architecture-audit
Skill12 starsChanged 6 days agoMITView on GitHub
架构体检:找出该合并加深的浅模块,用 eli5 图解呈现,再为选中的一项并行设计几种接口。
16 other projects use a version of this.
Adopted by
Most recently taken up by
- harshitsinghbhandari/domain-expansiontheir own version, first seen Nov 8, 2026
- MarieLynneBlock/arcanum-artifextheir own version, first seen Nov 1, 2026
- RBraga01/a-teamtheir own version, first seen Nov 1, 2026
- helderberto/agent-skillstheir own version, first seen Oct 11, 2026
- nelantone/cogniviatheir own version, first seen Oct 11, 2026
- Vincweb/caudron-plugintheir own version, first seen Oct 9, 2026
Used with
Projects with it also use review and tdd.
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.Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 16
- RBraga01/a-team★ 24same name
- helderberto/agent-skills★ 19same name
- BrentRector/claude-skills★ 6same name
- creativedeals/free-claude-skill-architecture-audit★ 4same name
- MarieLynneBlock/arcanum-artifex★ 4same name
- gootf/software-agent-sop★ 2same name
- harshitsinghbhandari/domain-expansion★ 2same name
- seikaikyo/dash-skills★ 2same name
- InsightStudio-2026/agent-assets★ 1same name
- MKAbuMattar/skills★ 1same name
6 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 repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- gpt-imageSkill
- postSkill
- promoSkill
- videoSkill
- cuepadSkill
- better-testSkill
- project-setupSkill
- prototypeSkill
- prSkill
- shipSkill
- write-swiftSkill
- ui-craftSkill
- ui-picksSkill
- better-browser-useSkill
- better-computer-useSkill
- herdrSkill
- sshSkill
- researchSkill
- session-dataSkill
- web-searchSkill
- fan-outSkill
- grillingSkill
- hillclimbSkill
- retroSkill
- eli5Skill
- writing-for-agentsSkill
- writing-for-humansSkill
The file
Files
架构体检
找出值得加深的模块:接口几乎和实现一样复杂、理解一个概念要在许多小文件间来回跳、bug 藏在调用方式里的地方。目标是改一处就够、测试只打一个入口。
1. 圈范围
用户指了模块、子系统或痛点就只看那里。否则沿较长一段 git log --oneline 找反复改动的热点,优先看它们;改动分散时再扩大。按 fan-out 中档按热点拆片,交回摩擦点及证据(文件、调用方)。
判断一个模块是不是透传层,用删除测试:想象删掉它,复杂度随之消失的是透传层;复杂度散回 N 个调用方的,它在干活。
2. 呈现
按 eli5 把候选画成图解,文件放 $TMPDIR,不进仓库。每个候选讲清:涉及文件、问题、改法、收益(用行为说:改价格规则只动一个文件,不写「更易维护」)、改前改后对比图、推荐强度(值得做 / 值得探索 / 推测)、依赖类别(见下)。最后说最先做哪一个及原因。此时不提接口方案,问用户想展开哪一个。
3. 设计接口
用户选定后,先写一段约束说明(新接口必须满足什么、依赖属于哪一类、一段粗略代码示意)给用户看,同时按 fan-out 高档并行出 3 个以上截然不同的接口:
- 最小接口:1–3 个入口,每个入口承担尽量多的行为。
- 最大灵活:支持多种用例与扩展。
- 为最常见的调用方优化:默认情况最简单。
- (跨进程依赖时)围绕端口与适配器设计。
每份方案交回:接口(类型、不变量、调用顺序、错误形态)、调用示例、藏在接口后面的东西、依赖与适配器、强弱处。逐个展示后比较:调用方学一个接口能用到多少行为、改动会不会集中在一处、接口放在哪。给出明确推荐,能取长补短就提混合方案。需要逐项和用户对齐决策时用 grilling。
依赖类别
类别决定加深后怎么测:
- 进程内(纯计算、内存状态):直接合并,经新接口测试。
- 可本地替代(PGLite 代 Postgres、内存文件系统):用替代物测,不在接口上开端口。
- 自有远程服务:接口处定义端口,生产用 HTTP/队列适配器,测试用内存适配器。
- 第三方服务(Stripe 等):作为注入的端口,测试给模拟适配器。
判断规则
- 只有一个适配器的端口是假设,两个(通常是生产 + 测试)才是真的;不够两个就别开端口,那只是多一层间接。
- 内部接缝可以给自己的测试用,不为此暴露到接口上。
- 加深后,浅模块上的旧单元测试删掉;改动从新接口的真实入口验证。
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.

