# intent-flow

> intent-flow — thechengxi-intent-flow. Use this tool when you need to streamline your development workflow with AI assistance, solving problems of manual handovers and inefficiencies in the development process. IntentFlow provides a comment-driven framework that automates workflows across four stages: demand, design, execution, and reporting. It accepts inputs via @intent annotations and outputs automated state machine transitions, available through pi extensions, MCP Server, and CLI interfaces.

Canonical page: https://skillsregistry.net/skills/thechengxi-intent-flow  
JSON: https://api.skillsregistry.net/v1/skills/thechengxi-intent-flow

## Description

IntentFlow — Comment-Driven Development Framework 注释驱动开发框架：以 @intent 注释为契约的 AI 辅助开发工作流（需求/设计/执行/报告四阶段 + 状态机自动流转），提供 pi 扩展、MCP Server、CLI 三种形态

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/TheChengXi/intent-flow)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "thechengxi-intent-flow"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/thechengxi-intent-flow` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/thechengxi-intent-flow/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt