C-Level Advisory PostmortemAnalysisLearning

Executive Mentor — Postmortem

Honest analysis of what went wrong and why.

$skillfish add ~skills/executive-mentor-postmortem

Real Examples Get Started Models & Context

Real Conversations

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

You

We launched our enterprise tier 3 months ago after 9 months of development. We have 2 customers on it (target was 12). The feature set is solid but we priced at $48K ACV without doing enough customer discovery. Sales team resisted it from day one — they said 'customers won't pay that.' I ignored them. Help me do an honest postmortem.

Agent

A good postmortem separates causation from correlation and identifies system failures, not just the final mistake. Let me work through this with you.

What actually happened (the causal chain):

9 months of development without customer validation of price point
Sales team flagged resistance; you overrode it
Launched at $48K ACV; market accepted 2 of 12

But the root cause is earlier. When did you set the $48K price? What was the logic? If it was margin math ("we need $48K to make the economics work"), that's a pricing-from-cost error. If it was competitive benchmarking ("Ironclad charges $60K"), that ignores your brand position as a newer entrant. If it was investor pressure ("you should be at enterprise price points"), that's strategy captured by optics.

The sales team signal: This is the part that stings most in a good postmortem. The sales team told you the market wouldn't pay that price. You had a data point from the people closest to the market, and you discounted it. Why? Possible answers:

You didn't trust their judgment on strategic pricing (understandable but needs examination)
You thought they were afraid of selling premium (possible, but did you test it?)
You needed the $48K price to make the business model work and didn't want to confront what $24K ACV meant for your unit economics

The honest question: If you'd done 10 customer discovery calls about willingness-to-pay before finalizing the price, what would you have heard?

System fixes (not just individual lessons):

Price validation before development commitment, not after
A formal "war game" where sales presents their strongest objection case to any new product initiative
A definition of what constitutes enough customer signal to override sales pushback

The 2 customers you have: That's your beachhead. What do they have in common? Build the enterprise motion around those profiles.

You

We lost a $2M enterprise deal at final contract stage after 8 months of sales process. The deal was 60% of our annual target. The customer cited 'strategic direction change' but our champion told us off the record it was a security review failure — they found gaps in our SOC 2 scope. Do the postmortem with me.

Agent

8 months and $2M in the final stage is a significant failure, and the security gap is only the proximate cause. Let me help you find the systemic failures.

The causal chain:

Month 1–8: Sales process progressing normally
Security review triggered (month 6–8, typical for enterprise contracts)
SOC 2 scope gaps identified
Deal killed

Root cause analysis — working backwards:

Why did the SOC 2 gap matter at month 8 instead of month 2? Enterprise security reviews typically happen after contract negotiation, but a good discovery process surfaces security requirements early. Did your AE ask: "What does your security review process look like and what will they need to approve a SaaS vendor?" in the first 30 days? If not, this is a qualification gap, not a security gap.

What was the SOC 2 scope gap specifically? This matters. Common failures:

Data retention policies not formalized
Subprocessor list not maintained (critical for EU data)
Penetration test not completed in the required window
Encryption standards documentation inadequate

Each has a different fix. "Improve security" is too vague to act on.

The champion told you off the record: This person is a signal. They were invested in the deal, they're telling you the real reason. Have you had a proper close-loss call with them to understand the full scope of the finding? That call is more valuable than the deal itself — it tells you exactly what every other enterprise deal will hit.

Systemic fix: Add a "security qualification" step at deal stage 2 (after initial interest, before significant investment). A 1-page security questionnaire sent to the champion: "Can you share your standard vendor security requirements? We want to get ahead of any gaps now." This surfaces blockers at month 1, not month 8.

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 — Postmortem?

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

$skillfish add ~skills/executive-mentor-postmortem

← Browse all 169 skills