code-writing-guide Audit report.

Warnings

• The frontmatter uses a YAML block scalar for `description` (`>-`), but the parsed metadata shows the description as `>-`, so skill catalogs using a simple frontmatter parser will display no useful description.
• The skill assumes `unity_play_control`, Rider MCP refactoring tools, and the `edit-scene` skill are available, but it does not list these as prerequisites or define fallback behavior when they are missing.
• Resource paths use `${CLAUDE_SKILL_DIR}` with no mention of how that variable is set or what to do if it is unavailable, which may reduce portability across agent environments.
• Low GitHub adoption signal
• Quality score needs review
• GitHub adoption: 19 GitHub stars
• Stars/forks activity: 19 stars, 3 forks; issue activity unavailable in current metadata
• README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context

Method

This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.