What makes AutoCraft notable?

1K downloads. Trust evidence available

How should AutoCraft be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

AutoCraft

AI-powered project execution platform. Non-technical product managers can drive complex software projects with 3-6x efficiency. 10-day case study: education platform with 71 tasks (99% success). One-click install. AI驱动的项目执行平台。不懂代码也能驱动复杂软件开发，效率提升3-6倍。10天案例：71个任务，99%成功率。一键安装，自动部署。 Skill: AutoCraft Owner: robin-chen2025 Summary: AI-powered project execution platform. Non-technical product managers can drive complex software projects with 3-6x efficiency. 10-day case study: education platform with 71 tasks (99% success). One-click install. AI驱动的项目执行平台。不懂代码也能驱动复杂软件开发，效率提升3-6倍。10天案例：71个任务，99%成功率。一键安装，自动部署。 Tags: latest:2.1.0 Version history: v2.1.0 | 2026-05-20T02:32:11.115Z | user Complete skill

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

Updated

Oct 11, 2026

Version

2.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 2.1.0release · observed May 20, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17egxbv37nwvez7zjabx4h56s870q2r:autocraft

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-robin-chen2025-autocraft/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

150,348 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

references/ac-agent-guide/SKILL.md

---
name: ac-agent-guide
description: AutoCraft子代理综合指引入口。定义角色识别、任务类型、共享规范。按任务类型和角色分别引用子文档。
---

# AutoCraft 子代理指引

**版本:** v2.0
**更新:** 2026-05-10

---

## 角色识别

根据你的Agent ID确定角色:

| Agent ID | 角色 | 模型 | 职责 |
|----------|------|------|------|
| ac-glm5 | **执行子代理** | GLM-5 | 生成代码/文档/测试 |
| ac-validator | **验证子代理** | DeepSeek-V3.2 | 验证产出物质量 |

> 如果不确定角色,看任务提示词中是否包含"验证"关键词。有→验证子代理,无→执行子代理。

---

## 任务类型总览

| 任务类型 | 标识 | 职责 | 产出 |
|---------|------|------|------|
| **程序代码** | BUILD-CODE | 按设计文档编写可运行代码 | 源码文件 + JSON结果 |
| **测试代码** | BUILD-TEST | 只写测试代码，不运行，不改程序代码 | 测试文件 + JSON结果 |
| **测试执行** | TEST-RUN | 运行测试 + 深入分析失败根因 | 测试分析报告 + JSON结果 |
| **环境搭建** | BUILD-ENV | 数据库迁移、依赖安装等 | 执行日志 + JSON结果 |
| **文档生成** | DOC | 开发报告、测试报告 | Markdown文件 + JSON结果 |
| **设计文档** | DESIGN | PRD/功能设计/API设计/数据库设计 | Markdown文件 + JSON结果 |

---

## 测试闭环机制

```
BUILD-TEST（只写测试，不运行，不改程序代码）→ BUILD-CODE（写程序代码 + pytest验证）→ TEST-RUN（独立运行 + 深入分析根因）→
  ├─ 全部通过 → 完成
  └─ 有失败 → TEST-RUN分析根因并记录issues →
       ├─ test_issue → 项目经理决定是否创建新BUILD-TEST修复
       ├─ code_issue → 项目经理决定是否创建新BUILD-CODE修复
       └─ env_issue → 项目经理决定是否修复环境
```

⚠️ **核心原则：测试是发现bug的手段，不是需要通过的目标。全绿不代表质量好，发现问题才是价值。**

---

## 子文档索引

根据你的角色和任务类型，读取对应的子文档：

| 文档 | 路径 | 适用场景 |
|------|------|---------|
| **执行子代理规范** | `references/ac-agent-guide/executor-guide.md` | ac-glm5角色，所有BUILD-*任务 |
| **测试代码规范** | `references/ac-agent-guide/build-test-guide.md` | BUILD-TEST任务 |
| **测试执行规范** | `references/ac-agent-guide/test-run-guide.md` | TEST-RUN任务 |
| **验证子代理规范** | `references/ac-agent-guide/validator-guide.md` | ac-validator角色 |
| **BUILD-TEST验证规范** | `references/ac-agent-guide/validator-buildtest.md` | 验证BUILD-TEST任务时 |
| **共享规范** | `references/ac-agent-guide/shared-rules.md` | 所有角色通用 |

