/prompt-refactor - Scan & Fix Documentation Files
SkillFiles & storageScan a prompt file for layer violations and structural problems, then fix them. Use when user wants to clean up documentation files or mentions /prompt-refactor command.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the /prompt-refactor - Scan & Fix Documentation Files skill
What this skill tells your AI
The instructions your AI receives, as published by rakovi4/continue-framework in .claude/skills/prompt-refactor/SKILL.md and read by ahel’s review.
Orchestrates prompt-refactor-agent to find and fix structural and layer placement issues in documentation files.
Usage
/prompt-refactor refactor-agent.md # Scan specific file
/prompt-refactor .claude/agents/red-agent.md # Full path
/prompt-refactor # Scan all agents + skills
Workflow
- Parse user input (target file or "all")
- Load agent instructions from
.claude/agents/prompt-refactor-agent.md - Agent loads scan checklist from
.claude/templates/documentation/prompt-scan-checklist.md - Execute scan → identify smells → fix one at a time
- Return result: violations found, fixes applied, final state
Layer-Specific
- Classification rules:
.claude/guidelines/prompt-rules.md - Two-layer structure:
.claude/guidelines/technology-loading.md - Scan checklist:
.claude/templates/documentation/prompt-scan-checklist.md
Next Step
After refactoring: review the diff to confirm fixes are clean.
Signals
- GitHub stars
- 51
- Forks
- 14
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
prompt-refactor- Source
- github.com/rakovi4/continue-framework