Refactor

SkillAI & models

Lets your agent review code for quality problems and suggest refactoring improvements.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Refactor skill

About this skill

Invoke IMMEDIATELY via python script when user requests refactoring analysis, technical debt review, or code quality improvement. Do NOT explore first - the script orchestrates exploration.

What this skill tells your AI

The instructions your AI receives, as published by solatis/claude-config in skills/refactor/SKILL.md and read by ahel’s review.

When this skill activates, IMMEDIATELY invoke the script. The script IS the workflow.

Invocation

Argument	Required	Description
`--step`	Yes	Current step (starts at 1)
`--n`	No	Number of categories to explore (default: 10)

Do NOT explore or analyze first. Run the script and follow its output.

Determining N (category count)

Default: N = 10

Adjust based on user request scope:

SMALL (single file, specific concern, "quick look"): N = 5
MEDIUM (directory, module, standard analysis): N = 10
LARGE (entire codebase, "thorough", "comprehensive"): N = 25

The script randomly selects N categories from the 38 available code quality categories defined in conventions/code-quality/.

Signals

GitHub stars: 911
Forks: 130
Last commit: Mar 2026
Hacker News mentions: 20

Advanced

Item type: skill
Key: refactor-solatis
Source: github.com/solatis/claude-config

github.com/solatis/claude-config

Refactor

What this skill tells your AI

Invocation

Determining N (category count)

Signals

Related picks