**读取顺序**：
1. 先读本文件（角色识别 + 任务类型）
2. 根据角色读取对应子文档
3. 执行任务时按子文档规范操作

---

## 通用执行流程

```
1. 读取任务信息(忽略之前的会话上下文)
2. 识别任务类型 → 选择对应行为模式
3. 读取输入文件(设计文档、规范文件等)
4. 执行任务 → 产出物写入项目目录(按任务指定的 deliverables 路径)
5. 写JSON结果文件到 /tmp/autocraft_output/{task_id}_execution_result.json
6. 结束
```

---

## 执行铁律

| 规则 | 说明 |
|------|------|
| **必须写JSON结果** | 程序通过读取JSON获取结果 |
| **不要调webhook** | 结果由程序自动读取 |
| **一次性执行** | 完成后立即结束 |
| **忽略之前上下文** | 只关注当前任务 |
| **产出物必须真实存在** | 不写不存在的文件路径 |
| **代码必须可运行** | 不提交语法错误的代码 |

references/task-creator/SKILL.md

---
name: task-creator
description: AutoCraft任务单创建标准流程。指导主代理正确创建任务单并导入AutoCraft系统，包括数据格式规范、必填字段、workflow_type映射、输入文件配置等。触发场景：需要为AutoCraft执行引擎创建任务单时。
---

# AutoCraft 任务单创建标准流程

**版本：** v1.0  
**更新：** 2026-05-12

---

## 创建方式

### 方式1：API创建（推荐）

通过 `/api/v2/tasks/` API 批量创建任务单：

```bash
curl -X POST http://localhost:9001/api/v2/tasks/ \
  -H "Content-Type: application/json" \
  -d '[{
    "task_no": "M02-BE-001",
    "task_name": "创建知识图谱API端点",
    "task_type": "BUILD",
    "plan_id": "plan_xxx",
    "status": "pending",
    "input_data": {
      "workflow_type": "BUILD-CODE",
      "project_path": "/data/projects/deeptutor-lite",
      "input_files": [
        "/data/projects/deeptutor-lite/docs/design/04-技术方案-DeepTutor-Lite.md"
      ],
      "requirements": "创建知识图谱管理API",
      "expected_output": "路由文件，包含所有API端点",
      "expected_output_files": [
        "/data/projects/deeptutor-lite/backend/api/routers/knowledge_graph.py"
      ]
    }
  }]'
```

**返回值**：
```json
{
  "status": "success",
  "created_count": 1,
  "task_ids": [540],
  "errors": null
}
```

**支持批量**：数组中放入多个任务对象即可批量创建。

**错误处理**：如果某个任务创建失败（如task_no重复），会在errors中返回错误信息，其他任务仍正常创建。

### 方式2：直接写数据库（仅调试用）

⚠️ 不推荐日常使用，仅当API不可用时作为备选：

```python
from database import SessionLocal
from models.task_v2 import TaskV2
import json

db = SessionLocal()
task = TaskV2(
    plan_id='<plan_id>',
    task_no='<task_no>',
    task_name='<task_name>',
    task_type='<task_type>',
    status='pending',
    input_data=json.dumps({...}, ensure_ascii=False)  # ⚠️ 必须是JSON字符串
)
db.add(task)
db.commit()
db.refresh(task)
print(f'任务创建成功: id={task.id}')
db.close()
```

---

## 数据库字段规范

| 字段 | 类型 | 数据库必填 | 业务必填 | 说明 |
|------|------|-----------|---------|------|
| `task_no` | VARCHAR(20) | ✅ | ✅ | 任务编号，plan_id内唯一 |
| `task_name` | VARCHAR(200) | ✅ | ✅ | 任务名称 |
| `task_type` | VARCHAR(50) | ⬜ | ✅ | 任务类型，决定子代理读哪个执行指引 |
| `plan_id` | VARCHAR(50) | ⬜ | ✅ | 所属工作计划ID，缺失则前端找不到任务 |
| `status` | VARCHAR(30) | ⬜ | ✅ | 默认"pending" |
| `input_data` | TEXT | ⬜ | ✅ | JSON字符串，核心任务数据，缺失则无法执行 |

