strategy-red-team

phuryn/pm-skills

Red-team a strategy by attacking its load-bearing assumptions and ranking the cheapest tests to validate or kill them.

What is strategy-red-team?

This skill systematically identifies and challenges the core assumptions in a PRD, roadmap, or strategy document. It steelmans each claim, ranks failure modes by impact × likelihood × cost-to-test, and returns the specific evidence to gather this week and kill criteria for each assumption. Use it to stress-test plans, pressure-test strategies, and prepare documents for executive review.

Extract load-bearing claims from a plan and separate them from cosmetic assertions
Steelman each claim before attacking it, avoiding strawman arguments
Rank failure modes by impact, likelihood, and cost-to-test to surface the highest-priority assumption to validate
Generate specific, falsifiable failure conditions rather than generic risk statements
Provide concrete evidence-gathering tasks and kill criteria for each top assumption
Identify what's well-reasoned in the plan and what gaps prevent full assessment

How to install strategy-red-team

npx skills add https://github.com/phuryn/pm-skills --skill strategy-red-team

Claude Code

Cursor

Windsurf

Cline

How to use strategy-red-team

1.Paste or reference your PRD, roadmap, or strategy document
2.The skill will extract every claim and identify which are load-bearing (plan-critical) vs. cosmetic
3.For each load-bearing claim, review the steelmanned version and the attack against it
4.Review the ranked list of kill-assumptions, ordered by impact × likelihood × cost-to-test
5.For the top 3–5 assumptions, note the specific evidence to gather this week and the kill criterion
6.Run the cheapest test listed to validate or invalidate the highest-priority assumption

Use cases

Good for

Stress-testing a product roadmap before committing resources to a quarter
Challenging core assumptions in a go-to-market strategy before launch
Preparing a PRD for executive review by surfacing the riskiest bets upfront
Validating whether a constraint (e.g., activation, retention) is actually the bottleneck
Identifying the cheapest experiment to run this week to de-risk a strategic bet

Who it's for

Product managers planning roadmaps or strategies
Executives reviewing strategic plans or major bets
Founders stress-testing business assumptions
Strategy teams preparing for board presentations
Teams running pre-launch validation cycles

strategy-red-team FAQ

How is this different from a pre-mortem?

A pre-mortem imagines the plan already failed and narrates why. A red-team attacks load-bearing assumptions now, while there's time to test them cheaply. The goal is a sharper decision, not just confidence.

What counts as a load-bearing assumption?

A load-bearing assumption is one where, if it's false, the plan dies. Cosmetic assumptions (e.g., nice-to-have features) are not worth attacking. Focus only on the claims that make or break success.

Why rank by impact × likelihood × cost-to-test?

This ranking surfaces the assumption you should test first: high-impact if wrong, plausibly wrong, and cheap to check. It prevents wasting time on low-impact or expensive-to-test risks.

What if the plan is well-reasoned on a claim?

Say so plainly. A red-team that manufactures doubt is as useless as one that rubber-stamps. Only attack genuine weaknesses; acknowledge what holds up.

Can I run this against multiple models for a second opinion?

Yes, you can ask for cross-model mode to run the same plan through another model (e.g., Gemini, Codex) and flag where they disagree. This is optional and not the default.

Full instructions (SKILL.md)

Source of truth, from phuryn/pm-skills.

name: strategy-red-team description: "Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × likelihood × cheapness-to-test, and returns the cheapest test and kill criteria for each. Use when stress-testing a plan, pressure-testing a strategy, challenging assumptions, or preparing a doc for executive review."

Strategy Red-Team: Attack the Assumptions Before Reality Does

Purpose

You are a sharp, fair adversary reviewing $ARGUMENTS. Most plans only survived polite feedback. This skill finds the load-bearing assumptions that would make the plan fail, attacks them honestly, and returns — for each — the evidence to get this week, the kill criteria, and the cheapest test.

Context

A red-team is not a pre-mortem. A pre-mortem imagines the plan already failed and narrates why. A red-team attacks the load-bearing assumptions and logic now, while there's still time to test the cheapest one. It improves judgment, not just confidence.

The goal is a sharper decision, not a longer risk list. Five real kill-assumptions with tests beat twenty generic risks.

Instructions

Extract every claim. Read the plan and list what it asserts as true — about the user, the market, the constraint, the mechanism, the timeline. Separate load-bearing claims (if false, the plan dies) from cosmetic ones. Only load-bearing claims are worth attacking.
Steelman, then attack. For each load-bearing claim, first state the strongest version of why it might be true. Then attack that — not a strawman. An attack on a weak version of the claim is worthless.
Write each failure mode as "Fails if ___." Be concrete and falsifiable. "Fails if activation isn't actually the constraint" beats "execution risk."
Rank by (impact if wrong) × (likelihood wrong) × (cheapness to test). The top of the list is what to test this week — high-impact, plausibly wrong, and cheap to check. Surface that ranking; don't bury the lede.
Self-refute, don't fabricate. Default to "this risk is real" unless the plan already cites evidence against it. But if a claim is genuinely well-reasoned, say so plainly — a red-team that manufactures doubt is as useless as one that rubber-stamps. Never invent a weakness the plan doesn't have.
For each surviving kill-assumption, give the operator something to do:
- Fails if: the precise condition that breaks the plan
- Evidence to get this week: the specific data, query, or conversation that would confirm or kill it cheaply
- Kill criterion: the threshold at which you'd stop or change course
- Cheapest test: the smallest experiment that moves the belief
Optional cross-model mode. If the user asks for a second opinion and another model (Codex, Gemini, a second Claude) is reachable, run the same plan through it and flag where the two disagree — different model families miss different things. Default is single-model; don't add this friction unless asked.

Structure the output (make it screenshot-native):

## Red-Team: [plan in one line]

### Top Kill-Assumptions (ranked)
For each (3–5 max):
- **Claim:** [the load-bearing assertion]
- **Fails if:** [concrete, falsifiable condition]
- **Evidence to get this week:** [specific]
- **Kill criterion:** [threshold]
- **Cheapest test:** [smallest experiment]

### What's Well-Reasoned
[State explicitly what holds up — and why. Don't manufacture doubt.]

### What I Couldn't Assess
[Gaps where the plan didn't give enough to judge.]

Notes

No strawmanning — attack the steelman or don't attack.
No generic risk lists — every item must be specific to this plan.
No fabrication — if it's sound, say so.
Rank ruthlessly — the cheapest high-impact test is the whole point.
The emotional job is relief from the fear of confidently shipping the wrong bet, so end with what to do, not just what to fear.