agentsclimarketplace

Yalla simplify audit

Skill iwo-szapar/yalla-autonomus-coding/skills/yalla-simplify-audit

Whole-repo audit for avoidable complexity, dead abstractions, custom stdlib/native behavior, unnecessary dependencies, and minimum-diff opportunities. Use when the user says audit for bloat, repo simplify audit, what can we delete, or /yalla-simplify-audit.From its SKILL.md

Install
npx -y skills add iwo-szapar/yalla-autonomus-coding --skill yalla-simplify-audit

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, as published. Nobody here has run it

/yalla-simplify-audit

Repo-wide complexity audit. Rank findings by deleted maintenance burden, not cleverness. Apply nothing.

Scope

If the user gives a directory or subsystem, stay there. Otherwise scan the repo excluding generated/runtime directories such as node_modules, .git, .pipeline, dist, build, and vendored assets.

Read ${CLAUDE_PLUGIN_ROOT}/knowledge/yalla/MINIMUM-DIFF.md first.

Hunt

  • Unused files, exports, flags, config, scripts, or compatibility paths.
  • Pass-through wrappers and one-method service layers.
  • Interfaces or abstract classes with one implementation and no test substitute.
  • Helpers with one caller where inline code is clearer.
  • Hand-rolled stdlib/native behavior.
  • Dependencies used for one small feature the platform already covers.
  • Parallel implementations of the same workflow.
  • Tests that only verify mocks or private internals when a public seam exists.

Output

Rank biggest cut first:

<tag> <what to cut>. <replacement>. [path]

Tags: delete, existing, stdlib, native, dependency, yagni, shrink, test-seam.

Keep the report to high-confidence cuts. Prefer five deletions a maintainer can act on today over a long speculative inventory.

End with:

net: -<N> lines, -<M> deps possible.

If nothing meaningful appears:

Lean already. Ship.

Boundaries

  • Do not apply fixes.
  • Do not report correctness/security/performance bugs unless the fix is deletion or simplification.
  • Do not count essential validation, accessibility, error handling, or deterministic proof as bloat.
  • Prefer 5 high-confidence cuts over a long speculative list.

Keep looking

Skills are one crate of 627,801. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.