refly-ai /

refly

趋势观察中

The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.

原始仓库简介 · 中文摘要待补充 · agent / agent-skills / automation / claude / clawdbot / codex

GitHub 仓库 ↗项目主页 ↗

README / 项目原文

README.md ↗抓取于 2026/10/24 00:49:26

the first open-source agent skills builder

Refly — Agent Skills Builder Powered by Vibe Workflow

English · 中文

APIs for Lovable · Webhooks for Lark/Feishu · Skills for Claude Code · Build Clawdbot

Skills are not prompts. They are durable infrastructure.

Refly is the first open-source platform for building stable, atomic, and versioned agent skills.

Try it Now

Refly Skills

Refly Skills is the official executable skill registry for Refly.

⚡ Run instantly: Execute skills in Refly with one click
🧩 Reusable infrastructure: Versioned skills, not one-off prompts
🔌 Export anywhere: Ship skills to Claude Code or deploy as APIs
🌍 Community-powered: Import, fork, and publish your own skills

Explore the registry: Refly Skills Repo

Skills are deterministic agent capabilities—reusable across workflows, teams, and runtimes.

TL;DR: Refly compiles your enterprise SOPs into executable agent skills. Built in 3 minutes. Shipped anywhere.

Quick Start

Deploy Refly

📘 Self-Deployment Guide
(Recommended for Developers) Step-by-step guide to deploying Refly on your own server using Docker.
🔌 API Reference
Complete API documentation for integrating Refly into your applications.

[!TIP] Want to explore instantly? Open the hosted workspace: Refly Workspace

What's Next?

After deployment, choose your path based on your use case:

I want to...	Start here	Time
🔧 Build my first workflow	Create a Workflow	5 mins
🔌 Call workflows via API	API Integration	10 mins
💬 Connect to Lark/Feishu	Webhook Setup	15 mins
🤖 Export for Claude Code	Export Skills	15 mins
🦞 Build a Clawdbot	Build Clawdbot	20 mins

Why Refly?

Most AI Agents fail in production because they rely on "Vibe-coded" scripts and fragile, black-box logic. As the ecosystem moves toward agentic frameworks like Claude Code, AutoGen, and MCP, the bottleneck is no longer the LLM—it's the lack of standardized, reliable actions.

Refly bridges the gap between raw APIs and intelligent agents. We allow you to codify messy business logic into structured, version-controlled Agent skills that any agent can invoke with 100% reliability.

Stop hard-coding tools. Build modular skills once in Refly's visual IDE and deploy them as MCP servers, standard APIs, or portable SDKs to any agent framework. Try it Now

Core Capabilities

🎯 Construct with Vibe (Copilot-led Builder)

Describe your business logic in natural language, and Refly's Model-Native DSL compiles your intent into a high-performance skill.

Intent-Driven Construction: Describe the work once; Refly turns intent into deterministic, reusable, and composable skills.
Efficiency at Scale: Streamlined DSL optimized for LLMs, ensuring fast execution and significantly lower token costs.
3-Minute Deployment: Transition from a static enterprise SOP to a production-ready agent skill in under 3 minutes.

⚡ Execute with Control (Intervenable Runtime)

Break the "black box" of AI execution with a stateful runtime designed for deterministic reliability.

Intervenable Runtime: Pause, audit, and re-steer agent logic mid-run to ensure 100% operational compliance.
Deterministic Guarantees: Enforce strict business rules that minimize hallucinations and handle failure recovery.

🚀 Ship to Production (Unified Agent Stack)

Unify MCP integrations, tools, models, and reusable skills into a single execution layer.

Universal Delivery: Export as APIs for Lovable, webhooks for Slack or Lark/Feishu, or native tools for Claude Code and Cursor.
Stable Scheduling: Run workflows reliably on schedule with managed execution.

🏛️ Govern as Assets (Skill Registry)

Transform fragile scripts into governed, shared infrastructure across your organization.

Central Skill Registry: Securely manage, version, and share agent capabilities.
Team Workspace Collaboration: Build together with native version control and audit logs.

Ecosystem

Refly is designed to be the universal bridge between your existing enterprise toolchain and the next generation of agentic runtimes.

Tooling & Protocols (Inputs)

Bring your own data and logic into Refly with zero friction.

