Audit uat
Skill that gives AI coding agents persistent memory and quality enforcement
npx -y skills add mattjaikaran/meridian --skill audit-uatAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, as published. Nobody here has run it
/meridian:audit-uat — Cross-Phase Verification Debt Audit
Scan all phases for outstanding verification items and produce a summary report.
Arguments
- None (scans all phases automatically)
Procedure
Step 1: Run UAT Audit
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from scripts.audit import audit_uat
result = audit_uat()
print(result['report'])
print()
print(json.dumps({
'total_debt': result['total_debt'],
'has_debt': result['has_debt'],
'phase_count': len(result['phases']),
}, indent=2))
"
Step 2: Review Results
- If
has_debtistrue, review unchecked sign-off items and pending human verifications - Each phase section shows actionable items that need attention
- Prioritize items in earlier phases (regression risk)
Step 3: Address Debt (if needed)
For each outstanding item:
- Unchecked sign-off: Verify the condition and check it off in VALIDATION.md
- Pending human verification: Perform the manual test and update VERIFICATION.md
When to Use
- Before marking a milestone complete
- During periodic quality reviews
- Before releases to verify no verification debt remains
- When onboarding to understand outstanding work
When NOT to Use
- For automated regression testing (use
/meridian:executeregression gate instead) - For individual phase verification (use
/meridian:verify-workinstead)