skill-auditorlisted

# Skill Auditor Comprehensive audit of the skills library for quality and consistency. ## Audit Modes | Mode | Scope | Command | |---|---|---| | `skills` (default) | Public skills, commands, bundles, and catalog sync | Follow the categories below | | `routines` | Local Claude scheduled tasks and Codex automations | `python3 scripts/audit-routines.py` | Routine mode follows `.agents/memory/system/routine-standards.md`. It is read-only: detect normalized duplicate bodies and prompt-level model, effort, schedule, cwd/workspace/worktree, and environment leakage. Report source identifiers and field names only; never print prompt bodies, environment values, or TOML values. Use `--show-paths` only when the caller explicitly wants local paths in the report. ## Audit Categories ### 1. Duplicate Detection Find skills that overlap and should be consolidated: - Compare descriptions for semantic similarity - Check for skills with near-identical `when_to_use` triggers - Flag naming collisions (e.g., `react-patterns` vs `react-refactor`) ### 2. Spec Compliance For each SKILL.md, check: - Frontmatter follows Agent Skills spec (see `.agents/memory/system/skill-standards.md`) - `version`/`tags` inside `metadata:` block, not top-level - No forbidden fields (`auto_activate`, `auto_trigger`, `risk`) - `metadata.tags` is a comma-separated string, not YAML list - No harness-owned execution parameters in reusable content; apply `.agents/memory/system/execution-boundary.md` to skills, co