3,000+ Native Tools: Seamlessly integrate with Stripe, Slack, Salesforce, GitHub, etc.

A full list of supported model and tools providers can be found in provider-catalog.json.

part supported tools integrations in refly

MCP Support: Full compatibility with Model Context Protocol servers
Private Skill Connectors: Connect to your databases, scripts, and internal systems

Agent Runtimes & Platforms (Outputs)

Export your deterministic skills to any environment where work happens.

deterministic skills can be exported to cursor, claude code and etc.

AI Coding Tools: Native export for Claude Code and Cursor (coming soon)
App Builders: Power Lovable or custom frontends via stateful APIs
Automation Hubs: Deploy as webhooks for Slack, Lark/Feishu, or Microsoft Teams
Agent Frameworks: Compatible with AutoGen, Manus, LangChain, and custom Python stacks

Why Teams Choose Refly

For Builders: From Vibe to Production

Most agent tooling today falls into two categories:

Workflow builders (n8n, Dify): Great for orchestration, but workflows are fragile, trigger-only "black boxes," and hard to reuse.
Agent frameworks (LangChain): Powerful primitives, but require heavy engineering, manual boilerplate, and high maintenance to keep running. Refly eliminates the friction of manual configuration, giving you the fastest path from a "vibe" to a usable agent tool. By using our Streamlined DSL, you get the speed of a GUI with the precision of code.

Dimension	Legacy Automation _{(n8n, Dify)}	Code-First SDKs _(LangChain)	Refly Skills
Interaction Depth	Trigger-only _{Black box}	Programmatic _{Code changes}	Intervenable runtime _{Steer logic mid-run}
Construction	Manual API wiring & JSON	Manual Python/TS boilerplate	Copilot-led _{Describe intent → skills generated}
Recovery	Fail = restart from scratch	Debug → redeploy → rerun	Hot-fix _{Repair workflows during execution}
Portability	Hard to reuse across environments	Framework-specific	Export everywhere _{To Claude Code, Cursor, Manus}
Deployment	Limited function tools	Custom microservices	Production Ready _{Stateful, validated APIs}

For Enterprise: Scalable Skills Governance

Workflow tools like n8n are great for basic connectivity, and frameworks like LangChain offer powerful primitives — but neither provides the governed, production-ready capability layer required for enterprise agent infrastructure.

Refly acts as the Agent skills builder, providing the governance and reliability infrastructure required to deploy AI across the entire organization.

Enterprise Requirement	Legacy Tools _{(Workflow-first)}	SDKs _(Code-first)	Refly (Skill OS)
Governance & Reuse	Templates are copied and _{reconfigured per instance}	No native registry _{for sharing logic}	Central skill registry _{Versioned, shareable capability assets}
Operational Reliability	Trigger-based _{limited recovery}	Custom handling required	Stateful runtime _{With validation + failure recovery}
SOP Enforcement	Workflows drift _{across copies}	Depends on manual _{engineering discipline}	SOP-grade deterministic skills _{With controlled execution}
Deployment	Instance-bound workflows	Code maintained manually _{per team}	Local-first, on-prem ready _{Open-source infrastructure}
Total Cost (TCO)	Overhead grows with _{workflow complexity}	High engineering _{maintenance costs}	Minimal DSL _{Reduces token spend}

Create Your First Workflow

[!NOTE] This section assumes you have completed self-deployment and can access Refly at http://localhost:5700

Step 1: Register and Log In

Open http://localhost:5700 in your browser
Register with your email and password
Configure your first model provider:
- Click the account icon (top right) → Settings
- Add a provider (e.g., OpenAI, Anthropic)
- Add your first chat model
- Set it as default

📖 Detailed setup with screenshots: Self-Deployment Guide

Step 2: Create a Workflow

Click "New Workflow" on the home page
Choose a template or start from scratch:
- Blank Canvas: Build with visual nodes
- Vibe Mode: Describe your workflow in natural language

Example - Product Research Workflow:

1. Add "Web Search" node - searches for product information
2. Add "LLM" node - analyzes search results
3. Add "Output" node - formats the report
4. Connect the nodes
5. Click "Save"

[!TIP] If you want the fastest path, start with Vibe Mode and iterate from a template.

