agentleFS
Sign inStart free
elfrostelfrost/ai-patchlab/.agents/skills/refactor/SKILL.md

refactor

Skill1 starsChanged 30 days agoMITView on GitHub

Analyze code for smells, complexity, and pattern violations, then optionally execute selected refactorings with validation after each change. Use when the user wants to clean up a file, module, or directory without changing behavior.

196 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

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 9

    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:

    Read CLAUDE.md for thresholds (file size, function length, complexity)

    line 11
  2. Distinctive:

    Ask the user which refactorings to execute:

    line 28
  3. Distinctive:

    If validation fails, REVERT the change and flag it

    line 42
  4. Distinctive:

    Run the full validation loop after all changes

    line 46
  5. Distinctive:

    Ask the user to approve the commit

    line 48
  6. Distinctive:

    Never refactor without showing the plan first

    line 52
  7. Distinctive:

    Always run tests after each refactoring

    line 53
  8. Distinctive:

    If tests break, revert and flag — don't try to "fix forward"

    line 54
  9. Distinctive:

    Keep refactorings atomic — one change at a time

    line 55

“Common” is measured: kept by at least 6 in 10 of the 169 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

Targeted refactoring with diff preview and per-change validation. Default scope is src/; user may pass a path.

Phase 1: Analyze

  1. Read CLAUDE.md for thresholds (file size, function length, complexity)
  2. Detect smells in scope:
    • Files > 300 lines (per project standard)
    • Functions > 50 lines
    • Cyclomatic complexity > 10
    • Duplicated blocks
    • Naming violations (per CLAUDE.md conventions)
    • Missing type hints (required per CLAUDE.md)

Phase 2: Propose

Produce a numbered refactoring report:

  • R-001: <smell> in file:line -> <proposed fix> (impact: low / med / high)
  • R-002: ...

For each proposal, include the exact change (diff preview), why it improves the code, and the risk level.

Phase 3: Approve

Ask the user which refactorings to execute:

  • "all" — execute all
  • "R-001, R-003" — execute selected
  • "none" — report only

Phase 4: Execute (atomic per change)

For each approved refactoring:

  1. Apply the change
  2. Run validation:
    ruff check src/
black --check src/
pytest tests/ -v --tb=short
  3. If validation fails, REVERT the change and flag it
  4. Continue with the next refactoring

Phase 5: Final validation + commit

  1. Run the full validation loop after all changes
  2. Show the cumulative diff
  3. Ask the user to approve the commit
  4. Commit message: refactor: <description>

Rules

  • Never refactor without showing the plan first
  • Always run tests after each refactoring
  • If tests break, revert and flag — don't try to "fix forward"
  • Keep refactorings atomic — one change at a time
  • Preserve behavior — refactoring is not a feature change

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