agentleFS
Sign inStart free
CodeCaroSCodeCaroS/MythOs_Aegis/.agents/skills/improve-codebase-architecture/SKILL.md

improve-codebase-architecture

Skill0 starsChanged 3 months agoApache-2.0View on GitHub

Review a codebase for evidence-backed architecture improvements, prioritizing hot paths, duplicated complexity, leaky boundaries, and hard-to-test flows while preserving established domain decisions. Use for architecture audits, module reviews, refactor candidates, or blunt good-cop/bad-cop reviews.

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use migrate-to-shoehorn, writing-beats and 10 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.
  • simo97Skill

    migrate-to-shoehorn

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

    Also in 73 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 68 projects that use this

  • simo97Skill

    request-refactor-plan

    Use this skill when user wants to create a refactor plan.

    Also in 43 projects that use this

  • 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

  • LesaniSkill

    writing-shape

    Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

    Also in 65 projects that use this

  • +2 more from simo97

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 184 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the review analysis-only until implementation is explicitly requested.

    line 15
  2. Distinctive:

    Read repository instructions, status, recent history, domain vocabulary, and relevant ADRs.

    line 19
  3. Distinctive:

    Prefer deletion, consolidation, or an existing seam over a new abstraction.

    line 22
  4. Distinctive:

    Use a diagram or HTML report only when relationships are materially clearer than concise prose.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 184 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Improve Codebase Architecture

Keep the review analysis-only until implementation is explicitly requested.

Workflow

  1. Read repository instructions, status, recent history, domain vocabulary, and relevant ADRs.
  2. Scope the review to the named area or recurring change hotspots.
  3. Trace each candidate end to end, including callers, persistence, trust boundaries, UI state, and tests.
  4. Prefer deletion, consolidation, or an existing seam over a new abstraction.
  5. Apply the deletion test: removing a module should concentrate complexity, not merely relocate it.
  6. Rank only confirmed findings:
    • Strong: repeated friction with a small, testable root fix.
    • Worth exploring: credible benefit with unresolved tradeoffs.
    • Speculative: insufficient evidence; do not recommend implementation.
  7. For each finding, cite files, explain current friction, give the smallest root-cause change, and name the verification.
  8. Use a diagram or HTML report only when relationships are materially clearer than concise prose.

Reject one-implementation interfaces, speculative factories, framework rewrites, test-only extraction, and patterns imported against the repository's architecture. Distinguish implementation evidence from formal acceptance or release status.

Adapted for MythOs Aegis from mattpocock/skills improve-codebase-architecture.

Shared output profile

Compose the review profile from output-templates. Rank findings by impact with location, evidence, consequence, smallest refactor, risk, and verification seam. Preserve stricter domain rules above, omit empty components, and never fill a component with invented evidence.

Download now (ZIP)

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.

Check your setup, free