agentleFS
PradnyeshpPradnyeshp/Claude-Skills/.claude/skills/refactor/SKILL.md

refactor

Skill2 starsChanged 4 months agoMITView on GitHub

Restructure a file, function, or module toward a stated goal (readability, decoupling, extracting logic, reducing duplication) without changing its behavior. Use when the user says "refactor this", "clean up this function", "extract this into", "decouple", "restructure", or "make this more readable".

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ascii-diagram, debug-fix 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.
  • SethGammonSkill

    ascii-diagram

    Generate perfectly aligned ASCII diagrams — architecture, flow, sequence, box-and-arrow. Uses a programmatic character-grid approach so alignment is guaranteed by math, not token prediction. Includes post-render verification.

    Also in 4 projects that use this

  • zebbernSkill

    debug-fix

    Find and fix a bug or issue — from any source (GitHub issue, error message, user report, or observed behavior)

    Also in 4 projects that use this

  • parcadeiSkill

    agent-context-isolation

    Agent Context Isolation

    Also in 3 projects that use this

  • parcadeiSkill

    agentica-infrastructure

    Reference guide for Agentica multi-agent infrastructure APIs

    Also in 3 projects that use this

  • +8 more from parcadei

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 2

    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:

    Verify: Run the relevant tests / type-checker / linter and confirm they still pass.

    line 27
  2. Distinctive:

    Don't gold-plate — make the change the goal requires, not a sweeping rewrite of unrelated code.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 170 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

Test setup (used to verify behavior is preserved)

!ls package.json pyproject.toml Cargo.toml go.mod pom.xml build.gradle Makefile 2>/dev/null

Instructions

Refactor the target named in $ARGUMENTS toward the stated goal. If the target or goal is unclear, ask which code to refactor and what outcome they want before touching anything.

Core principle

Behavior must not change. A refactor changes how code is expressed, never what it does. Public APIs, return values, and side effects stay identical unless the user explicitly asks otherwise.

Method

  1. Read first. Open the target and its call sites (use Grep). Understand the current behavior and who depends on it before changing it.
  2. Establish a safety net. Identify the tests covering this code. If none exist and the change is non-trivial, say so and offer to add characterization tests first (the test-gen skill can help).
  3. Make small, reviewable moves toward the goal: extract functions/variables, rename for clarity, remove duplication, simplify conditionals, separate concerns. Keep each change focused.
  4. Update all call sites and imports affected by the change. Don't leave the codebase in a broken intermediate state.
  5. Verify. Run the relevant tests / type-checker / linter and confirm they still pass.

Rules

  1. Preserve behavior, signatures, and side effects. Flag explicitly if a change is unavoidably behavior-altering.
  2. Don't gold-plate — make the change the goal requires, not a sweeping rewrite of unrelated code.
  3. Match the project's existing style and idioms; don't introduce new patterns or dependencies just to refactor.
  4. Work in coherent steps and explain each. If the refactor is large, outline the plan and confirm before applying.
  5. End with a summary of what moved/changed and the verification result.

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.