | Invocation | Example |
|---|---|---|
| **Claude Code** | /vibe | Plan this task /vibe |
| **Codex** | $vibe | Plan this task $vibe |
| **OpenCode** | /vibe | Plan this task with vibe. |
| **OpenClaw** | Skills entry | Refer to the host docs |
| **Cursor / Windsurf** | Skills entry | Refer to each platform's Skills docs |
</div>
<br/>
- First try a small request such as planning, clarifying, or breaking down a task.
- If you want later turns to stay inside the governed workflow, append
$vibeor/vibeto each message. - If VibeSkills is not installed yet, start with Prompt-based install (recommended).
MCP note:$vibeor/vibeonly enters the governed runtime. It is not MCP completion, and it does not by itself prove that MCP is installed in the host's native MCP surface.
Public host status: codex and claude-code are the clearest install-and-use paths today. cursor, windsurf, openclaw, and opencode are available too, but some of those paths are still preview-oriented or host-specific.
<br/>
---
<details> <summary><b>📚 Documentation & Installation Guides (click to expand)</b></summary>
<br/>
Start here
Open only if needed
- 🛠 Command install reference
- 🧩 Custom workflow onboarding
- 📄 OpenClaw host notes
- 📄 OpenCode host notes
- 📁 Manual copy install (offline)
- 🧊 Cold start & other environments
</details>
<br/>
🤝 Join the Community · Build Together
Give it a try! If you have questions, ideas, or suggestions, feel free to open an issue — I'll take every piece of feedback seriously and make improvements.
<br/>
This project is fully open source. All contributions are welcome!
Whether it's fixing bugs, improving performance, adding features, or improving documentation — every PR is deeply appreciated.
Fork → Modify → Pull Request → Merge ✅<br/>
⭐ If this project helps you, a Star is the greatest support you can give! Its underlying philosophy has been well-received; however, the current codebase carries some technical debt, and certain features still require refinement. We welcome you to point out any such issues in the Issues section. Your support is the enriched uranium that fuels this nuclear-powered donkey 🫏
<br/>
Thank you to the LinuxDo community for your support!
Tech discussions, AI frontiers, AI experience sharing — all at Linuxdo!
</div>
<br/>
---
🎬 Practice Demos: Real Work You Can See
People asked what VibeSkills looks like in real work. These examples are easier to judge than a feature list: each one starts with a plain goal, goes through a governed vibe run, and ends with something you can open, inspect, or rerun.
| Demo | Starting Point | How vibe Moves It Forward |
|---|---|---|
| **Image Workbench** | Build a GPT-image workspace for prompt chat, reference uploads, and real image generation. | Turns the idea into a product scope, UI/API tasks, workflow checks, and screenshot review. |
| **Video Editing Pipeline** | Recut a rocket moon-landing history clip into a short-video style edit. | Breaks the media work into caption, music, pacing, render, and review passes, with rough edges recorded plainly. |
| **ML Experiment + Paper** | Build a face-recognition ML demo and turn the run into a paper. | Guides dataset and model choice, training, evaluation, figure generation, and LaTeX compilation. |
</div>
The useful pattern is not just the final screenshot. A good demo also shows how the work moved:
Inspired by the VibeSkills 3.1.0 community practice cases: a GPT-image workbench, a video-editing run, and an ML experiment that produced a paper. The best examples link to concrete outputs: a running app, a rendered clip, a compiled paper, or the commands and evidence used to produce them.
---
成熟的AI智能体生态项目，星数稳健增长。框架设计合理，适合中高级开发者快速原型开发和生产部署。文档完善度需确认。
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- Python 依赖冲突：建议用 venv / uv 隔离环境
- CLI：直接 npm install -g / pip install，命令行调用
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- Python 依赖冲突：建议用 venv / uv 隔离环境
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
- +Apache-2.0 协议，可免费商用
- +完全开源免费，无授权费用
- +本地部署，数据完全自主可控
- +开发者社区支持，遇问题可查可问
- −安装和初始配置可能需要一定技术基础
- −功能完整性通常不如成熟商业产品
- −技术支持主要依赖开源社区，响应速度不稳定
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。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
AI Skill Hub 点评：振动技能AI智能体框架 的核心功能完整，质量良好。对于AI爱好者来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | Vibe-Skills |
| 原始描述 | 开源Prompt模板：Vibe-Skills is an all-in-one AI skills package. It seamlessly integrates expert-。⭐2.1k · Python |
| Topics | 智能体框架Prompt模板代理技能AI编程开源工具 |
| GitHub | https://github.com/foryourhealth111-pixel/Vibe-Skills |
| License | Apache-2.0 |
| 语言 | Python |
收录时间：2026-05-16 · 更新时间：2026-05-19 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。