fix broken claude skills

The problem

Skills often fail to trigger because of subtle frontmatter typos, vague descriptions, or invalid YAML. Manually debugging why an agent ignores a specific instruction is time-consuming and prone to trial-and-error.

What it does

• Audits SKILL.md files against official templates to find critical frontmatter and structural errors.
• Identifies hallucination risks where instructions reference non-existent scripts, files, or tools.
• Rewrites skill descriptions into high-performance, third-person trigger text for better routing.
• Provides a deploy-ready fixed file along with a severity-ranked findings report.

Why this beats prompting it yourself

General-purpose LLMs often overlook technical frontmatter requirements or silently hallucinate missing dependencies. This skill uses a specific checklist and validation script to ensure every line is load-bearing and compliant with the agent's router logic.

Use cases

• Debug a skill that is currently ignored by the agent during conversations.
• Standardize a large library of skills to ensure consistent behavior and formatting.
• Perform a pre-deployment QA check on new skills to catch silent failures before shipping.

Known limitations

This skill audits and edits file contents but does not perform filesystem operations like renaming folders without explicit confirmation.