Step 3: Test Your Workflow

Click "Run" button
Enter test input (e.g., a product URL)
View execution results in real-time
Check logs if something fails

Use Cases

Use Case 1: API Integration

Goal: Call your workflow from your application via REST API

Get Your API Credentials

Go to Settings → API Keys
Click "Generate New Key"
Copy your API key (keep it secure!)

Make Your First API Call

curl -X POST https://your-refly-instance.com/api/v1/workflows/{WORKFLOW_ID}/execute \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "product_url": "https://example.com/product"
    }
  }'

Response:

{
  "execution_id": "exec_abc123",
  "status": "running"
}

Check Execution Status

curl https://your-refly-instance.com/api/v1/executions/{execution_id} \
  -H "Authorization: Bearer YOUR_API_KEY"

📖 Full API Documentation: API Reference

Use Case 2: Webhook for Lark (Feishu)

Goal: Trigger your workflow when someone sends a message in Lark

Prerequisites

A Lark workspace with admin access
A workflow created in Refly

Setup Steps

In Refly:
- Open your workflow
- Click "Settings" → "Triggers"
- Enable "Webhook Trigger"
- Copy the Webhook URL
In Lark/Feishu:
- Go to api.feishu.com/apps
- Create a "Custom App"
- Navigate to "Event Subscriptions"
- Paste the Refly Webhook URL into "Request URL"
- Click "Add Event" and select "Receive Message"
- Go to "Version Management" and publish the app
Test:
- In Feishu, find your bot in the search bar and send a message (e.g., analyze report.pdf)
- Your workflow executes and returns results via the webhook

⚠️ Note: Detailed Lark/Feishu integration guide coming soon. For now, see API Reference for webhook configuration.

Use Case 3: Skills for Claude Code

Goal: Publish your Refly workflows as Claude Code skills

Quick Start

Install Refly CLI

npm install -g @powerformer/refly-cli

Install a Skill

# Via Refly CLI
refly skill install <skill-id>

#Via npx
npx skills add refly-ai/<skill-name>

Publish a Skill

refly skill publish <skill-id>

The skill is now available in Claude Code, Cursor, and MCP-powered workflows. Agent can invoke your workflow as a tool!

📖 Documentation: Refly Skills

Use Case 4: Build Clawdbot

📖 Tutorial: Build Clawdbot Tutorial

Community & Support

🌟 Star us on GitHub: It helps us keep building!
💬 Discord: Join our community
🐦 Twitter: Follow us for updates
📖 Documentation: Full guides and tutorials
🐛 Issues: Report bugs or request features

Join Us

Join our community to get help, share your experience, and connect with other Refly users: Refly Community

Contributing

For those who'd like to contribute code, see our Contribution Guide. At the same time, please consider supporting Refly by sharing it on social media and at events and conferences.

We are looking for contributors to help translate Refly into languages other than Mandarin or English. If you are interested in helping, please see the Contribution Guide for more information.

Star History

License

This repository is licensed under the ReflyAI Open Source License, which is essentially the Apache 2.0 License with some additional restrictions.

README_CN.md ↗抓取于 2026/10/24 00:49:26

img_v3_02uh_3e01e906-f84a-4cd8-8b7a-b7274ae8e89g

Refly — 首个基于 Vibe Workflow 的开源 Agent Skills 构建器

English · 中文

可作为 Lovable 的 API · Lark/飞书的 Webhook · Claude Code 的 Skills

Skills 不是提示词，而是持久化的基础设施

Refly 是首个用于构建稳定、原子化、版本化 Agent Skills 的开源平台。Skills 是确定性的 Agent 能力——可在工作流、团队和运行时之间复用

Refly Skills

Refly Skills 是 Refly 官方可执行技能仓库

⚡ 即开即用：一键在 Refly 中运行技能
🧩 可复用基础设施：版本化 Skills，而不是一次性提示词
🔌 随处交付：导出到 Claude Code 或部署为 API
🌍 社区共建：导入、Fork 并发布你自己的技能

查看仓库：Refly技能仓库

TL;DR：Refly 将您的企业 SOP 编译为可执行的 Agent Skills；3 分钟构建完成，立即部署。

快速开始

部署 Refly

📘 自部署指南
(推荐给开发者) 使用 Docker 在你自己的服务器上部署 Refly 的分步指南。
🔌 API 参考
将 Refly 集成到你应用中的完整 API 文档。

