agentleFS
Sign inStart free
qivora-labsqivora-labs/agentinit/.claude/skills/refactor/SKILL.md

refactor

Skill1 starsChanged 12 days agoMITView on GitHub

Pin current behavior with tests, then change structure in small steps.

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

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read AGENTS.md, ARCHITECTURE.md, and the active rules that apply to the target.

    line 15
  2. Distinctive:

    Wait until those characterization tests pass before changing structure.

    line 17
  3. Distinctive:

    NEVER: run network commands, install packages, or read secrets.

    line 30

“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

Purpose

Change structure only. Behavior and the public API stay as they are unless the user's input asks for a change.

Input

The user's input: a target and a goal. If either part is missing, ask for it and stop.

Steps

  1. Read AGENTS.md, ARCHITECTURE.md, and the active rules that apply to the target.
  2. If tests do not already cover the target's observable behavior, write characterization tests before any edit. Follow the active test-library rule. Start from a test named x with a dummy expected value, run it, copy the actual result into the assertion, and name the test for that behavior. Keep the observed result unless the user has called it a bug.
  3. Wait until those characterization tests pass before changing structure.
  4. Refactor toward the goal in small steps. After each step, run:
    • pnpm typecheck
    • pnpm lint
    • pnpm test

Output

Summarize the structural changes, the tests that pin current behavior, and each check result. State that behavior and the public API are unchanged, or quote the request that allowed a change.

Guardrails

  • NEVER change observable behavior or the public API unless the user's input asks for that change.
  • NEVER change structure while characterization tests are missing or failing.
  • NEVER edit a characterization test to hide a behavior change the refactor introduced.
  • NEVER run network commands, install packages, or read secrets.

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