经 AI Skill Hub 精选评估,AI工作流引擎 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
基于技能的AI工作流引擎,支持规划、TDD、工作树编排
AI工作流引擎 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
基于技能的AI工作流引擎,支持规划、TDD、工作树编排
AI工作流引擎 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g arcforge # 方式二:npx 直接运行(无需安装) npx arcforge --help # 方式三:项目依赖安装 npm install arcforge # 方式四:从源码运行 git clone https://github.com/GregoryHo/arcforge cd arcforge npm install npm start
# 命令行使用
arcforge --help
# 基本用法
arcforge [options] <input>
# Node.js 代码中使用
const arcforge = require('arcforge');
const result = await arcforge.run(options);
console.log(result);
# arcforge 配置说明 # 查看配置选项 arcforge --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export ARCFORGE_CONFIG="/path/to/config.yml"
arcforge is a minimal, composable skill toolkit for Claude Code, Codex, Gemini CLI, and OpenCode. It gives agents lightweight routing, structured SDD artifacts, and eval-backed quality gates without turning every task into a mandatory workflow.
All 33 skills, each listed once. Workflow skills hand off sequentially, discipline skills fire as quality gates when their condition is present, and meta skills are invoked directly (see arc-using for routing).
Note: Installation differs by platform. Claude Code has a built-in plugin system. Codex and OpenCode require manual setup.
Check that commands appear:
/help
```
npm install
cd hooks && npm install && cd ..
pip install pytest pyyaml # Required for test:skills
These are the most frequently used commands:
| Command | Purpose | When to Use |
|---|---|---|
/arcforge:arc-using | Routing help + skill index | When unsure which skill or workflow applies |
/arcforge:arc-brainstorming | Design exploration | When starting new work or clarifying requirements |
/arcforge:arc-writing-tasks | Break down into tasks | When you have a clear spec and need executable steps |
/arcforge:arc-executing-tasks | Run task list | When tasks are ready and you want to implement |
/arcforge:arc-journaling | Session journaling | At end of session to capture reflections |
/arcforge:arc-reflecting | Analyze patterns | After 5+ journal entries to summarize learnings |
The CLI manages the DAG that arc-planning produces. You typically do not run these directly — skills invoke them. For manual use or debugging, the commands are:
The examples below use the bare arcforge <cmd> shorthand. In a plugin session, invoke the CLI as node "${ARCFORGE_ROOT}/scripts/cli.js" <cmd> — the SessionStart hook sets ARCFORGE_ROOT to the installed plugin directory. (The package is not published to npm; the bare shorthand only works from a local checkout via node scripts/cli.js.)
```bash
These guides live in the repo under docs/guide/:
| Guide | Link |
|---|---|
| CLI Invocation Convention | [docs/guide/cli-invocation.md](docs/guide/cli-invocation.md) |
| Eval System | [docs/guide/eval-system.md](docs/guide/eval-system.md) |
| Composable Skill Eval Coverage | [docs/guide/composable-skill-eval-coverage.md](docs/guide/composable-skill-eval-coverage.md) |
| Hooks System | [docs/guide/hooks-system.md](docs/guide/hooks-system.md) |
| Worktree Workflow | [docs/guide/worktree-workflow.md](docs/guide/worktree-workflow.md) |
| Skills Reference | [docs/guide/skills-reference.md](docs/guide/skills-reference.md) |
| Learning Dashboard | [docs/guide/learning-dashboard.md](docs/guide/learning-dashboard.md) |
Register the marketplace:
/plugin marketplace add GregoryHo/arcforge
Install the plugin:
/plugin install arcforge@arcforge-dev
.arcforge-epicarcforge status
To develop arcforge itself with live plugin loading, see the Plugin Development section in CONTRIBUTING.md. Quick version: npm run dev starts a Claude session that loads the plugin directly from your local checkout.
高质量的AI工作流引擎,支持多种工作流模式
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。
AI Skill Hub 点评:AI工作流引擎 的核心功能完整,质量优秀。对于自动化工程师和运维人员来说,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 | arcforge |
| 原始描述 | 开源AI工作流:Skill-based workflow engine for AI coding agents: planning, TDD, worktree orches。⭐6 · JavaScript |
| Topics | AI工作流JavaScript |
| GitHub | https://github.com/GregoryHo/arcforge |
| License | MIT |
| 语言 | JavaScript |
收录时间:2026-06-17 · 更新时间:2026-06-17 · 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