C-Level Advisory Stress TestAssumptionsValidation

Executive Mentor — Stress Test

Business assumption stress testing and validation.

$skillfish add ~skills/executive-mentor-stress-test

Real Examples Get Started Models & Context

Real Conversations

See how the Executive Mentor — Stress Test skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

My Series B model shows $8M ARR in 24 months from $2.2M today. Key assumptions: 3 new AEs hired in Q1 ramping to $200K quota, 2x marketing budget generating 150 MQLs/month, NRR improving from 92% to 108%. Stress test this for me.

Agent

Running a structured stress test across your three key assumption clusters.

Cluster 1 — AE ramp and quota attainment: Base assumption: 3 AEs × $200K quota × 4 quarters = $2.4M gross new ARR from new AEs. Stress scenario: SaaS AE average quota attainment is 68%. Ramp takes 9–12 months for enterprise AEs. Realistic contribution in 24 months from Q1 hires: $200K × 68% attainment × 1.5 effective years (accounting for ramp) × 3 AEs = $612K gross new ARR, not $2.4M. That's a $1.8M gap in your model from this assumption alone.

Cluster 2 — Marketing MQL scaling: Base assumption: 2x budget → 150 MQLs/month → pipeline to support $8M ARR. Stress scenario: Marketing channels exhibit diminishing returns. If your current budget generates 60 MQLs/month, doubling spend rarely generates exactly 2x MQLs — typically 1.5x–1.8x. At 1.6x, you get 96 MQLs/month, not 150. At your current conversion rates (MQL → close), that's a 35% reduction in revenue contribution from this channel. Ask: What's your empirical CPL at current spend, and what evidence do you have that it holds at 2x budget?

Cluster 3 — NRR improvement (92% → 108%): This is your most optimistic and least supported assumption. A 16-point NRR improvement requires either significant expansion revenue (upsell/cross-sell motion you may not have built) or a 50%+ reduction in gross churn. What specifically changes between now and month 24 that drives this?

Downside scenario: AE attainment at 68%, MQL scale at 1.6x, NRR improves modestly to 98%. Result: $4.8M ARR at month 24, not $8M.

Recommendation: Build three cases (base/upside/downside) with explicit sensitivities. Present the downside to investors before they find it.

You

We've decided our ICP is 'Head of Operations at SaaS companies, 50-200 employees.' We've built our entire GTM around this. Before we invest $400K in marketing and 3 sales hires, stress-test the ICP assumption. We have 90 customers today.

Agent

ICP assumptions are the highest-leverage thing to stress test before a $400K GTM bet. Here's the framework.

Test 1 — Do your best customers actually match this ICP? Pull your top 20 customers by (a) highest ACV, (b) lowest churn risk, (c) fastest time-to-value, and (d) highest NPS. Map each against your ICP definition. The question isn't what you think your ICP is — it's what your actual best customers reveal.

Common finding: the buyers are heads of operations, but the actual champions (people who pushed hardest for the purchase) are one level below — operations managers or project leads. This matters for your outbound targeting.

Test 2 — Is "50-200 employees" the right size band? Run this analysis on your 90 customers: what's the ACV distribution by company size? If customers at 50–100 employees pay $4K ACV but customers at 150–300 employees pay $12K ACV, your ICP size band is leaving significant revenue density on the table by targeting the lower end.

Test 3 — How do you actually reach a "Head of Operations"? LinkedIn has ~180,000 people with "Head of Operations" titles at SaaS companies 50–200 employees in the US. But what fraction of those have the problem you solve? What's your empirical win rate on inbound vs. outbound to this title? If your inbound win rate for this title is 22% but your outbound win rate is 4%, you have an ICP-channel fit problem.

Test 4 — What does the losing pattern look like? Who did you lose to? If you lose consistently to a specific competitor in the 50–100 employee band, you may be fighting on their home turf. Your wins may be concentrated in 150–200 employees without you noticing it.

Recommendation before the $400K bet: Run a 30-day ICP validation sprint. Interview 10 of your best customers and 5 of your most qualified recent losses. Map the findings against your ICP definition before committing to GTM investment.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best

Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2

Good

Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only

32K+ Skill + conversation

100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Executive Mentor — Stress Test?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

$skillfish add ~skills/executive-mentor-stress-test

← Browse all 169 skills