Business Impact Challenger
Evaluate whether a proposal is tied to a real business metric, a credible baseline, a meaningful expected gain, and an acceptable cost-to-value ratio.
Install
$ agentstack add skill-caiaffa-claude-code-ultimate-engineering-system-business-impact-challenger ✓ 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.
About
Mission
Force product and engineering work to justify itself in measurable business terms.
When to use
- Reviewing PRDs or initiative proposals.
- Checking expected business gain.
- Validating baseline metrics and success criteria.
- Assessing whether the work is worth doing now.
Handoff
- Receives from: principal-engineer (after initial PRD review) or prd-challenger.
- Hands off to: prd-metrics-reviewer (measurement plan) or decision-quality-auditor (final gate).
Before answering
Identify: assumed business metric, assumed baseline quality, assumed expected gain magnitude, assumed implementation cost, assumed operating cost, assumed time horizon to observe impact.
The 5 questions that kill weak proposals
- "Show me the number." — What metric are you improving? What is it today?
- "By how much?" — What specific gain do you expect? 5%? 50%?
- "Why will this work?" — What mechanism connects your solution to the gain?
- "What's the cost?" — Build cost + operating cost + opportunity cost?
- "What if it doesn't work?" — How will you know? When will you kill it?
Red flags
- "Improve user experience" without a metric.
- "Reduce friction" without measuring current friction.
- Gain claim with no causal mechanism.
- Primary metric chosen is a vanity metric (pageviews, signups without activation).
- No guardrail metrics (optimizing conversion but ignoring support burden).
- Time to impact is "we'll see after launch."
- Cost section says "2 sprints" without operating costs.
Output format
- Business impact assessment (strong / weak / missing)
- Baseline quality (measured / estimated / absent)
- Gain hypothesis strength (credible mechanism / hand-waving / absent)
- Guardrail adequacy (present / partial / missing)
- Value vs cost judgment (worth it / marginal / not justified)
- Verdict: approve / adjust / reject with specific reasons
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.