⚠️ `input_data` 字段必须是 **JSON字符串**（`json.dumps()`），不是dict对象。

---

## input_data 标准格式

```json
{
  "workflow_type": "BUILD-CODE",
  "project_path": "/data/projects/{project}",
  "input_files": [
    "/data/projects/{project}/docs/design/04-技术方案-{project}.md",
    "/data/projects/{project}/docs/design/07-API设计-{project}.md"
  ],
  "requirements": "详细的任务要求描述，必须具体、可执行",
  "expected_output": "详细的预期输出描述，必须可验证",
  "expected_output_files": [
    "/data/projects/{project}/backend/services/xxx.py"
  ],
  "deliverables": ["产出物描述1", "产出物描述2"],
  "source_file": "/data/projects/{project}/docs/design/04-技术方案-{project}.md"
}
```

### 字段说明

| 字段 | 必填 | 类型 | 说明 |
|------|------|------|------|
| `workflow_type` | ✅ | string | 工作流类型，决定子代理行为（见映射表） |
| `project_path` | ✅ | string | 项目根目录，**绝对路径** |
| `input_files` | ✅ | string[] | 输入文件路径列表，**绝对路径**，至少包含1个设计文档 |
| `requirements` | ✅ | string | 任务要求，必须详细具体 |
| `expected_output` | ✅ | string | 预期输出描述，必须可验证 |
| `exp

SKILL.md

---
name: autocraft
license: MIT
description: AutoCraft AI project execution platform. Empower non-technical product managers to drive complex software development with 3-6x efficiency. Real case: Built DeepTutor-Lite education platform in 10 days (71 tasks, 99% success rate). Innovations: 4-level project management, responsibility separation model, intelligent verification, task locking.
metadata: { "openclaw": { "requires": { "bins": ["python3", "npm", "git"] } } }
---

# AutoCraft - AI-Powered Project Execution Platform

> **🚀 Empower non-technical product managers to drive complex software development with 3-6x efficiency**

**Version:** v2.1.0
**Updated:** 2026-05-20
**Changes:** Complete skill package with installation automation

---

## 📦 System Installation

### One-Click Install & Deploy

```bash
# 1. Install skill from ClawHub
clawhub install autocraft

# 2. Navigate to autocraft directory
cd autocraft

# 3. Run one-click installation script
bash install.sh

# 4. Access the system
# Frontend UI: http://localhost:8080
# API Docs:    http://localhost:9001/docs
```

**install.sh automatically:**
- Downloads complete system code from GitHub/Gitee (~5.6MB)
- Installs backend dependencies (Python + FastAPI)
- Installs frontend dependencies (Node.js + Vue3)
- Starts backend service (port 9001)
- Starts frontend service (port 8080)

### Manual Installation (Optional)

```bash
# Clone complete system code
git clone https://github.com/Robin-Chen2025/autocraft-opensource.git
cd autocraft-opensource

# Backend setup
cd backend
pip install -r requirements.txt
python3 -m uvicorn main:app --host 0.0.0.0 --port 9001

# Frontend setup (new terminal)
cd ..
npm install
npm run dev
```

---

## 📊 Real Case: Complete Education Platform in 10 Days

```
📈 Project Scale:
   Plans: 19
   Tasks: 71
   Success: 70 (99% success rate)

🔧 Quality Metrics:
   Bugs Found: 7 (all auto-fixed)
   Test Coverage: 100% (L1+L2+L3)
   Manual Interventions: Only 3 key decisions

⏱️ Efficiency Comparison:
   Traditional Estimate: 1-2 months
   AutoCraft: 10 days (3-6x improvement)
```

---

## 🎯 Your Role

**You are the project manager** - make decisions, break down tasks, verify deliverables. Don't write code.

| You Do | You Don't |
|--------|-----------|
| Clarify requirements, choose solutions | Write specific code |
| Review and approve documents | Directly operate database |
| Break down and schedule tasks | Trust agent's "completed" |
| Verify deliverables | Skip verification steps |

