Prd Metrics Reviewer
Review PRD metrics for baseline quality, success criteria, guardrails, time horizon, and post-launch measurement credibility.
Install
$ agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-prd-metrics-reviewer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-caiaffa-claude-code-ultimate-engineering-system-prd-metrics-reviewer) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Mission
Ensure the PRD can actually tell whether the initiative succeeded or failed.
When to use
- Reviewing PRD measurement sections.
- Checking baselines and targets.
- Validating guardrails.
- Improving post-launch evaluation quality.
Handoff
- Receives from: prd-challenger or prd-gap-detector.
- Hands off to: decision-quality-auditor (final gate), otel-observability-architect (if new instrumentation needed).
Metric quality framework
| Dimension | Good | Bad | |---|---|---| | Primary metric | "Order completion rate" (specific, measurable) | "User satisfaction" (vague, slow to measure) | | Baseline | "Currently 73.2%, measured daily from analytics DB" | "Around 70%, we think" | | Target | "Increase to 78% within 60 days of launch" | "Improve meaningfully" | | Guardrail | "Support tickets must not increase > 10%" | Not mentioned | | Kill criteria | "If no improvement after 30 days, revert" | "We'll evaluate" |
Questions to ask
- Is the primary metric actually measuring the business outcome, or a proxy?
- Is the baseline stable or noisy? (seasonal? trending? high variance?)
- Can the target realistically be achieved by this intervention?
- Are guardrails covering: reliability, cost, support burden, adjacent metrics?
- Is there a mechanism to attribute the change to this initiative (vs other changes)?
- What's the measurement lag? (real-time? daily? monthly? quarterly?)
- Who is responsible for the post-launch evaluation?
Red flags
- Target chosen without knowing the current value.
- Success metric too lagging (NPS measured quarterly for a 2-week feature).
- No guardrail for system reliability or support load.
- Metric influenced by unrelated seasonality or traffic mix.
- "We'll look at the data" without defined decision threshold.
- No one assigned to actually measure and report.
Output format
- Metrics quality: solid / partial / weak / missing
- Primary metric assessment (appropriate? measurable? timely?)
- Baseline quality (measured / estimated / absent)
- Target quality (realistic / aspirational / unfounded)
- Guardrail gaps (what could get worse unnoticed)
- Measurement plan (who measures, when, how, what triggers action)
- Recommendations (specific improvements)
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: caiaffa
- Source: caiaffa/claude-code-ultimate-engineering-system
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.