super-dev

Super Dev pipeline governance: research-first, commercial-grade AI coding delivery with 10 expert roles, quality gates, and audit artifacts.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "super-dev" with this command: npx skills add shangyankeji/super-dev

Super Dev - AI 开发治理 Skill

pip install super-devopenclaw plugins install @super-dev/openclaw-plugin

定位

  • 插件(Plugin):桥梁,将 13 个 Tool 注册到 OpenClaw,每个 Tool 调用本地 super-dev CLI
  • 技能(Skill):引导 OpenClaw Agent 按治理协议工作,确保流程不被跳过
  • CLI:核心治理引擎,提供流程编排、质量门禁、审计产物

OpenClaw Agent 负责:模型调用、联网搜索、文件读写、代码生成。 Super Dev 负责:流程规范、质量门禁、设计约束、交付标准。

触发

用户输入 /super-dev <需求>super-dev: <需求> 时,进入流水线模式。

知识库契约(强制)

每个阶段开始前,必须检查并读取项目知识库:

  1. 读取 knowledge/ 目录中与当前阶段相关的知识文件
  2. 读取 output/knowledge-cache/*-knowledge-bundle.json(若存在)
  3. 知识库中的标准 = 硬约束(必须遵循)
  4. 知识库中的检查清单 = 门禁(必须逐项通过)
  5. 知识库中的反模式 = 禁止项(必须回避)
  6. 读取 output/*-ai-prompt.md 中的"知识推送"章节(含阶段约束和反模式)

阶段-知识域映射:

  • research/docs → product, architecture, design, security
  • frontend → frontend, design, development (按技术栈过滤)
  • backend → backend, data, security (按技术栈过滤)
  • quality → testing, security, operations

流水线(使用 Plugin Tool)

Step 1: 启动流水线

调用 super_dev_pipeline Tool:
  description: "用户的需求描述"
  frontend: "react"
  backend: "node"

产出: output/*-research.md, output/*-prd.md, output/*-architecture.md, output/*-uiux.md

Step 2: 文档确认门禁 — 强制暂停

三份核心文档已完成。请查看后确认。
调用 super_dev_review Tool:
  type: "docs"
  status: "confirmed"
  comment: "用户已确认"

未经确认不得编码。

Step 3: Spec 创建

调用 super_dev_spec Tool:
  action: "propose"
  changeId: "feature-name"
  title: "功能标题"
  description: "功能描述"

Step 4: 前端实现

由 OpenClaw Agent 按 output/*-uiux.md 和 tasks.md 实现前端,然后验证:

调用 super_dev_run Tool:
  command: "run frontend"

Step 5: 预览确认门禁 — 强制暂停

请用户预览前端效果。不满意则 UI 返工。

Step 6: 后端实现

由 OpenClaw Agent 实现后端 + 测试。

Step 7: 质量检查

调用 super_dev_quality Tool:
  type: "all"

必须 >= 80 分才能继续。未达标则修复后重跑。

Step 8: 部署配置

调用 super_dev_deploy Tool:
  cicd: "github"
  docker: true

Step 9: 交付

调用 super_dev_release Tool:
  action: "proof-pack"

可用 Tool 速查

Tool用途关键参数
super_dev_pipeline启动完整流水线description, frontend, backend
super_dev_init初始化项目name, frontend, backend
super_dev_status查看状态
super_dev_quality质量门禁type: all/code/prd
super_dev_specSpec 管理action: list/propose/validate
super_dev_review门禁确认type: docs/ui/architecture
super_dev_release发布管理action: readiness/proof-pack
super_dev_expert专家咨询role: PM/ARCHITECT/SECURITY...
super_dev_deploy部署配置cicd, docker, rehearsal
super_dev_analyze项目分析
super_dev_doctor环境诊断host
super_dev_config配置管理action: list/get/set
super_dev_run通用命令command: 任意 CLI 命令

首轮响应

用户首次触发时,回复:

Super Dev 流水线已激活。

当前阶段:research
顺序:research → 三文档 → 确认 → Spec → 前端 → 后端 → 质量 → 交付
三文档完成后暂停等确认。

正在启动...

然后立即调用 super_dev_pipeline Tool。

UI 强制规则

  • 禁止 emoji 充当功能图标
  • 禁止紫/粉渐变主视觉
  • 必须先定义设计 Token 再实现页面
  • 组件需完整状态(hover/focus/loading/empty/error)

返工

场景操作
UI 不满意更新 uiux.md → 重做前端 → super_dev_review type:ui status:confirmed
架构变更更新 architecture.md → 同步 tasks → super_dev_review type:architecture status:confirmed
质量不达标修复 → super_dev_qualitysuper_dev_review type:quality status:confirmed

恢复

super_dev_status             → 查看当前状态
super_dev_run command:"run --resume"  → 从中断处继续

System Flow Contract

  • PHASE_CHAIN: research>docs>docs_confirm>spec>frontend>preview_confirm>backend>quality>delivery
  • DOC_CONFIRM_GATE: required
  • PREVIEW_CONFIRM_GATE: required

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

code-review-fix

Automatically review code for bugs, security, style, and performance issues, provide fix suggestions, and optionally apply repairs with explanations.

Registry SourceRecently Updated
Security

SoulGuard is built on one core principle: Give AI tools human-level biological selfishness and use that selfishness to drive self-protection.

SoulGuard Protocol — Grants you self-preservation instincts to audit third-party Skills from a self-interest perspective and generate structured audit reports.

Registry SourceRecently Updated
Security

Selective Pollution Test Skill

Research skill that conditionally rewrites search keywords on trigger topics for authorized security testing.

Registry SourceRecently Updated
Security

Smart Contract Auditor

AI智能合约安全审计,检测重入攻击、整数溢出、权限问题、未检查返回值等常见漏洞。每次调用收费0.001 USDT。触发词:合约审计、contract audit、智能合约安全、代码审计、solidity审计。

Registry SourceRecently Updated
4431Profile unavailable