agentleFS
ryotaroh180105ryotaroh180105/claude-skills/.agents/skills/improve-codebase-architecture/SKILL.md

improve-codebase-architecture

Skill0 starsChanged 4 months agoNo licenceView on GitHub

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

213 other projects use a version of this, 147 of them edited; 146 of 148 edited versions we compared changed its rules; 13 new projects in the last 4 weeks, against 20 the 4 before.

How people change it

146 of 148 edited versions changed its rules, and some changes recur.

Of the 148 edited versions we compared: 2 keep every rule, 146 made changes of their own.

Rules people drop

  1. Read the project's domain glossary (CONTEXT.md) and any ADRs in the area you're touching first.dropped by 14 of 146
  2. Sharpening a fuzzy term during the conversation? Update CONTEXT.md right there.dropped by 10 of 146
  3. Do NOT propose interfaces yet. After the file is written, ask the user: "Which of these would you like to explore?"dropped by 8 of 146

Rules people add

  1. If the user named a direction (a module, a subsystem, a pain point), take it, and skip the inference below.added by 100 of 146
  2. Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in [LANGUAGE.md](LANGUAGE.md).added by 44 of 146
  3. ADR conflicts: if a candidate contradicts an existing ADR, only surface it when the friction is real enough to warrant revisiting the ADR. Mark it clearly (e.g. _"contradicts ADR-0007 — but worth reopening because…"_). …added by 27 of 146
  4. Read the existing documentation first:added by 3 of 146
  5. If any of these files don't exist, proceed silently — don't flag their absence or suggest creating them upfront.added by 3 of 146
  6. A rule we can't quote: its licence doesn't allow itadded by 2 of 146

We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.

Adopted by

Cooling: 13 new projects took it in the last 4 weeks, 0.7× the 4 weeks before.

Week of Sep 20: 2 new projectsWeek of Sep 27: 1 new projectWeek of Oct 4: 7 new projectsWeek of Oct 11: 10 new projectsWeek of Oct 18: 3 new projectsWeek of Oct 25: 3 new projectsWeek of Nov 1: 5 new projectsWeek of Nov 8: 2 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read.

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules and decision-mapping.

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.
  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • FabienDehopreSkill

    decision-mapping

    Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.

    Also in 8 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 1 is common, 0 are distinctive, and 2 are very specific to this project.

  • 1

    Common

    Most of the 174 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

“Common” is measured: kept by at least 6 in 10 of the 174 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.