Verify phase
Skill that gives AI coding agents persistent memory and quality enforcementFrom the repository description
npx -y skills add mattjaikaran/meridian --skill verify-phaseAssembled 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
2.3 KB, 561 tokens by cl100k_base, as published. Nobody here has run it
/meridian:verify-phase -- Nyquist Compliance Check
Check VALIDATION.md frontmatter presence and currency for phases. Does NOT re-run tests -- only reads existing frontmatter.
Procedure
Step 1: Check compliance (all phases or specific phase)
If a phase number argument is provided, check only that phase. Otherwise check all phases.
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from pathlib import Path
from scripts.nyquist import parse_validation_md
phases_dir = Path('.planning/phases')
results = []
for phase_dir in sorted(phases_dir.iterdir()):
if not phase_dir.is_dir():
continue
parsed = parse_validation_md(phase_dir)
if parsed is None:
continue
results.append({
'phase': parsed.get('phase', '?'),
'slug': parsed.get('slug', phase_dir.name),
'compliant': parsed.get('nyquist_compliant', False),
'status': parsed.get('status', 'unknown'),
'wave_0': parsed.get('wave_0_complete', False),
'validated_at': parsed.get('wave_0_validated', 'never'),
'failure_reason': parsed.get('failure_reason'),
})
print(json.dumps(results, indent=2))
"
Step 2: Display Results
Format output as a table:
| Phase | Name | Status | Compliant | Issues |
|---|---|---|---|---|
| 1 | database-foundation | validated | [x] | -- |
| 2 | error-infrastructure | failed | [ ] | Tests failed |
Rules:
- Compliant phases: show
[x]checkmark - Non-compliant phases: show
[ ]with reasonstatus: draft-> "Not validated yet"status: failed-> "Tests failed" (include failure_reason if present)
- Non-compliant phases are warnings, not errors (per project decision)
Step 3: Offer backfill (if gaps found)
If any phases are non-compliant, suggest running the backfill command:
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from pathlib import Path
from scripts.nyquist import backfill_validation
results = backfill_validation(Path('.planning'))
print(json.dumps(results, indent=2))
"
This will re-run tests for all non-compliant phases and update their VALIDATION.md frontmatter with actual results.
Output
Summary table of phase compliance status. Non-compliant phases are warnings, not blockers.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.