y-score-readiness
Skill0 starsChanged 5 months agoMITView on GitHub
Score a PRD or pilot against the 7-dimension Y-Score launch-readiness rubric (problem clarity, target user, success metric, constraints, compliance, eval plan, rollback). Returns a 0-100 score plus per-dimension findings and a go / no-go recommendation. Use when a PO is deciding whether a pilot is ready to launch, especially in BFSI / healthcare / regulated domains.
In this repository6 other files it gives its agents.
- agents.mdAGENTS.md
- AGENTS.mdAGENTS.md
- pptx-officialSkill
- prd-to-sdlcSkill
- cavemanSkill
- productowner-skillSkill
The file
Files
y-score-readiness
The PO gate that runs before prd-to-sdlc produces any artifacts. Refuses to proceed if score < 70.
When to trigger
/y-score <prd.md>- User says "is this ready to launch?", "readiness check", "score this PRD"
- Auto-invoked by
prd-to-sdlcorchestrator stage 1
The 7 dimensions
| # | Dimension | Weight | Anchor for full marks |
| 1 | Problem clarity | 15 | One-sentence statement, measurable, user-visible |
| 2 | Target user | 10 | Named persona + JTBD + frequency |
| 3 | Success metric | 20 | Leading + lagging metric with baseline + target |
| 4 | Constraints | 10 | Latency / cost / data residency / SLA defined |
| 5 | Compliance posture | 15 | Domain checklist done (HIPAA / PCI / GDPR / EU-AI-Act) |
| 6 | Eval plan | 20 | Golden set + judge + regression suite + drift monitor |
| 7 | Rollback plan | 10 | Kill switch + comms + data-recovery RTO defined |
Scoring
- Per dimension: 0 (missing) / 50 (partial) / 100 (full)
- Weighted total = sum(dim_score × weight) / 100
- Gate: total ≥ 70 → proceed. < 70 → return findings, block downstream stages.
Output format
{
"score": 78,
"verdict": "go",
"dimensions": {
"problem_clarity": {"score": 100, "note": "..."},
"target_user": {"score": 50, "note": "Persona named but JTBD missing"},
...
},
"blockers": [],
"recommendations": ["Add LLM-as-judge calibration step to eval plan"]
}Domain-aware compliance dimension
Compliance dimension auto-checks against domain:
bfsi→ PCI-DSS, FATF, BSA, fair-lending, EU-AI-Act high-riskhealthcare→ HIPAA, FHIR consent, FDA SaMD class (if applicable)eu→ GDPR DPIA, EU-AI-Act risk tiergeneric→ baseline SOC 2 + privacy review
Author
Vignesh AIPM — distilled from 10 years shipping AI in regulated BFSI / healthcare environments.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

