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.
Further Reading
Source: phuryn/pm-skills → pm-execution/skills/strategy-red-team/SKILL.md
1---2name: strategy-red-team3description: 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.4---5
6
7# Strategy Red-Team: Attack the Assumptions Before Reality Does
8
9## Purpose
10
11You 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.
12
13## Context
14
15A 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.
16
17The goal is a sharper decision, not a longer risk list. Five real kill-assumptions with tests beat twenty generic risks.
18
19## Instructions
20
211. **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.
22
232. **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.
24
253. **Write each failure mode as "Fails if ___."** Be concrete and falsifiable. "Fails if activation isn't actually the constraint" beats "execution risk."
26
274. **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.
28
295. **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.
30
316. **For each surviving kill-assumption, give the operator something to do:**
32 - **Fails if:** the precise condition that breaks the plan
33 - **Evidence to get this week:** the specific data, query, or conversation that would confirm or kill it cheaply
34 - **Kill criterion:** the threshold at which you'd stop or change course
35 - **Cheapest test:** the smallest experiment that moves the belief
36
377. **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.
38
398. **Structure the output (make it screenshot-native):**
40
41 ```
42 ## Red-Team: [plan in one line]
43
44 ### Top Kill-Assumptions (ranked)
45 For each (3–5 max):
46 - **Claim:** [the load-bearing assertion]
47 - **Fails if:** [concrete, falsifiable condition]
48 - **Evidence to get this week:** [specific]
49 - **Kill criterion:** [threshold]
50 - **Cheapest test:** [smallest experiment]
51
52 ### What's Well-Reasoned
53 [State explicitly what holds up — and why. Don't manufacture doubt.]
54
55 ### What I Couldn't Assess
56 [Gaps where the plan didn't give enough to judge.]
57 ```
58
59## Notes
60
61- No strawmanning — attack the steelman or don't attack.
62- No generic risk lists — every item must be specific to *this* plan.
63- No fabrication — if it's sound, say so.
64- Rank ruthlessly — the cheapest high-impact test is the whole point.
65- 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.
66
67---
68
69### Further Reading
70
71- [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas)
72- [How to Manage Risks as a Product Manager](https://www.productcompass.pm/p/how-to-manage-risks-as-a-product-manager)
73- [How Meta and Instagram Use Pre-Mortems to Avoid Post-Mortems](https://www.productcompass.pm/p/how-to-run-pre-mortem-template)
74
75---
76
77**Source:** [`phuryn/pm-skills`](https://github.com/phuryn/pm-skills) → `pm-execution/skills/strategy-red-team/SKILL.md`
thedixitjain