select-refactor

Analyzes a candidate shortlist and writes a decision.md with the chosen refactor.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Read a refactor candidate shortlist, pressure-test the leading options with cheap repo evidence, and lock the final refactor choice in a work item before planning. Use when the user wants the best refactor chosen from a shortlist, wants the current favorite challenged, or wants a final decision before creating an ExecPlan.

Core Features & Use Cases

  • Read the candidate brief and current metadata to extract the candidate set, provisional leader, assumptions, falsifiers, cheapest probes, and constraints.
  • Run an adversarial challenge pass to examine potential weaknesses and alternative runners-ups.
  • Perform a cheap evidence round with repo probes before committing to a decision.
  • Write a decision.md with the chosen refactor, rationale, and success criteria, and update metadata accordingly.

Quick Start

Provide the current candidate shortlist and let this skill test, challenge, and lock the winning refactor decision.

Frequently Asked Questions about select-refactor

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

FAQPage Schema
How do I lock a final decision from a list of refactor candidates?

To lock a final decision from refactor candidates, provide your shortlist to pressure-test leading options against cheap repo evidence, then record the chosen refactor and rationale in a decision.md file before planning.

What is the best way to challenge a provisional refactor leader before planning?

The best way to challenge a provisional refactor leader is to run an adversarial pass that examines potential weaknesses and alternative runners-up, validating assumptions with cheap repo probes before committing to a work item.

How do I evaluate refactor risks using repository evidence?

You evaluate refactor risks using repository evidence by running cheap repo probes against your candidate shortlist to surface falsifiers and constraints, ensuring the chosen refactor is tested before updating metadata.

Do I need a working repository workspace to select a refactor?

Yes, you need a working repository workspace to select a refactor, because the workflow requires access to candidate metadata and the ability to run cheap repo probes to gather evidence before locking the decision.

When should I not use an adversarial challenge pass for refactoring?

You should not use an adversarial challenge pass when you lack a defined candidate shortlist or provisional leader, as the workflow requires existing candidate metadata to extract assumptions and falsifiers for evaluation.