agentleFS
ack-solutionsack-solutions/claude-code-ai-skills/skills/code-quality/SKILL.md

code-quality

Skill1 starsChanged 44 days agoMITView on GitHub

Audit code organization, coupling, duplicated business rules and reuse, or perform requested refactoring. Use for maintainability reviews, remove duplicated logic, or clean up this module. For a specific failure prefer systematic-debugging; for a dedicated security review prefer security-audit.

77 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use spring-boot, logging-patterns 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.
  • ffsshhttiikkSkill

    spring-boot

    Spring Boot framework and Java enterprise patterns

    Also in 3 projects that use this

  • DIL8654Skill

    logging-patterns

    Keep logs structured, correlated, low-noise, and safe for production support. Use when adding operational logging, reviewing observability, or improving diagnostics in .NET services.

    Also in 3 projects that use this

  • mstuder-slalomSkill

    jpa-patterns

    JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.

    Also in 3 projects that use this

  • ffsshhttiikkSkill

    design-patterns

    Practical application and coding skills for Design Patterns

    Also in 4 projects that use this

  • glommerSkill

    pr-workflow

    General guidelines for Commits, formatting, CI, dependencies, security

    Also in 4 projects that use this

  • vm0-aiSkill

    cli-design

    Design patterns and conventions for the Okou CLI user experience

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 71 edited versions we read keep these.

  • 3

    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:

    If the user has reported a failure, prioritize reproducing and understanding that failure before structural cleanup.

    line 15
  2. Distinctive:

    Use the refactor checklist for changes across callers or shared state.

    line 34
  3. Distinctive:

    Use the project's review format or this compact default per material finding:

    line 38

“Common” is measured: kept by at least 6 in 10 of the 71 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

Code quality

Improve maintainability with evidence from real responsibilities and callers. Follow existing project conventions and the user's scope.

Select the requested mode

  • Audit/review: inspect and report; do not change application behaviour or files merely because a finding exists.
  • Refactor/fix quality issues: make the requested scoped improvements and verify preservation of intended behaviour. Do not ask again for authorization already present in the request.

If the user has reported a failure, prioritize reproducing and understanding that failure before structural cleanup. Keep feature changes distinct from refactors.

Investigate

Discover relevant project rules, package boundaries, contracts and tests. Trace entry points, consumers and data ownership in the requested area. Widen inspection only when shared behaviour crosses that boundary.

Assess:

  • Business-rule duplication: do repeated conditions represent the same policy and need to evolve together?
  • Responsibilities and coupling: misplaced decisions, cycles, leaky abstractions, oversized public APIs and unrelated concerns in one component/service.
  • Reuse: existing domain helpers and UI components, copy-pasted logic, speculative generic wrappers and components overloaded by unrelated flags.
  • Contracts and state: conflicting type definitions, duplicate sources of truth, derived state that can become stale, and client/server disagreement.
  • Failure handling and testability: swallowed errors, misleading success states, hidden side effects and dependencies that prevent meaningful tests.
  • Dead code: verify exports, configuration, reflection/dynamic use and other consumers before removing apparently unused symbols.

Similar syntax is not sufficient evidence for abstraction. Separate business concepts may correctly have similar implementations. Caches, snapshots and denormalized summaries are valid when their authoritative source and update/rebuild rules are clear.

Refactor when requested

Use the refactor checklist for changes across callers or shared state. Keep changes reviewable, move a rule to its correct owner, and update all affected in-scope consumers. Preserve external contracts, permissions and intended observable behaviour. Identify any required functional change explicitly.

Report format

Use the project's review format or this compact default per material finding:

  • Finding and kind: correctness defect, maintenance cost or optional preference.
  • Location and callers: file/symbol and affected consumers.
  • Evidence and impact: observed behaviour or coupling, with uncertainty stated.
  • Proposed change and verification: intended improvement and checks that would establish it.

Prioritize by impact and confidence; do not invent a quality score or enforce arbitrary file-length targets. Report relevant security or runtime defects encountered rather than ignoring them because a specialist workflow exists.

For implemented refactors, report the changed responsibility/reuse and checks actually run. Do not equate fewer lines or a passing linter with a correct refactor.

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.