[!TIP] 想快速体验不部署？直接打开在线版：立即尝试 接下来做什么？

部署完成后，根据你的使用场景选择路径：

我想要…	从这里开始	时间
🔧 构建第一个工作流	创建工作流	5 分钟
🔌 通过 API 调用工作流	API 集成	10 分钟
💬 连接到 Lark	Webhook 设置	15 分钟
🤖 导出到 Claude Code	导出技能	15 分钟
🦞 构建 ClawdBot	构建 ClawdBot	20 分钟

创建你的第一个工作流

[!NOTE] 本节假设你已完成自部署，并且可以通过 http://localhost:5700 访问 Refly

第一步：注册并登录

在浏览器中打开 http://localhost:5700
使用你的邮箱和密码注册
配置你的第一个模型提供方：
- 点击右上角账号图标 → Settings
- 添加一个 Provider（如 OpenAI、Anthropic）
- 添加你的第一个对话模型
- 将其设置为默认

📖 含截图的详细配置说明：自部署指南

第二步：创建工作流

在首页点击 “New Workflow”
选择一个模板或从零开始：
- Blank Canvas：使用可视化节点构建
- Vibe Mode：用自然语言描述你的工作流

示例 —— 产品调研工作流：

1. 添加 “Web Search” 节点 —— 搜索产品信息
2. 添加 “LLM” 节点 —— 分析搜索结果
3. 添加 “Output” 节点 —— 格式化报告
4. 连接各节点
5. 点击 “Save”

[!TIP] 想最快跑通流程，可以先用Vibe Mode，再从模板迭代完善。

第三步：测试你的工作流

点击“Run”按钮
输入测试内容（例如：产品 URL）
实时查看执行结果
如果出现失败，查看日志排查问题

使用场景

使用场景 1：API 集成

目标：通过 REST API 从你的应用中调用工作流

获取你的 API 凭证

前往Settings → API Keys
点击“Generate New Key”
复制你的 API Key（请妥善保管！）

发起你的第一次 API 调用

curl -X POST https://your-refly-instance.com/api/v1/workflows/{WORKFLOW_ID}/execute \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "product_url": "https://example.com/product"
    }
  }'

响应:

{
  "execution_id": "exec_abc123",
  "status": "running"
}

查询执行状态

curl https://your-refly-instance.com/api/v1/executions/{execution_id} \
  -H "Authorization: Bearer YOUR_API_KEY"

📖 完整API文档: API文档

使用场景 2：Lark Webhook

目标：当有人在 Lark 中发送消息时触发你的工作流

前置条件

拥有管理员权限的 Lark 工作区
已在 Refly 中创建工作流

配置步骤

在 Refly 中：
- 打开你的工作流
- 点击“Settings” → “Triggers”
- 启用“Webhook Trigger”
- 复制 Webhook URL
在飞书 / Lark 中：
- 前往 api.feishu.com/apps
- 创建一个“自定义应用”
- 进入“事件订阅（Event Subscriptions）”
- 将 Refly 的 Webhook URL 粘贴到“请求地址（Request URL）”
- 点击“添加事件（Add Event）”并选择“接收消息（Receive Message）”
- 前往“版本管理（Version Management）”并发布应用
测试：
- 在飞书中，通过搜索找到你的机器人并发送消息（例如：analyze report.pdf）
- 工作流将被触发，并通过 Webhook 返回执行结果

⚠️ 注意：详细的 Slack / 飞书集成指南即将推出。目前可参考 API 参考进行 Webhook 相关配置。

使用场景 3：Claude Code 技能

目标：将你的 Refly 工作流导出为 Claude Code Skills

快速开始

安装 CLI

npm install -g @powerformer/refly-cli

安装 Skill

# Via Refly CLI
refly skill install <skill-id>

# Via npx
npx skills add refly-ai/<skill-name>

发布Skill

refly skill publish <skill-id>

该技能已全面支持 Claude Code、Cursor 与 MCP 生态工作流，可作为标准化工具被 Agent 直接调用，实现生产级自动执行!

