dev-workflow
Skill0 starsChanged 8 months agoMITView on GitHub
全栈开发工作流编排器,按 8 阶段顺序执行:需求分析 → 技术选型 → 技术评审 → 程序设计 → 任务拆分 → 单元测试 → 代码开发 → 自我验证。
32 other projects use a version of this.
Adopted by
Most recently taken up by
- AsiaOstrich/EngramGraphtheir own version, first seen Nov 8, 2026
- pandazki/pneuma-skillstheir own version, first seen Nov 6, 2026
- bmsuisse/skillstheir own version, first seen Nov 6, 2026
- openflocon/Flocontheir own version, first seen Nov 1, 2026
- Youngju-Heo/claude-skilltheir own version, first seen Nov 1, 2026
- dzianisv/skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use retrospective, brainstorm and 6 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkillretrospective
Review how work went and improve the next round. USE WHEN asked for a retro, delays, or process lessons. DO NOT USE for code review or transcript replay.
Also in 3 projects that use this
nicolasestremSkillbrainstorm
Structured idea generation and solution exploration with systematic analysis.
Also in 4 projects that use this
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 4 projects that use this
HashiCorpSkillchangelog
Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.
Also in 3 projects that use this
VercelSkilldeploy
Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".
Also in 3 projects that use this
GoogleSkillimprove-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Also in 3 projects that use this
Other versions32 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 32
- ag2ai/faststream★ 5.4ksame name
- xstongxue/best-skills★ 2.9ksame name
- AltimateAI/vscode-dbt-power-user★ 586same name
- openflocon/Flocon★ 379same name
- SmartThingsCommunity/SmartThingsEdgeDrivers★ 349same name
- pandazki/pneuma-skills★ 161same name
- AsiaOstrich/universal-dev-standards★ 84same name
- clarity-digital-development/tworkflow★ 47same name
- addxai/enterprise-harness-engineering★ 44same name
- muyen/vibe-to-prod★ 34same name
22 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- .claude/skills/CLAUDE.mdCLAUDE.md
- code-developmentSkill
- history-managerSkill
- program-designSkill
- requirements-analysisSkill
- self-verificationSkill
- task-breakdownSkill
- technical-reviewSkill
- technology-selectionSkill
- unit-testingSkill
The file
Files
全栈开发工作流
用户通过 /dev-workflow 启动。可选传入 iteration-id 恢复已有迭代。
启动流程
- 调用
history-managerskill 执行init(确保docs/history.json存在)。 - 若传入
$ARGUMENTS且为有效 iteration id,恢复该迭代;否则调用history-manager执行new-iter创建新迭代。 - 调用
history-manager执行status读取当前迭代的state,从该阶段继续执行。
阶段执行顺序
| 顺序 | 阶段 | Skill | 执行方式 | 说明 |
| 1 | 需求分析 | requirements-analysis | inline | 与用户对话,梳理功能点 |
| 2 | 技术选型 | technology-selection | inline | 询问全栈/前端/后端,选定技术栈 |
| 3 | 技术评审 | technical-review | fork/Explore | 评审架构可行性、API 契约、风险项 |
| 4 | 程序设计 | program-design | inline | 设计模块分层、流程、工程目录 |
| 5 | 任务拆分 | task-breakdown | fork/Plan | 将设计拆为可管理的开发单元 |
| 6 | 单元测试 | unit-testing | fork | 按任务单元设计测试用例 |
| 7 | 代码开发 | code-development | inline | 按测试驱动实现代码 |
| 8 | 自我验证 | self-verification | fork/Explore | 运行测试、集成验证、质量自检 |
执行规则
- Inline 阶段必须与用户对话:需求分析、技术选型、程序设计、代码开发(阶段 1、2、4、7)均在主对话中执行。所有决策点以结构化选项呈现(编号选项,让用户选择而非自由输入),等待用户选择后再产出/推进,不得跳过用户直接生成结果。每轮不超过 3 个问题。
- 状态恢复:每个阶段开始前,调用
history-manager的get-phase和check-file检查该阶段是否已完成。若已完成则跳过,直接进入下一阶段。 - 状态写入:每个阶段完成后,调用
history-manager的set-phase <phase> <phase_id>更新 history。 - 阶段 id 生成:使用
{阶段缩写}-001格式(如req-001、ts-001)。同一迭代内递增。 - 自我验证失败:若 self-verification 报告有未通过项,回退到 code-development 修复后重新验证。
- 产出位置:所有阶段文档写入
docs/{current_iteration_id}/。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

