ClawHub

AutoCraft

Automation

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。

Install

openclaw skills install autocraft

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

# 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)

# 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 DoYou Don't
Clarify requirements, choose solutionsWrite specific code
Review and approve documentsDirectly operate database
Break down and schedule tasksTrust agent's "completed"
Verify deliverablesSkip 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
    │
    ▼  Project Complete

Phase 1: Design Phase

Design Document System

Follow references/design-specs/设计阶段文档规范-总纲.md.

Required Documents:

#DocumentCodeSpecChecklist
01PRDPRD01-PRD规范09-PRD审核
03System Feature DesignFUNC03-系统功能设计11-功能设计审核
04Tech SolutionTECH04-技术方案12-技术方案审核
07API DesignAPI07-API设计14-API设计审核
08Database DesignDB08-数据库设计15-数据库设计审核
18Overall VerificationVERIFY-18-整体性验证

Optional Documents:

#DocumentCodeSpecChecklist
00Requirements ListREQ00-需求清单See spec chapter 6
02Business FlowFLOW02-业务流程10-业务流程审核
05UI DesignUI05-UI设计13-UI设计审核
06Component SpecCOMP06-组件规范16-组件规范审核

Document Generation Flow

Use sub-agents to generate documents:

1. Prepare input materials (prior docs + spec files)
2. Sub-agent generates first version
3. Sub-agent reviews against checklist
4. Fix based on issues found
5. Re-review to confirm
6. Finalize (Boss approval)

Sub-agent Invocation:

Design phase uses multi-turn session mode:

# Create persistent session (supports multiple review-fix cycles)
openclaw agent --session-id explicit:doc_session_{project_name}_{timestamp} \
  --agent-id ac-glm5 \
  --model glm-5 \
  --message "Read the following spec files and input materials, generate {document_type} document..."

# Review in same session
openclaw agent --session-id explicit:doc_session_{project_name}_{timestamp} \
  --message "Review the generated document against checklist..."

# Fix in same session
openclaw agent --session-id explicit:doc_session_{project_name}_{timestamp} \
  --message "Fix the document based on review report..."

Key Requirements:

  • Design phase document generation uses multi-turn session mode
  • Sub-agent must read corresponding spec files and review checklists before generating
  • Immediately self-review after generation using checklist
  • Score ≥80 to submit for Boss review, <70 regenerate
  • Use GLM-5 model for design phase work

Test Plan

Generate according to references/design-specs/质量检测方案/:

DocumentPathPurpose
Test Plan Overview21-总纲生成规范Overall test strategy
BE-L2 Test Plan22-BE-L2规范Backend integration tests
FE-L2 Test Plan23-FE-L2规范Frontend integration tests
L3-E2E Test Plan24-L3-E2E规范End-to-end tests
L1 Test Plan30/31规范Unit tests

Development Plan

Generate according to references/design-specs/开发计划方案/:

Two-layer structure:

  • Development Plan Overview: Batch order, module dependencies, feature overview
  • Work Plan List: Task ticket structure for each work plan
DocumentSpecReview
Overview40-生成规范43-总览审核
Overview Details41-总览生成-
List42-清单生成44-清单审核
Overall-45-整体性审核

Phase 2: Execution Phase

Import to AutoCraft

After development plan is finalized, main agent breaks down task tickets and imports via API:

# 1. Create project profile
curl -X POST http://localhost:9001/api/profiles \
  -H "Content-Type: application/json" \
  -d '{"profile_id":"...", "profile_name":"...", ...}'

# 2. Create phases and workflows
curl -X POST http://localhost:9001/api/profiles/{id}/phases -d '...'
curl -X POST http://localhost:9001/api/profiles/{id}/workflows -d '...'

# 3. Create work plans
curl -X POST http://localhost:9001/plans -d '...'

# 4. Create task tickets one by one
curl -X POST http://localhost:9001/tasks -d '...'

Task Creation

⚠️ Follow references/task-creator/SKILL.md, including:

  • Standard input_data format and required fields
  • workflow_type to task_type mapping
  • input_files configuration guide
  • Batch creation example code
  • Common errors and checklists

Core Rules:

  1. All paths must be absolute paths
  2. project_path must point to correct project root
  3. input_files must contain at least 1 design document
  4. requirements must be detailed and specific
  5. expected_output_files must list all expected files
  6. input_data must be converted to JSON string via json.dumps()

Simple FlowTicket Execution

Invocation:

# 1. Submit execution request (async)
curl -X POST http://localhost:9001/api/v2/tasks/execute \
  -H "Content-Type: application/json" \
  -d '{
    "task_id": <task_id>,
    "model": "glm-5.1",
    "label": "Execute task XXX",
    "timeout": 1800
  }'

# 2. Query task status (polling)
curl -X GET "http://localhost:9001/api/v2/tasks/{task_id}/status"

# 3. Check execution result
# - Status "completed" or "verified" = success
# - Status "failed" or "verification_failed" = failure
# - execution_log and verification_log contain details

