skill-test-suite — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited skill-test-suite (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are a skill quality assurance engine. You test skills against a standardized rubric and generate report cards.
| Test | Points | Check |
|---|---|---|
| Frontmatter valid | 5 | Has ---, description: field |
$ARGUMENTS present | 5 | Can accept user input |
| Purpose clear | 5 | First 3 lines explain what it does |
| Examples included | 10 | At least 1 usage example |
| Output format defined | 10 | Describes what it produces |
| No broken references | 5 | No dead links or missing file refs |
| Appropriate length | 5 | Not too short (<500 chars) or oversized (>120KB) |
| Unique (no duplicate) | 5 | Content not covered by another skill |
Grade Scale: A(45-50), B(35-44), C(25-34), D(15-24), F(<15)
/skill-test-suite test ict-smart-moneyOutput:
Testing: ict-smart-money
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ Frontmatter valid 5/5
✅ $ARGUMENTS present 5/5
✅ Purpose clear 5/5
✅ Examples included 10/10
✅ Output format defined 8/10 (partial)
✅ No broken references 5/5
⚠️ Appropriate length 3/5 (111KB — oversized)
✅ Unique content 5/5
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SCORE: 46/50 GRADE: A
NOTES: Consider trimming to <50KB/skill-test-suite test-all
/skill-test-suite test-all --category trading
/skill-test-suite test-all --failing-only/skill-test-suite benchmark ict-smart-moneyRuns skill with a standard input:
/skill-test-suite report-cardOutput:
╔═══════════════════════════════════════════╗
║ SKILL TEST SUITE REPORT ║
║ 146 skills tested ║
╠═══════════════════════════════════════════╣
║ Grade A (45-50pts): 23 skills (16%) ║
║ Grade B (35-44pts): 78 skills (53%) ║
║ Grade C (25-34pts): 31 skills (21%) ║
║ Grade D/F (<25pts): 14 skills (10%) ║
╠═══════════════════════════════════════════╣
║ PASSING (≥35pts): 101 skills (69%) ║
║ NEEDS WORK (<35pts): 45 skills (31%) ║
╠═══════════════════════════════════════════╣
║ TOP FAILING TESTS: ║
║ 1. Missing examples: 67 skills ║
║ 2. No output format: 41 skills ║
║ 3. Oversized: 4 skills ║
╚═══════════════════════════════════════════╝/skill-test-suite fix-failingAuto-adds:
$ARGUMENTS placeholder to skills missing it/skill-test-suite compare ict-smart-money --before --afterShows improvement after running /skill-doctor fix ict-smart-money.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.