technical-design
Skill0 starsChanged 21 days agoMITView on GitHub
生产级前期系统架构、技术方案设计 (TDD/RFC)、数据建模与算法状态机规范技能。 涵盖方案先行与审阅确认铁律、苏格拉底式需求收敛协议 (Socratic Refinement)、 附带自动化检验指令的微任务拆解 (Bite-Sized Verifiable Tasks)、完成前铁证验证门禁 (Verification Evidence Gate)、 严禁静默重试与兜底补偿、复杂算法标准 LaTeX 公式推导、领域建模 (ER/索引/分表) 及有限状态机闭环。
7 other projects use a version of this.
Adopted by
Most recently taken up by
- ericwang200608-beep/LANYANT-Skillstheir own version, first seen Nov 8, 2026
- Lanqiao-Luca/ai-java-workflowtheir own version, first seen Nov 8, 2026
- thunderstormwang/AgentSkillstheir own version, first seen Nov 6, 2026
- willgt-oss/willgt-skillstheir own version, first seen Nov 1, 2026
- simscal/sapiens-dtjtheir own version, first seen Oct 20, 2026
- gener8v/gener8v.claude-skillstheir own version, first seen Sep 15, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- Lanqiao-Luca/ai-java-workflow★ 220same name
- gener8v/gener8v.claude-skills★ 3same name
- dirkkok101/skills★ 2same name
- ericwang200608-beep/LANYANT-Skills★ 2same name
- simscal/sapiens-dtj★ 0same name
- thunderstormwang/AgentSkills★ 0same name
- willgt-oss/willgt-skills★ 0same 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 repositoryOne other file it gives its agents.
- technical-designSkill
The file
Files
系统架构与前期技术方案设计规范 (Technical Design Skill)
核心设计铁律 (Core Redlines)
- 🚨 复杂需求必须“方案先行、审阅确认后再编码”：严禁在未输出 TDD/RFC 并经用户确认前直接动工写业务代码；
- 🚨 多层级递进分治与全局闭环串联铁律 (Hierarchical Decomposition & Closure Gate)：复杂需求坚决禁止单层平铺设计；强制按 L1 宏观边界 -> L2 领域阶段 -> L3 原子单元递进拆解；局部设计完成后，必须向上执行契约拓扑、逆向补偿与状态终态三大闭环检查，方可进入微任务拆解；
- 🚨 坚决禁止静默添加重试、兜底与补偿逻辑：凡遇潜在失败，必须在方案中设立专门章节阐明原因、副作用并由用户拍板；
- 🚨 苏格拉底式需求收敛协议 (Socratic Refinement)：需求模糊时严禁长篇脑补，必须提出 2-3 个关键决策点聚焦收敛；
- 🚨 复杂算法与数学模型标准 LaTeX 规范：严禁用自然语言含糊替代关键算法，强制使用标准 LaTeX 公式给出定义域与边界；
- 🚨 完成前铁证验证门禁 (Verification Evidence Gate)：严禁口头声明完成，微任务实施落地必须提供真实命令通过证据（Exit Code 0）。
标准设计工作流 (Workflow SOP)
- 需求探测与边界收敛：通过苏格拉底协议澄清歧义，确定 In-Scope 与容量指标；
- 多层级递进分治设计：按 L1 宏观全景 -> L2 领域阶段 -> L3 原子单元逐层拆解并针对性设计；
- 架构推演与模型设计：制定 ER/索引、Redis 命名空间与 TTL、Mermaid 时序图与 FSM 状态机；
- 整体串联与闭环审查：执行契约拓扑、逆向补偿与状态机终态三大闭环门禁自查；
- 可验证微任务拆解：输出携带 Target Files、自动化检验命令与 Evidence Gate 的原子任务列表；
- 用户审阅确认与开干：交由用户审阅确认后，方可解锁写入权限开展微任务落地。
渐进式参考手册索引 (Progressive Disclosure References)
更深入的设计模板、状态机规范与技术栈专项，按需调阅：
| 领域模块 | 子手册路径 | 核心覆盖内容 |
| 需求收敛、分治与 RFC 模板 | 01_rfc_template_and_socratic_refinement.md | 苏格拉底提问协议、多层级递进分治与闭环检查、标准 RFC 交付模板、ADR 决策记录 |
| 数据建模与算法状态机 | 02_data_fsm_and_latex_modeling.md | MySQL 索引/分表、Redis Key 规范、Mermaid 时序与 FSM 闭环、LaTeX 数学公式推导 |
| 微任务拆解与验证门禁 | 03_bite_sized_tasks_and_evidence_gate.md | 10~20 分钟微任务四要素、自动化验证命令标准、完成前铁证验证门禁 |
| 可观测性与安全规范 | 04_observability_security_and_domain_specs.md | SLO/Trace 穿透、越权防护与敏感脱敏、Go/FastAPI/爬虫专属前置规范与评审 Checklist |
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.