Utility Pm Skill Validate

This is the linter you run before you ship a pm-skills skill. It runs two tiers of checks: structural rules that mirror CI (frontmatter completeness, naming conventions, file presence) and quality heuristics assessed by the LLM (does the example match the template, are checklist items actually testable, did you leave scaffolding placeholders behind). You get a structured report with pass/fail/warn findings that you can scan yourself or feed directly into utility-pm-skill-iterate to fix what's broken. Use it after building a new skill, after manual edits, or in batch mode to audit the whole library when conventions change. The quality checks reflect what v2.8 skills actually look like in the wild, not aspirational standards, which makes the feedback grounded and actionable.

skills.sh installs: 736
GitHub stars: 794
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add product-on-purpose/pm-skills --skill utility-pm-skill-validate --agent claude-code

Installs into .claude/skills of the current project.

Files

PM Skill Validate

This skill audits an existing pm-skills skill against the repo's structural conventions and quality criteria. It produces a validation report that a human can scan and that utility-pm-skill-iterate can consume as input.

The validator checks two tiers:

Tier 1 (Structural) - deterministic checks that mirror CI: frontmatter, naming, file presence, description word count.
Tier 2 (Quality) - LLM-assessed coherence checks: does the output contract reference the template? Is the example complete? Are checklist items testable?