agentleFS
nazmirketnazmirket/skills/skills/refactor/SKILL.md

refactor

Skill0 starsChanged 2 days agoMITView on GitHub

Use for distinct structural work that simplifies existing code while preserving its observable contract.

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

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 1

    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:

    Remove duplication when it enforces one shared rule.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 168 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

Make the smallest change that improves the structure. Handle incidental simplification within the current task. Raise a separate change when the work expands scope, such as merging untouched helpers with multiple callers.

Establish what must stay true

  • Inspect the callers and behavior the edit could affect, including outputs, ordering, errors, and side effects. Use Adapt if project facts are missing. If a consumer might rely on undocumented behavior, show the evidence and ask what to preserve. Continue work that cannot change it. Route lasting boundary choices to Architect.
  • Reuse focused checks that cover the affected behavior. If an important outcome is untested and the edit could change it, add a focused characterization case and run it before and after. Reuse the existing test file when it fits.
  • Record baseline failures. Continue if a failure is demonstrably unrelated; if it might overlap, investigate that overlap before editing.

Simplify and verify

  • Remove duplication when it enforces one shared rule. Keep similar logic local when its callers or requirements evolve independently. Review the affected diff for scope and unintended changes.
  • Fix a bounded, in-scope violation of an established contract in the same task. Verify the correction separately and report the exact behavior that changed. Use Debug if the cause is unclear. Flag unrelated defects and ask before changing a product rule.
  • Compare against the baseline and rerun relevant and required project checks. Use Test when verification needs specialist work. Report pre-existing failures and what actually passed. If a behavior check cannot run, deliver the patch with the exact steps still needed and mark that behavior unverified. Honor explicit completion gates and use Preflight for setup blockers.
  • Describe what became simpler or what work was removed. Claim a runtime gain only with comparable measurements.

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.