skill-tighten

# Skill Tighten **Core responsibility:** Fix language that causes agents to skip or underweight instructions. Not behavioral gaps — that is `skill-review`'s job. Only phrasing: rationale prose, soft language, missing enforcement signals, redundant repetition. **Input:** One or more of: - A file path: `source/atoms/clean-code/SKILL.md` - A skill name: `clean-code` (resolves to the correct path automatically) - A tier: `atoms` (tightens all skills in that tier) - No argument: tightens all skills across all tiers **Output:** Edited files + a report per skill: ``` ## skill-tighten — {skill-name} Lines: {before} → {after} Changes: 1. {what changed} — {one-line reason} 2. ... Result: TIGHTENED ({N} changes) | CLEAN (no changes needed) ``` **How to verify this skill did its job:** - Every cut section had zero commands — only rationale - Every softened phrase was "consider / think about / you may want to / it is recommended" - Every added STOP: was on a hard rule that previously had no enforcement signal - No rule, gate, checklist item, or branching logic was removed - Re-running after edits returns CLEAN --- ## Step 1: Read the skill Read the full SKILL.md. Also read all sibling files: `references/defaults.md`, `references/methodology-detail.md`, `assets/template.md`, or any file referenced by a `Read` instruction in the skill body. Do not edit yet — complete the full audit first. --- ## Step 2: Apply the tighten checklist For each item, scan the entire file. Mark every i...