From forge3
Analysis phase for /assist:health-check command - scores each component
How this skill is triggered — by the user, by Claude, or both
Slash command
/forge3:skills/health-analyze-skillThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The second phase of the `/assist:health-check` workflow. Performs detailed health analysis and scoring of each component.
The second phase of the /assist:health-check workflow. Performs detailed health analysis and scoring of each component.
Analyze each component's quality, completeness, and suitability, producing a health score.
| Factor | Points |
|---|---|
| File exists in correct location | 5 |
| Valid YAML frontmatter | 5 |
| All required fields present | 10 |
| Optional fields present | 5 |
| Factor | Points |
|---|---|
| Non-trivial content length | 10 |
| Clear formatting | 5 |
| Proper sections | 5 |
| No placeholder text | 5 |
| Factor | Points |
|---|---|
| All references valid | 10 |
| Appropriate tool selection | 10 |
| No orphaned components | 5 |
| Factor | Points |
|---|---|
| Component type matches purpose | 10 |
| Appropriate for Claude Code plugin | 10 |
| Follows best practices | 5 |
| Score | Grade | Meaning |
|---|---|---|
| 90-100 | A | Excellent - Production ready |
| 80-89 | B | Good - Minor improvements possible |
| 70-79 | C | Acceptable - Should address issues |
| 60-69 | D | Needs work - Multiple issues |
| < 60 | F | Critical - Requires significant fixes |
COMPONENT: skills/router-skill
TYPE: skill
SCORES:
Structure: 22/25
Content: 23/25
References: 25/25
Suitability: 20/25
TOTAL: 90/100 (A)
ISSUES:
- None
RECOMMENDATIONS:
- Consider adding more trigger phrase variations
To proceed to aggregate phase, provide:
analyzed_count: Number of components analyzedscores: Map of component path to scoregrade_distribution: Count of A/B/C/D/F gradesnpx claudepluginhub chkim-su/forge3Audits skill quality against routing, progressive loading, and verification criteria. Produces health reports with per-skill ratings and a Gate outcome.
Audits Claude Code skills by reading SKILL.md, references, scripts; evaluates 12 best-practice dimensions, scores 0-24, grades A-F, suggests top fixes, supports batch mode.
Evaluates Claude skills across description quality, content organization, writing style, and structural integrity. Generates weighted scores, letter grades, and improvement plans.