From sd0x-dev-flow
Validates skills using automated lint script and checklists for frontmatter, routing cues, structure, output definitions, and cross-references. Outputs health reports with per-skill ratings and gating.
npx claudepluginhub sd0xdev/sd0x-dev-flow --plugin sd0x-dev-flowThis skill is limited to using the following tools:
- Keywords: skill health, skill audit, skill lint, check skills, skill quality, validate skills
Audits Claude Code skills for structure compliance, triggering accuracy, instruction quality, and best practices. Scores 0-100 with prioritized improvement recommendations.
Lints Claude skills for errors like broken symlinks and missing SKILL.md/frontmatter, warnings on description quality and fields, plus info on best practices. Includes bash script.
Audits SKILL.md files against unified AgentOps template with 15 checks: 7 structural via heal-skill and 8 content checks. Use for quality reviews before skill deployment.
Share bugs, ideas, or general feedback.
/codex-review-fast)/codex-review-doc)skill-creator plugin, external)/claude-health)Skills are on-demand context packages. Their value comes from routing precision (right skill triggers at right time) and context efficiency (minimum tokens for maximum capability). A poorly routed skill wastes context on every mismatch; a well-routed skill transforms a generalist into a specialist at exactly the right moment.
Run automated lint → Review manual dimensions → Produce integrated report → Gate
node skills/skill-health-check/scripts/skill-lint.js --fix-hint
Script I/O contract:
| Parameter | Description |
|---|---|
--skills-dir <path> | Skills directory (default: ./skills) |
--agents-dir <path> | Agents directory (default: ./agents) |
--json | Output JSON instead of markdown |
--fix-hint | Include fix suggestions |
| Exit 0 | All pass |
| Exit 1 | Warnings only (P2) |
| Exit 2 | Errors found (P0/P1) |
Per-skill checks (11 items):
| # | Check | Severity | Criteria |
|---|---|---|---|
| 1 | Frontmatter exists | P0 | name + description required |
| 2 | Routing signature | P1 | Description has at least 2 of 3 routing cues (Use/Avoid/Output); 0 cues = P1, 1 cue = P2 |
| 3 | When NOT section | P1 | Body has "When NOT to Use" heading |
| 4 | Output section | P2 | Body defines expected deliverable |
| 5 | Verification section | P2 | Body has verification checklist |
| 6 | References routing | P2 | Each reference file mentioned in body |
| 7 | Scripts contract | P2 | Each script filename referenced in SKILL.md body |
| 8 | Line count | P2 | Warning >150, flag >250 |
| 9 | Agent entitlement | P2 | Body describes Agent() dispatch but allowed-tools lacks Agent |
| 10 | Task entitlement | P2 | Body describes Task() dispatch but allowed-tools lacks Task |
| 11 | Cross-skill ref path | P1 | Bare ref paths not found locally but existing in another skill → must use @skills/<parent>/ prefix |
Cross-skill checks (3 items):
| # | Check | Severity | Criteria |
|---|---|---|---|
| 12 | Description overlap | P2 | Jaccard similarity >60% flagged |
| 13 | Agent ref validity | P1 | subagent_type references in skills must exist in agents/ |
| 14 | Agent tools syntax | P2 | Agent .md tools field uses canonical format (ToolName or Bash(<prefix>:*)) |
Read flagged skills and evaluate:
| Dimension | Question | Rating |
|---|---|---|
| Why > What | Does skill explain underlying principles, not just steps? | ⭐1-5 |
| Scope fitness | Is the skill focused? Could it be split? | ⭐1-5 |
| Progressive loading | Is heavy content in references/, not inline? | ⭐1-5 |
| Routing precision | Would a user's request unambiguously trigger this skill? | ⭐1-5 |
Only run Step 2 when user explicitly requests deep audit. Default: Step 1 only.
# Skill Health Check Report
## Summary
| Metric | Value |
|--------|-------|
| Skills scanned | N |
| Checks passed | N |
| P0 (Must Fix) | N |
| P1 (Should Fix) | N |
| P2 (Suggestion) | N |
## Per-Skill Results
| Skill | Routing | When-NOT | Output | Verification | Refs | AgEnt | TskEnt | Lines | Status |
|-------|---------|----------|--------|--------------|------|-------|--------|-------|--------|
| name | ✅/🟡/⚪ | ... | ... | ... | ... | ✅/⚪ | ✅/⚪ | N | ✅/🟡/⚪/🔴 |
## P0 (Must Fix)
- **skill-name**: Issue → Fix recommendation
## P1 (Should Fix)
- **skill-name**: Issue → Fix recommendation
## P2 (Suggestion)
- **skill-name**: Issue → Fix recommendation
## Gate: ✅ All Pass / ⛔ N issues need fixing
references/routing-signature-guide.md — How to write effective routing signatures (read when fixing P1 routing issues)Input: /skill-health-check
Action: Run skill-lint.js → Output markdown report + Gate
Input: /skill-health-check --deep
Action: Run skill-lint.js → Manual review of flagged skills → Integrated report
Input: Are my skills well-designed?
Action: Trigger health check → Report + improvement suggestions