Refactor
Safe refactoring in small verifiable steps; no scope creep outside handoff or explicit request.From its SKILL.md
npx -y skills add LaProgrammerie/ai-engineering-core --skill refactorAssembled 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, 266 tokens by cl100k_base, as published. Nobody here has run it
Refactor (global)
Objective
Improve structure and readability without changing observable behaviour, in verifiable steps.
When to use
- Hard-to-follow, duplicated, or overly coupled code
- Before adding a feature on brittle structure
Expected inputs
- Scope (files, module, or symptom)
- Tests or verification commands (if none, say so)
- Constraints (public API, backward compatibility, performance)
Scope discipline
- Do not refactor outside the defined scope (handoff, spec slice, or explicit user request).
- If broader cleanup is desirable, list it as follow-ups rather than doing it silently.
Steps
- Clarify goal: readability, layering, targeted performance — do not mix goals in one step.
- Phased plan if scope is large — propose before editing.
- Small steps: one transformation at a time; run tests / checks after each step when possible.
- Preserve public contracts unless a breaking change is explicitly requested (then document migration).
- Remove dead code only when sure it is unused.
Output format
- Ordered plan → changes made or proposed
- Risks and rollback lever
- Remaining work if partial
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.