strategy-red-team

Name: strategy-red-team
Author: phuryn

782installs2.5kforks

How to install strategy-red-team?

phuryn/pm-skills/strategy-red-team

$npx -y skills add phuryn/pm-skills --skill strategy-red-team

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# Strategy Red-Team: Attack the Assumptions Before Reality Does
2
3	## Purpose
4
5	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.
6
7	## Context
8
9	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.
10
11	The goal is a sharper decision, not a longer risk list. Five real kill-assumptions with tests beat twenty generic risks.
12
13	## Instructions
14
15	1. 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.
16
17	2. 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.
18
19	3. Write each failure mode as "Fails if ___." Be concrete and falsifiable. "Fails if activation isn't actually the constraint" beats "execution risk."
20
21	4. 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.
22
23	5. 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.
24
25	6. For each surviving kill-assumption, give the operator something to do:
26	- Fails if: the precise condition that breaks the plan
27	- Evidence to get this week: the specific data, query, or conversation that would confirm or kill it cheaply
28	- Kill criterion: the threshold at which you'd stop or change course
29	- Cheapest test: the smallest experiment that moves the belief
30
31	7. 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.
32
33	8. Structure the output (make it screenshot-native):
34
35	```
36	## Red-Team: [plan in one line]
37
38	### Top Kill-Assumptions (ranked)
39	For each (3–5 max):
40	- Claim: [the load-bearing assertion]
41	- Fails if: [concrete, falsifiable condition]
42	- Evidence to get this week: [specific]
43	- Kill criterion: [threshold]
44	- Cheapest test: [smallest experiment]
45
46	### What's Well-Reasoned
47	[State explicitly what holds up — and why. Don't manufacture doubt.]
48
49	### What I Couldn't Assess
50	[Gaps where the plan didn't give enough to judge.]
51	```
52
53	## Notes
54
55	- No strawmanning — attack the steelman or don't attack.
56	- No generic risk lists — every item must be specific to this plan.
57	- No fabrication — if it's sound, say so.
58	- Rank ruthlessly — the cheapest high-impact test is the whole point.
59	- 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.
60
61	---
62
63	### Further Reading
64
65	- [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas)
66	- [How to Manage Risks as a Product Manager](https://www.productcompass.pm/p/how-to-manage-risks-as-a-product-manager)
67	- [How Meta and Instagram Use Pre-Mortems to Avoid Post-Mortems](https://www.productcompass.pm/p/how-to-run-pre-mortem-template)

People who liked this also viewed

6 picks

Type

strategy-red-team

782installs2.5kforks

View on GitHub

How to install strategy-red-team?

phuryn/pm-skills/strategy-red-team

$npx -y skills add phuryn/pm-skills --skill strategy-red-team

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Strategy Red-Team: Attack the Assumptions Before Reality Does
2
3	## Purpose
4
5	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.
6
7	## Context
8
9	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.
10
11	The goal is a sharper decision, not a longer risk list. Five real kill-assumptions with tests beat twenty generic risks.
12
13	## Instructions
14
15	1. 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.
16
17	2. 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.
18
19	3. Write each failure mode as "Fails if ___." Be concrete and falsifiable. "Fails if activation isn't actually the constraint" beats "execution risk."
20
21	4. 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.
22
23	5. 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.
24
25	6. For each surviving kill-assumption, give the operator something to do:
26	- Fails if: the precise condition that breaks the plan
27	- Evidence to get this week: the specific data, query, or conversation that would confirm or kill it cheaply
28	- Kill criterion: the threshold at which you'd stop or change course
29	- Cheapest test: the smallest experiment that moves the belief
30
31	7. 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.
32
33	8. Structure the output (make it screenshot-native):
34
35	```
36	## Red-Team: [plan in one line]
37
38	### Top Kill-Assumptions (ranked)
39	For each (3–5 max):
40	- Claim: [the load-bearing assertion]
41	- Fails if: [concrete, falsifiable condition]
42	- Evidence to get this week: [specific]
43	- Kill criterion: [threshold]
44	- Cheapest test: [smallest experiment]
45
46	### What's Well-Reasoned
47	[State explicitly what holds up — and why. Don't manufacture doubt.]
48
49	### What I Couldn't Assess
50	[Gaps where the plan didn't give enough to judge.]
51	```
52
53	## Notes
54
55	- No strawmanning — attack the steelman or don't attack.
56	- No generic risk lists — every item must be specific to this plan.
57	- No fabrication — if it's sound, say so.
58	- Rank ruthlessly — the cheapest high-impact test is the whole point.
59	- 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.
60
61	---
62
63	### Further Reading
64
65	- [Assumption Prioritization Canvas: How to Identify And Test The Right Assumptions](https://www.productcompass.pm/p/assumption-prioritization-canvas)
66	- [How to Manage Risks as a Product Manager](https://www.productcompass.pm/p/how-to-manage-risks-as-a-product-manager)
67	- [How Meta and Instagram Use Pre-Mortems to Avoid Post-Mortems](https://www.productcompass.pm/p/how-to-run-pre-mortem-template)

People who liked this also viewed

6 picks

Type