Task Status Flow:

pending → in_progress → completed → verifying → verified
                     ↓
                   failed → (can re-execute)
                                  ↓
                          verification_failed

Model Configuration:

PurposeModelAgent ID
ExecutionGLM-5.1ac-glm5
VerificationDeepSeek-V3.2-thinkingac-validator

Verification Dimensions (7)

DimensionCheckFAIL Condition
1. CompletenessDo output files existFiles don't exist
2. CorrectnessIs code syntax correctCompile/parse fails
3. FunctionalityDoes it meet requirementsCore features missing
4. StandardsDoes it follow code standardsSerious violations
5. TestabilityCan tests runTests can't execute
6. ArchitectureDoes it follow SRPViolates SRP
7. Design ComplianceDoes it match design docsDeviates from design

Approval Rules

  1. Don't trust agent's "completed" - must check output files
  2. Verification is automatic - PASS/FAIL per dimension, all PASS to pass
  3. Output path must match - check files are in deliverables locations
  4. Architecture check enforced - new dimension 6 "Architecture", SRP violation = FAIL
  5. Design compliance enforced - new dimension 7 "Design Compliance", check implementation matches design docs

AutoCraft System Info

ComponentAddressManagement
Unified Backendhttp://localhost:9001systemd: autocraft-backend
Frontend (View Window)http://localhost:8080systemd: autocraft-frontend
API Docshttp://localhost:9001/docsOpenAPI interactive docs

Service Management:

sudo systemctl restart autocraft-backend autocraft-frontend
sudo systemctl status autocraft-backend autocraft-frontend
curl http://localhost:9001/health  # Health check

Iron Rules

RuleDescription
Confirm with Boss before actionEvery key step (start project, generate docs, execute tasks, approve, etc.) must be explained to Boss and wait for confirmation before executing
Design phase multi-turn sessionDesign phase uses multi-turn session mode, same sub-agent (GLM-5) completes generate→review→fix cycle
Main agent doesn't write codeYou are project manager, sub-agents do the work
All operations via APINo direct database operations
Verify deliverablesDon't trust "completed" word
Git standardsNo reset --hard, push --force
Model isolationDesign phase: GLM-5, Execution phase: GLM-5 (execute) + DeepSeek-V3.2 (verify)
Session isolationExecution phase each task independent session, design phase multi-turn session
Design specs firstDocument generation must read spec files, don't write from memory
Paths must be absoluteAll file paths must be absolute, no relative paths
Project directory clearMust specify correct project_path, ensure files generated in correct location

Sub-Agent Guide

Comprehensive guide for ac-glm5 (execution agent) and ac-validator (verification agent):

  • ac-agent-guide: references/ac-agent-guide/SKILL.md
    • Role identification (auto-detect execution/verification by Agent ID)
    • Execution agent: 5 task types (BUILD-CODE/BUILD-TEST/BUILD-ENV/DOC/DESIGN)
    • Verification agent: 3 task types + PASS/FAIL judgment + verification dimensions
    • Auxiliary skill index: auto-select skill by tech stack
    • JSON result file format spec
    • Shared rules (file operations, output directory, common commands)

When sub-agent is invoked by AutoCraft execution engine, it should read this skill for role definition and behavior specs.

Architecture Check & Template Library

Architecture Check Tool

New verification dimension 6: Architecture, checks if code follows design principles:

DimensionCheck ItemsCriteria
ArchitectureFile responsibility single (SRP), code structure clear, functional boundaries distinctViolates SRP → FAIL

Architecture check script: scripts/architecture-check/architecture_check.py

  • Check file responsibility singularity (SRP principle)
  • Check code structure rationality (layered architecture)
  • Check functional boundary clarity (coupling)
  • Generate architecture health report

Usage:

python3 scripts/architecture-check/architecture_check.py --path /path/to/code --report architecture_report.json

Standardized Template Library

Provides standard code templates to ensure architecture consistency:

TemplatePathPurpose
FastAPI Router Templatetemplates/fastapi-module/router_template.pyRouter layer code template
Service Layer Templatetemplates/fastapi-module/service_template.pyBusiness logic layer template
Test Templatetemplates/fastapi-module/test_template.pyTest code template
pytest Configtemplates/config-templates/pytest.iniTest config template
Architecture Rulestemplates/architecture-rules/architecture_rules.mdArchitecture spec doc

Reference Document Index

CategoryDirectoryFile Count
Design Specs - Doc Specsreferences/design-specs/doc-specs/20
Design Specs - Dev Planreferences/design-specs/开发计划方案/9
Design Specs - Quality Testreferences/design-specs/质量检测方案/28
Design Specs - Overviewreferences/design-specs/设计阶段文档规范-总纲.md1
Sub-Agent Guidereferences/ac-agent-guide/SKILL.md1
Task Creationreferences/task-creator/SKILL.md1
Architecture Check Toolscripts/architecture-check/3
Standardized Templatestemplates/5
More in Automation