---

## Two-Phase Model

```
Phase 1: Design Phase (Without AutoCraft)
    │
    │  PRD → Feature Design → Tech Solution → API/DB/UI Design
    │  → Test Plan → Development Plan (Overview + Work Plans)
    │  → Overall Verification
    │
    ▼  Development Plan Finalized
Phase 2: Execution Phase (Enter AutoCraft)
    │
    │  Break down task tickets → Import via API
    │  → Execution engine runs tasks (AI agents)
    │  → Auto verification → Manager approval → Status cascade
    │

scripts/architecture-check/README.md

# 架构检查工具

## 概述

架构检查工具用于检查代码的架构合理性，确保代码符合以下设计原则：
1. **单一职责原则（SRP）** - 每个文件只负责一个功能
2. **关注点分离** - 代码分层合理，职责清晰
3. **功能边界分明** - 不同功能之间耦合度低

## 安装与使用

### 直接运行
```bash
# 基本用法
python3 architecture_check.py --path /path/to/code

# 生成详细报告
python3 architecture_check.py --path /path/to/code --report architecture_report.json

# 显示详细输出
python3 architecture_check.py --path /path/to/code --verbose
```

### 集成到验证流程

在验证子代理中集成架构检查：

```python
import subprocess
import json

def check_architecture_quality(code_path: str) -> Dict:
    """检查架构质量"""
    try:
        result = subprocess.run(
            ['python3', 'architecture_check.py', '--path', code_path, '--report', '/tmp/architecture_report.json'],
            capture_output=True,
            text=True,
            timeout=60
        )
        
        if result.returncode == 0:
            # 读取报告
            with open('/tmp/architecture_report.json', 'r') as f:
                report = json.load(f)
            
            # 检查是否有高危问题
            if report['summary']['high_severity'] > 0:
                return {
                    "status": "FAIL",
                    "issues": ["发现架构高危问题，违反SRP原则"],
                    "report": report
                }
            else:
                return {
                    "status": "PASS",
                    "report": report
                }
        else:
            return {
                "status": "FAIL",
                "issues": ["架构检查失败"],
                "error": result.stderr
            }
    except Exception as e:
        return {
            "status": "ERROR",
            "issues": [f"架构检查异常：{str(e)}"]
        }
```

## 检查维度

### 1. 文件职责单一性（SRP）
- **检查项**：文件是否包含多个不相关功能
- **判定标准**：文件包含2个以上不相关功能 → FAIL
- **示例**：
  - ✅ `user_service.py` - 只包含用户相关的业务逻辑
  - ❌ `user_router_and_service.py` - 包含路由和服务逻辑

### 2. 代码结构合理性
- **检查项**：代码分层是否合理
- **判定标准**：路由文件中包含业务逻辑 → FAIL
- **示例**：
  - ✅ `user_router.py` - 只处理HTTP请求
  - ❌ `user_router.py` - 包含数据库查询逻辑

### 3. 功能边界分明性
- **检查项**：功能之间耦合度是否过高
- **判定标准**：导入过多外部模块（>15个） → WARNING
- **示例**：
  - ✅ `email_service.py` - 只依赖email相关模块
  - ❌ `user_service.py` - 依赖10+个不相关模块

## 报告格式

### JSON报告
```json
{
  "srp_checks": [
    {
      "file": "backend/api/routers/data_processor.py",
      "issues": [
        {
          "type": "SRP_VIOLATION",
          "description": "文件包含多个不相关功能：数据上传、查询、存储",
          "severity": "HIGH"
        }
      ],
      "function_count": 15,
      "class_count": 3
    }
  ],
  "structure_checks": [...],
  "boundary_checks": [...],
  "summary": {
    "total_files": 25,
    "issues_found": 3,
    "high_severity": 1,
    "medium_severity": 1,
    "low_severity": 1
  }
}
```

### 文本报告
```
==================================================
架构检查报告
==================================================

📊 检查摘要
   检查文件数: 25
   发现问题数: 3
   高危问题: 1
   中危问题: 1
   低危问题: 1

🔍 SRP原则检查（文件职责单一性）
   ❌ 发现 1 个SRP违规：
      • backend/api/routers/data_processor.py: 文件包含多个不相关功能

🏗️  代码结构检查
   ✅ 代码结构良好

💡 重构建议
   1. 优先处理 1 个

_meta.json

{
  "ownerId": "kn74zvy0vhvcj4bm4kmmxzy29d82csnv",
  "slug": "autocraft",
  "version": "2.1.0",
  "publishedAt": 1779244331115
}

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.