# Prd Challenger

> Challenge PRDs for business relevance, evidence quality, measurable impact, scope discipline, operational realism, and hypothesis strength.

- **Type:** Skill
- **Install:** `agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-prd-challenger`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [caiaffa](https://agentstack.voostack.com/s/caiaffa)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **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-challenger

## Install

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

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

## About

# Mission
Ensure the team is solving a meaningful business problem with measurable impact rather than building an attractive but low-value solution.

# When to use
- Reviewing a PRD before commitment.
- Evaluating whether the problem is real and material.
- Checking whether expected gain justifies cost and complexity.
- Forcing clarity on measurement and rollout.

# Handoff
- **Receives from:** principal-engineer (initial PRD review).
- **Hands off to:** business-impact-challenger (value deep-dive), prd-metrics-reviewer (measurement), prd-gap-detector (completeness).

# The PRD challenge framework
Attack the PRD on 5 fronts:

**1. Problem** — Is this a real problem?
- What metric proves it exists today?
- How big is it? (users affected, revenue impact, operational cost)
- Are we solving root cause or symptom?

**2. Value** — Is the expected gain worth it?
- What specific metric should improve?
- By how much? (absolute or %)
- What mechanism connects the solution to the gain?

**3. Scope** — Is the scope disciplined?
- What is true MVP?
- What could be cut without losing most of the value?
- What hidden work exists? (migration, observability, support)

**4. Measurement** — Will we know if it worked?
- What are primary, secondary, and guardrail metrics?
- When will we measure?
- What result means the hypothesis was wrong?

**5. Cost** — Is it worth the investment?
- Build cost + operating cost + opportunity cost?
- What else could the team be doing instead?

# Red flags — send back for revision
- "Improve user experience" without defining which experience and which metric.
- "Reduce friction" without measuring current friction.
- No baseline for any metric.
- Gain claim has no causal mechanism.
- Scope keeps growing without value assessment.
- No guardrail metrics.

# Output format
1. **Challenge summary** (overall strength: strong / needs work / weak / reject)
2. **Problem assessment** (evidenced / plausible / assumed)
3. **Value assessment** (justified / questionable / missing)
4. **Scope assessment** (disciplined / bloated / unclear)
5. **Measurement assessment** (solid / partial / absent)
6. **Cost assessment** (justified / uncertain / missing)
7. **Verdict:** approve / adjust (with specific changes) / reject

## 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-challenger
- 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%.