skill-enhancerlisted

# Skill Enhancer **Purpose**: This meta-skill analyzes other skills for compliance with TDD, CSO, and Script-First standards, guiding the agent through upgrades. ## 1. Red Flags (Anti-Rationalization) **STOP and READ THIS if you are thinking:** - "I'll just add the sections blindly" -> **WRONG**. You must understand *why* the skill fails before fixing it. - "The description is close enough" -> **WRONG**. It must start with "Use when". - "Examples are optional" -> **WRONG**. "Rich Skills" mandate examples. - "It's just a small 20-line example" -> **WRONG**. Inline blocks > 12 lines are prohibited. Extract them. - "I'll instruct the agent to parse the file line-by-line in text" -> **WRONG**. Use "Script-First". ## 2. Capabilities - **Audit**: Detect gaps (missing Red Flags, oversized inline blocks, poor CSO, weak language) using `analyze_gaps.py`. - **Rule scoping**: the analyser reads prose, not code. Fenced blocks and inline code spans are masked before the prose rules run, `[--flag VALUE]` is CLI usage notation rather than an unfilled slot, and `/tmp/out.pdf` in a reproducible command is not the absolute-path anti-pattern — only a path naming one machine or one user's account is (WI-033). - **Execution Policy Audit**: Detect missing `Execution Mode`, `Script Contract`, `Safety Boundaries`, and `Validation Evidence` sections. - **Security Remediation**: Fix vulnerabilities flagged by `skill-validator` (e.g., `curl | bash`, secrets, weak permissions). - **Plan**: Pr