tech-design-writer
Skill1 starsChanged 3 months agoMITView on GitHub
技术方案设计。需求规格就绪后产出技术方案文档:方案对比与选型、架构、数据模型、接口、风险与应对、上线与回滚,每个决定写明取舍。Use to write a technical design document before implementation.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- VanGong1999/openwriting-skillstheir own version, first seen Mar 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- VanGong1999/openwriting-skills★ 8same name
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 repository28 other files it gives its agents.
- api-contract-designerSkill
- api-testerSkill
- bug-diagnoserSkill
- cache-governorSkill
- ci-cd-setupSkill
- code-migratorSkill
- code-reviewerSkill
- commit-message-writerSkill
- db-migration-reviewerSkill
- db-schema-designerSkill
- dev-env-troubleshooterSkill
- frontend-debugSkill
- git-workflowSkill
- log-analysisSkill
- meeting-minutesSkill
- natural-chinese-writerSkill
- performance-profilerSkill
- release-note-writerSkill
- requirement-clarifierSkill
- requirements-reviewerSkill
- security-reviewerSkill
- skill-creator-cnSkill
- skill-style-guideSkill
- sql-reviewerSkill
- task-decomposerSkill
- tdd-workflowSkill
- tech-doc-writerSkill
- weekly-reportSkill
The file
Files
技术方案设计
何时使用
- 用户说"写个技术方案""设计一下实现方案";
- 需求规格已确认,动手前要定架构和关键取舍;
- 方案有争议,需要文档化对比和选型依据;
- 大改动上线前,需要风险评估和回滚方案。
使用步骤
第 1 步:确认输入
- 需求规格(来自 requirement-clarifier 或 PRD);
- 现有系统现状(技术栈、模块、数据);
- 约束:时间、团队规模、运维能力、合规。
第 2 步:明确目标与不做的事
- 目标:解决什么问题、成功长什么样(可度量);
- 不做:明确排除的范围,防止方案失控。
第 3 步:方案对比与选型
每个关键决定至少列两个方案,写清楚:
| 方案 | 优点 | 缺点 | 成本 |
| A | … | … | … |
| B | … | … | … |
选型结论要写"为什么选 A 不选 B",不要只写结论。架构问题本质是取舍,不存在的方案才是问题。
第 4 步:写架构与细节
按模板输出:
# 技术方案:<名称>
## 背景与目标
## 方案对比
## 选型结论
## 架构设计
## 数据模型
## 接口设计
## 关键流程
## 风险与应对
## 上线与回滚原则:
- 架构画清模块和调用方向,数据流讲"请求怎么走";
- 数据模型列出核心表/字段/关系,引用 db-schema-designer;
- 接口列关键契约,引用 api-contract-designer;
- 风险每条配应对,不说"注意一下"这种空话。
第 5 步:校验与评审
用 design_checker.py 自查(见辅助脚本),修掉标出的缺口;然后把方案给相关人评审,重点确认取舍是否成立。
输入与输出
- 输入:需求规格 + 系统现状 + 约束;
- 输出:技术方案文档(含选型依据、风险、上线方案)。
示例
方案对比节选:
## 方案对比
| 方案 | 优点 | 缺点 |
|---|---|---|
| A:单体改造 | 改动小,上线快 | 长期耦合,扩展受限 |
| B:拆独立服务 | 边界清晰,独立扩展 | 需要消息队列与部署改造 |
## 选型结论
选 A:当前团队 3 人、上线窗口两周,拆分收益不足以覆盖成本;留 B 作为下一阶段演进方向。辅助脚本
scripts/design_checker.py 检查方案文档的完整性:
python skills/tech-design-writer/scripts/design_checker.py <方案.md>检查:必需章节是否齐全且非空、方案对比是否至少两个方案、选型是否给理由、风险是否每条有应对、有无占位符。脚本只做标记,结论需要人确认。
注意事项
- 取舍要写理由:不写理由的选型等于没选;
- 方案别堆术语,评审的人可能不熟你用的框架;
- 风险写"发生概率 × 影响 × 应对",别只列现象;
- 上线方案包含回滚:出问题怎么退,比怎么上更重要。
不适用场景
- 需求还没确认(先澄清需求);
- 只问某个技术怎么用,不需要方案文档;
- 已经进入编码阶段,需要的是任务拆解(用 task-decomposer)。
验证方式
- 触发:"写技术方案";
- 跑脚本:design_checker.py 无"必须"级问题;
- 走查:每个选型都有理由,每条风险都有应对;
- 确认:评审人对取舍无异议。
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.

