find-refactor-candidates

Generate refactor candidates with assumption ledgers in a work-item directory.

83|4|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/grp06/slop-janitor --skill find-refactor-candidates
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: find-refactor-candidates
Source: https://github.com/grp06/slop-janitor/tree/main/.agents/skills/find-refactor-candidates
Command: npx skills add https://github.com/grp06/slop-janitor --skill find-refactor-candidates

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Identify materially different refactor opportunities to unlock cleaner architecture and reduce technical debt.

Core Features & Use Cases

  • Generate 3-5 materially different refactor candidates, including a do-nothing option and a minimal surgical change.
  • Produce an assumption ledger for each candidate detailing scope, evidence, risks, and payoff.
  • Create and update a work-item meta and artifacts to keep decision space explicit and auditable.

Quick Start

Create a new work-item directory under .agent/work with a slug derived from this initiative, and draft an initial candidates.md and assumption ledgers.

Frequently Asked Questions about find-refactor-candidates

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I identify refactor candidates to reduce technical debt without committing to a single plan?

To identify refactor candidates and reduce technical debt safely, generate three to five materially different options including a do-nothing baseline and a minimal surgical change. This approach keeps the decision space explicit before committing to a specific architecture plan.

What is the best way to document assumptions and risks for different architecture refactor options?

To document assumptions for architecture refactor options, create a full assumption ledger for each candidate. Each ledger details scope, evidence, risks, and payoff, keeping the decision auditable and explicit within a dedicated work-item directory.

Can I generate a minimal surgical change option when planning a boundary extraction refactor?

Yes, you can generate a minimal surgical change option specifically for boundary extraction. The process produces multiple diverse candidates, ensuring you evaluate a low-risk surgical alternative alongside more comprehensive architectural refactors.

How do I structure work-item artifacts for an architecture review to keep refactor decisions auditable?

To structure work-item artifacts for architecture reviews, create a dedicated directory using a slug derived from the initiative. Store a candidates.md file alongside individual assumption ledgers to keep the decision space explicit and auditable.

When do I need a do-nothing option in my technical debt reduction planning?

You need a do-nothing option in technical debt reduction planning when evaluating materially different refactor paths. Including a baseline do-nothing candidate alongside surgical changes and full refactors ensures you explicitly evaluate the cost of inaction before committing.