📖 Skills文档: Refly Skills

使用场景 4：构建 ClawdBot

📖 使用教程：ClawdBot教程

为什么选择 Refly？

大多数 AI Agent 在生产环境中失败，是因为它们依赖"Vibe Coding" 的脚本和脆弱的黑盒逻辑。随着生态系统向 Claude Code、AutoGen 和 MCP 等智能体框架发展，瓶颈不再是 LLM 的能力——而是缺乏标准化、可靠的操作能力。

Refly 连接原始 API 和智能 Agent 之间的鸿沟。我们允许您将混乱的业务逻辑编码为结构化、版本控制的 Agent Skills，任何 Agent 都可以 100% 可靠地调用。

停止硬编码工具。在 Refly 的可视化 IDE 中一次性构建模块化Skills，并将其部署为 MCP 服务器、标准 API 或可移植的 SDK，供任何 Agent 框架使用。

核心基础设施

Refly 是首个用于创建生产就绪、确定性Skills的开源 Agent Skills 构建器——不仅仅是一次性工作流。

通过将自然语言意图转化为受治理的能力层，Refly 使团队能够在几分钟内交付可靠的智能体基础设施。

使用 Vibe 构建（Copilot 引导的构建器）

用自然语言描述您的业务逻辑，Refly 的模型原生 DSL 将您的意图编译为高性能 Skills。

意图驱动构建：描述一次工作，Refly 将意图转化为确定性、可复用、可组合的 Skills。
大规模高效：我们精简的 DSL 针对 LLM 优化，确保快速执行，与传统工具相比大幅降低 token 成本。
3 分钟部署：3分钟内将静态企业 SOP 快速转化为可上线运行的 Agent Skill。

可控执行（可干预运行时）

通过专为确定性可靠性和无限连接而设计的有状态运行时，打破 AI 执行的"黑盒"。

可干预运行时执行：支持在任务执行过程中实时暂停、审计与重定向 Agent 决策逻辑，确保全流程符合企业级操作规范与合规要求。
确定性执行保障：通过强约束业务规则显著降低幻觉风险，并提供完善的失败恢复与容错机制，保障关键流程稳定可靠运行。

交付生产（统一 Agent 堆栈）

将 MCP 集成、工具、模型和可复用 Skills 统一到单个执行层，可交付到任何平台。

通用交付：支持导出为 Lovable 的 API 接口、Slack/Lark（飞书）Webhooks，或直接集成为 Claude Code 和 Cursor 的原生工具。
定时运行：在全托管执行环境中，工作流可完成持续、可靠地按时运行。

作为资产治理（Skills 注册表）

将脆弱的脚本和手动剧本转化为组织范围内受治理的共享基础设施。

中央 Skills 注册表：安全管理、版本控制和共享 Agent 能力作为可复用的企业资产。
团队工作空间协作：在具有原生版本控制和审计日志的集中环境中共同构建和共享 SOP 剧本。

生态系统

Refly 旨在成为您现有企业工具链与下一代智能体运行时之间的通用桥梁。

工具与协议（输入）

零摩擦地将您自己的数据和逻辑引入 Refly。

3,000+ 原生工具：与 Stripe、Slack、Salesforce、GitHub 等工业级 API 无缝集成完整的支持模型和工具提供商列表可在此处找到：provider-catalog.json

img_v3_02uh_37c05264-a390-4ceb-9a96-efce1a61d1eg

MCP 支持：与任何模型上下文协议服务器完全原生兼容，以扩展超越标准 API 的 Agent 能力
私有 Skills 连接器：通过 Refly 安全接入企业数据库、脚本与内部系统

Agent 运行时与平台（输出）

将您确定的 Skills 导出到任何工作所需要的环境和平台

img_v3_02uh_2599ba2c-18f0-445d-b95c-aa7da6e41aag

AI 编码工具：原生导出到 Claude Code 和 Cursor，允许 Agent 使用您的版本化 Skills 作为标准化工具
应用构建器：通过有状态、经过认证的 API 为 Lovable 或自定义前端应用提供逻辑支持
自动化中心：部署为智能 webhook，从 Slack 或 Microsoft Teams 触发复杂的 SOP
Agent 框架：直接兼容 AutoGen、Manus 和自定义 LangChain/Python 技术栈

