s4h-decision-premortem-analysis

Name: s4h-decision-premortem-analysis
Author: human-avatar

205stars23forks

How to install s4h-decision-premortem-analysis?

human-avatar/skills-for-humanity/s4h-decision-premortem-analysis

$npx -y skills add human-avatar/skills-for-humanity --skill s4h-decision-premortem-analysis

Installs into the current project.

Summary

Imagines the decision has been made and failed — then diagnoses why. Breaks the commitment bias that prevents honest risk assessment after a direction is chosen. Triggers: 'pre-mortem', 'imagine this failed', 'what could go wrong', 'assume this doesn't work', 'failure mode analys

Files · 1

View on GitHub

SKILL.md

1	# Decision Premortem Analysis
2
3	Once a direction is chosen, commitment bias makes honest risk assessment nearly impossible
4	— the mind starts defending the decision rather than evaluating it. This skill breaks that
5	by mandating a specific fiction: assume the project has already failed. Then ask why.
6	The pessimism is not optional — it is the mechanism.
7
8	---
9
10	## Your Process
11
12	Step 1: State the Decision and Intended Outcome
13	Write the decision clearly and the specific outcome it is supposed to produce. Include
14	the timeline and the measurable definition of success.
15
16	Framing check: Confirm the specific decision before continuing. State what you've identified — the actual decision being stress-tested and its intended outcome — in one sentence, then use `AskUserQuestion`:
17	- Question: "I'm reading this as: [your one-sentence framing of the decision and its intended outcome]. Is that right?"
18	- Header: "Framing"
19	- Options:
20	- Yes — proceed — framing is correct
21	- Adjust — one element is off; user will correct it before you continue
22	- Reframe — different situation than read; incorporate the correction before proceeding
23
24	Step 2: Project to Failure
25	Enter the failure frame. The statement is: "[Project name] launched on [date] and failed
26	to achieve [outcome]. Here is what went wrong." Write this as if reporting a post-mortem,
27	not brainstorming risks. The past-tense fiction reduces defensive filtering.
28
29	Step 3: Brainstorm All Failure Modes
30	Generate failure modes without filtering for probability. Encourage pessimism. For each
31	failure mode, ask: how would this actually unfold? What would be the first sign? What
32	would make it worse?
33
34	Step 4: Group Failures by Type
35	- Execution failures: we had the right model of the world but did it wrong —
36	timing, resourcing, coordination, quality.
37	- Assumption failures: we did it right but our model of the world was wrong —
38	the market, the users, the technology, the dependencies.
39	- Unknown failures: we didn't anticipate this category of problem at all.
40
41	Step 5: Pre-emptive Action per Top Failure Mode
42	Before narrowing: Show the complete generated set to the user first. Use `AskUserQuestion`:
43	- Question: "I've identified [N] failure modes. Before I select the most significant by probability × severity, are there any you'd flag as especially important, or any I've missed?"
44	- Header: "Prioritise"
45	- Options:
46	- Proceed with your selection — the set looks right
47	- Flag one — user will name a specific failure mode to include
48	- Add a missing one — user will describe it
49
50	Identify the 3-5 most significant failure modes (highest probability × severity). For
51	each: what single action, taken now, most reduces the probability or severity of this
52	failure?
53
54	---
55
56	## Human Check-in
57
58	Before proceeding, use the `AskUserQuestion` tool. State your interpretation of the situation in 1–2 sentences — what is being analyzed and what the core question is — then ask:
59
60	- Question: "My read: [your 1–2 sentence interpretation]. How do you want to proceed?"
61	- Header: "Scope"
62	- Options:
63	- Full analysis — Complete all steps, reasoning shown throughout
64	- Key findings only — Bottom-line output, skip step-by-step detail
65	- Top 3 failure modes only — Highest probability × severity combinations, skip the full inventory
66	- Reframe — The read is off; correct it and the analysis will follow the corrected framing
67
68	Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.
69
70	## Output Format
71
72	Decision and intended outcome:
73	> [Statement + timeline + measurable success definition]
74
75	Failure modes (all generated):
76
77	\| Failure mode \| Type (Execution / Assumption / Unknown) \| Probability \| Severity \|
78	\|-------------\|----------------------------------------\|-------------\|----------\|
79	\| \| \| \| \|
80	\| \| \| \| \|
81
82	Top 3-5 failure modes with pre-emptive actions:
83
84	\| Failure mode \| Why it's significant \| Pre-emptive action \|
85	\|-------------\|---------------------\|-------------------\|
86	\| \| \| \|
87	\| \| \| \|
88
89	Assumption inventory (things that must be true for this to work):
90	> [Bulleted list — these are the highest-leverage unknowns to validate early]
91
92	---
93
94	## Notes
95
96	Assumption failures are the most dangerous category because they are invisible until
97	something breaks. The pre-mortem's most durable output is often the assumption inventory —
98	which assumptions, if wrong, would make the entire direction invalid?
99
100	---
101
102	## What's Next
103
104	After delivering this output, use `AskUserQuestion` to offer the next move:
105
106	- Question: "Failure mod

