agentleFS
Sign inStart free
charanjit-singhcharanjit-singh/lovable-skills/skills/refactor-safe-diff/SKILL.md

refactor-safe-diff

Skill10 starsChanged 6 months agoMITView on GitHub

Use when refactoring, renaming, or restructuring code where behavior must stay the same, or when the user asks for minimal/surgical changes. Not for greenfield features or intentional behavior changes unless listed.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Run through affected call sites — no broken imports.

    line 17
  2. Distinctive:

    Keep tests/flows working: auth, payments, critical paths unchanged.

    line 23
  3. Distinctive:

    Follow-up risks or deferred cleanup (if any).

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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-safe diff

Rules

  1. Smallest diff that achieves the goal — no drive-by formatting, renames, or "while we're here" features.
  2. Do not change behavior unless explicitly requested; list behavior changes if unavoidable.
  3. Touch only files required for the task; avoid moving files unless asked.
  4. Preserve public APIs (exports, prop names) unless migration is in scope.
  5. Run through affected call sites — no broken imports.

Process

  1. State what will change and what will not change.
  2. Refactor in steps: extract → wire → delete old (if safe).
  3. Keep tests/flows working: auth, payments, critical paths unchanged.

Verify

After each step:

  • TypeScript compiles (no new errors introduced).
  • Critical flows still work in chat preview (auth, primary action, payment if applicable).
  • Imports and exports resolved; no broken references left behind.

Output

When done, summarize:

  • Files changed (count and names).
  • Behavior preserved confirmation.
  • Follow-up risks or deferred cleanup (if any).

Avoid

  • Renaming entire codebase conventions in one pass.
  • Swapping libraries (SWR → React Query) without explicit ask.
  • Deleting code paths you did not verify unused.
  • Bundling unrelated bug fixes into the same refactor PR.

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