为什么团队选择 Refly

对于构建者：从 Vibe 到生产

当今大多数 Agent 工具分为两类：

工作流构建器（n8n、Dify）：非常适合编排，但工作流脆弱，仅触发"黑盒"，难以复用。
Agent 框架（LangChain）：强大的原语，但需要大量工程、手动样板代码和高维护成本才能保持运行。

Refly 消除了手动配置的摩擦，为您提供从"vibe"到可用 Agent 工具的最快路径。通过使用我们的精简 DSL，您可以获得 GUI 的速度和代码的精确性。

维度	传统自动化 _{(n8n, Dify)}	代码优先 SDK _(LangChain)	Refly Skills
交互深度	仅触发 _黑盒	程序化 _代码更改	可干预运行时 _{运行中引导逻辑}
构建方式	手动 API 接线和 JSON	手动 Python/TS 样板	Copilot 引导 _{描述意图 → 生成Skills}
恢复机制	失败 = 从头重启	调试 → 重新部署 → 重新运行	热修复 _{执行期间修复工作流}
可移植性	难以跨环境复用	框架特定	随处导出 _{到 Claude Code、Cursor、Manus}
部署方式	有限的函数工具	自定义微服务	生产就绪 _{有状态、经过验证的 API}

对于企业：可扩展的Skills治理

n8n 等工作流工具非常适合基本连接，LangChain 等框架提供强大的原语——但都无法提供企业 Agent 基础设施所需的受治理、生产就绪的能力层。

Refly 充当 Agent Skills 构建器，提供在整个组织中部署 AI 所需的治理和可靠性基础设施。

企业需求	传统工具 _{(工作流优先)}	SDK _{(代码优先)}	Refly (Skills OS)
治理与复用	模板被复制并 _{针对每个实例重新配置}	无原生注册表 _{用于共享逻辑}	中央Skills 注册表 _{版本化、可共享的能力资产}
运营可靠性	基于触发 _有限恢复	需要自定义处理	有状态运行时 _{具有验证 + 故障恢复}
SOP 执行	工作流在 _{副本间漂移}	依赖手动 _工程纪律	SOP 级确定性Skills _可控执行
部署方式	实例绑定工作流	代码由每个 _{团队手动维护}	本地优先、可私有部署 _{开源基础设施}
总拥有成本 (TCO)	开销随 _{工作流复杂性增长}	高工程 _维护成本	精简 DSL _{降低 token 开销}

贡献

对于希望贡献代码的人，请参阅我们的贡献指南。同时，请考虑通过在社交媒体、活动和会议上分享 Refly 来支持我们。

我们正在寻找贡献者帮助将 Refly 翻译成普通话或英语以外的语言。如果您有兴趣提供帮助，请参阅贡献指南了解更多信息。

社区

与 Refly 社区建立联系：

🌟 在 GitHub 上给我们加星：这有助于我们持续构建！
💬 Discord: 加入我们的社区
🐦 Twitter: 关注我们的Twitter
📖 文档: 完整指南和教程
🐛 问题: 报告 Bug 或提出功能需求

加入我们

加入社区获取支持、分享经验并与其他 Refly 用户交流： https://docs.refly.ai/community/contact-us

Star History

许可证

本仓库采用 ReflyAI 开源许可证，本质上是带有一些额外限制的 Apache 2.0 许可证。

热度有据可查

累计 Star: 7,543
近 7 天净增: 观察中

尚无约 7 天前的观测，不估算周净增。已有 7 天观测。

统计口径 ↗

项目档案

主要语言TypeScript

许可证未识别，请查阅仓库

Fork726

最近推送2026/10/22 00:32:27

本站发现2026/10/24 00:45:46

数据更新2026/10/29 13:59:35

收录与分类依据

仓库简介：The first open-source agent skills builder. Define skills by vibe workflow, run on Claude Code, Cursor, Codex & more. Build Clawdbot 🦞· APIs for Lovable · Bots for Slack & Lark/Feishu · Skills are infrastructure, not prompts.

GitHub Topics：agent, agent-skills, automation, claude, clawdbot, codex, cursor, lark-bot, lovable, n8n-alternative, skills, skills-builder

README 依据：已核实仓库中的 SKILL.md 文件或明确的技能安装命令

发现来源：分类检索 · 办公自动化