agentleFS
eugnmueller-87eugnmueller-87/claude-blueprint/.claude/skills/refactor/SKILL.md

refactor

Skill1 starsChanged 5 months agoMITView on GitHub

Behavior-preserving cleanup of a target guarded by the existing test suite — improve names, cut duplication, reduce nesting, without changing what the code does and without touching adjacent code. Use to clean up working code, never to add features. Trigger phrases "refactor X", "clean this up", "tidy this code".

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ascii-diagram, agent-context-isolation and 9 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

  • 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

4 rules. 0 are common, 2 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If there are no tests, that's the blocker — say so.

    line 14
  2. Very specific:

    Establish the safety net: Run the tests covering the target and confirm they pass FIRST.

    line 18
  3. Very specific:

    Run ruff check . — no new lint.

    line 36
  4. Distinctive:

    STOP and flag it, that's not a refactor.

    line 37

“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

refactor

Trigger: "refactor X" / "clean this up" / "tidy this code"

Standing rules: ../_conventions.md.

Refactoring changes structure, never behavior. The test suite is the proof it stayed the same. No scope creep, no adjacent rewrites, no new features slipped in. If there are no tests, that's the blocker — say so.

Steps

  1. Establish the safety net. Run the tests covering the target and confirm they pass FIRST. If the target has no tests, STOP and say so — offer to run test-writer to add a characterization test before refactoring. Never refactor blind.
  2. Scope it tight. Name exactly what you're cleaning and what you are NOT touching. One target. Don't wander into adjacent modules "while you're here".
  3. Refactor in small steps, re-running the tests after each:
    • Rename for clarity (names that lie, generic data/tmp, missing is_/has_).
    • Cut duplication that has actually recurred (not speculative abstraction).
    • Flatten nesting with early returns (>3 levels deep).
    • Split god-functions doing read+validate+transform+persist+notify.
    • Python: prefer pathlib over os.path, comprehensions over manual loops where clearer, logging over print, type hints on public signatures. Behavior stays identical at every step.
  4. Prove no behavior changed. Full relevant test file green, same as step 1. Run ruff check . — no new lint. If a test had to change, behavior changed — STOP and flag it, that's not a refactor.
  5. Report (terse): what you cleaned · tests green before and after · lines/ complexity reduced. Confirm zero behavior change, backed by the test run.

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.