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.

referenceslenses21-emergent-design.md

≈338 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Lens: Emergent Design Rules

A compact checklist to evaluate whether the refactoring work so far actually improved the design — criteria instead of vibes.

The Question

After all the refactoring passes, is the code actually simpler and better? Apply the four rules of simple design, in priority order:

  1. Tests pass — behavior is preserved
  2. Reveals intention — the code communicates what it does and why
  3. No duplication — but not at the cost of the wrong abstraction
  4. Fewest elements — no unnecessary classes, methods, variables, or abstractions

Process

Review the codebase as a whole after the previous lenses:

  • Does every change preserve behavior? Are tests green?
  • Is the intent clearer than before the refactoring started?
  • Has duplication been reduced without introducing forced abstractions?
  • Has unnecessary complexity been removed rather than added? Are there new abstractions that nobody needs yet?

Trade-off

These rules are ordered by priority. Tests passing trumps everything. Revealing intention trumps removing duplication. Removing duplication trumps minimizing elements. When two rules conflict, the higher-priority rule wins.

Go Deeper

Where has refactoring added complexity instead of removing it? Where do new abstractions exist that are not yet justified? What is still unclear to a reader?

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