All skills
lexler avatar

/refactoring-team

@628d2e9
by Lada Kesselerlexler/skill-factory238 stars
61

Iterative code refactoring through progressive lenses via a worker-reviewer agent team.

Use this Skill: https://skilld.dev/gh/lexler/skill-factory/refactoring-team

This session only. Nothing lands on disk.

referencesreviewer-guides21-emergent-design.reviewer.md

≈349 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Lens: Emergent Design Rules (Reviewer Guide)

When to Apply

After wrong abstraction. All refactoring passes are done — this lens evaluates the result against simple design criteria before the final meta-lenses.

What to Look For

This is an evaluation lens, not a refactoring lens. The reviewer should assess the codebase against the four rules:

  1. Tests pass — has any behavior been broken? Run the full test suite
  2. Reveals intention — is the code clearer than when we started?
  3. No duplication — has duplication been reduced without forced abstractions?
  4. Fewest elements — have unnecessary classes, methods, or abstractions been removed rather than added?

First Pass

Worker should review the codebase holistically and flag anything that got worse during refactoring — unnecessary abstractions added, clarity reduced, complexity increased.

Second Pass

If the worker found nothing:

  • Compare the current code to the starting point — is intent clearer or did refactoring add indirection?
  • Check for new abstractions that serve only one caller — are they earning their keep?
  • Look for complexity added by earlier lenses that later lenses did not clean up

When Done

Move on when the code is demonstrably simpler and clearer than when the refactoring started. If any refactoring made things worse, undo it before proceeding to the final meta-lenses.

Source: SKILL.md on GitHub

No alerts6d3 checks · Risk SAFE
  • Gen Agent Trust Hub6d

    The skill facilitates an automated, iterative refactoring workflow using a worker-reviewer agent team. It processes local source code and executes user-provided test commands to verify changes. The skill operates using local scripts and standard development tools without any detected malicious behaviors or obfuscation.

  • Socket6d

    No alerts

  • Snyk6d

    Risk: LOW · No issues

Signed by skilld at 628d2e9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 7 months ago
disable-model-invocation
true
argument-hint
[target-path]
Other metadata
hooks
{
  "TeammateIdle": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "${CLAUDE_SKILL_DIR}/references/guard-idle-worker.sh"
        }
      ]
    }
  ]
}

README badge

README badge for lexler/skill-factory/refactoring-team