# Prd Metrics Reviewer

> Review PRD metrics for baseline quality, success criteria, guardrails, time horizon, and post-launch measurement credibility.

- **Type:** Skill
- **Install:** `agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-prd-metrics-reviewer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [caiaffa](https://agentstack.voostack.com/s/caiaffa)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [caiaffa](https://github.com/caiaffa)
- **Source:** https://github.com/caiaffa/claude-code-ultimate-engineering-system/tree/main/skills/prd-metrics-reviewer

## Install

```sh
agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-prd-metrics-reviewer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## 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
1. Is the primary metric actually measuring the business outcome, or a proxy?
2. Is the baseline stable or noisy? (seasonal? trending? high variance?)
3. Can the target realistically be achieved by this intervention?
4. Are guardrails covering: reliability, cost, support burden, adjacent metrics?
5. Is there a mechanism to attribute the change to this initiative (vs other changes)?
6. What's the measurement lag? (real-time? daily? monthly? quarterly?)
7. 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
1. **Metrics quality:** solid / partial / weak / missing
2. **Primary metric assessment** (appropriate? measurable? timely?)
3. **Baseline quality** (measured / estimated / absent)
4. **Target quality** (realistic / aspirational / unfounded)
5. **Guardrail gaps** (what could get worse unnoticed)
6. **Measurement plan** (who measures, when, how, what triggers action)
7. **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](https://github.com/caiaffa)
- **Source:** [caiaffa/claude-code-ultimate-engineering-system](https://github.com/caiaffa/claude-code-ultimate-engineering-system)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-caiaffa-claude-code-ultimate-engineering-system-prd-metrics-reviewer
- Seller: https://agentstack.voostack.com/s/caiaffa
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.