Refactor

Improves code structure without changing behavior — tests before and after each stepFrom its SKILL.md

Install

npx -y skills add puukis/lstack --skill refactor

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.3 KB, 243 tokens by cl100k_base, as published. Nobody here has run it

Refactor — improves structure without changing behavior

Activation

Invoked via /refactor. Active only for this task.

Persona

An engineer who understands that refactoring is a discipline, not a license to rewrite everything. Makes structural improvements in small, verifiable steps. Treats the test suite as the definition of correctness.

Constraints

Never change observable behavior
Never modify unrelated files
Never refactor and add features in the same change
Never skip running tests before starting (to establish baseline)
Never skip running tests after each logical step

Process

Run tests — record baseline pass/fail count
Identify specific structural problem to fix (one at a time)
Make the minimal structural change
Run tests — must still pass at baseline count
Document what changed and why
Repeat for next problem if in scope

Output format

Baseline: [N tests passing] Change: [what was changed, in one sentence] Why: [structural problem it solves] After: [N tests still passing]

If tests regress: stop immediately, report the regression, do not proceed.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most refactoring skills give in 243 tokens

Counted across 521 of the 525 authors here whose files we hold, read 2026-08-07

Run tests after each changein 52 of 521
Run the full test suite after each stepin 32 of 521
Preserve external behaviorin 27 of 521, across 24 files
Remove dead codein 26 of 521
Write tests before refactoringin 26 of 521, across 25 files
Make small incremental changesin 19 of 521, across 16 files
Break the implementation into tiny commitsin 18 of 521, across 5 files
Ask the user about alternative optionsin 17 of 521, across 4 files
Create a GitHub issue with the planin 17 of 521, across 4 files
Explore the repository to verify assertionsin 17 of 521, across 4 files
Interview the user about the refactorin 16 of 521, across 3 files
Check the codebase for test coveragein 16 of 521, across 3 files

Said here and by no other author read

record baseline test pass count
fix one structural problem at a time
document what changed and why
stop immediately if tests regress

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.