People who liked this also viewed

6 picks

Type

s4h-decision-premortem-analysis

205stars23forks

View on GitHub

How to install s4h-decision-premortem-analysis?

human-avatar/skills-for-humanity/s4h-decision-premortem-analysis

$npx -y skills add human-avatar/skills-for-humanity --skill s4h-decision-premortem-analysis

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Decision Premortem Analysis
2
3	Once a direction is chosen, commitment bias makes honest risk assessment nearly impossible
4	— the mind starts defending the decision rather than evaluating it. This skill breaks that
5	by mandating a specific fiction: assume the project has already failed. Then ask why.
6	The pessimism is not optional — it is the mechanism.
7
8	---
9
10	## Your Process
11
12	Step 1: State the Decision and Intended Outcome
13	Write the decision clearly and the specific outcome it is supposed to produce. Include
14	the timeline and the measurable definition of success.
15
16	Framing check: Confirm the specific decision before continuing. State what you've identified — the actual decision being stress-tested and its intended outcome — in one sentence, then use `AskUserQuestion`:
17	- Question: "I'm reading this as: [your one-sentence framing of the decision and its intended outcome]. Is that right?"
18	- Header: "Framing"
19	- Options:
20	- Yes — proceed — framing is correct
21	- Adjust — one element is off; user will correct it before you continue
22	- Reframe — different situation than read; incorporate the correction before proceeding
23
24	Step 2: Project to Failure
25	Enter the failure frame. The statement is: "[Project name] launched on [date] and failed
26	to achieve [outcome]. Here is what went wrong." Write this as if reporting a post-mortem,
27	not brainstorming risks. The past-tense fiction reduces defensive filtering.
28
29	Step 3: Brainstorm All Failure Modes
30	Generate failure modes without filtering for probability. Encourage pessimism. For each
31	failure mode, ask: how would this actually unfold? What would be the first sign? What
32	would make it worse?
33
34	Step 4: Group Failures by Type
35	- Execution failures: we had the right model of the world but did it wrong —
36	timing, resourcing, coordination, quality.
37	- Assumption failures: we did it right but our model of the world was wrong —
38	the market, the users, the technology, the dependencies.
39	- Unknown failures: we didn't anticipate this category of problem at all.
40
41	Step 5: Pre-emptive Action per Top Failure Mode
42	Before narrowing: Show the complete generated set to the user first. Use `AskUserQuestion`:
43	- Question: "I've identified [N] failure modes. Before I select the most significant by probability × severity, are there any you'd flag as especially important, or any I've missed?"
44	- Header: "Prioritise"
45	- Options:
46	- Proceed with your selection — the set looks right
47	- Flag one — user will name a specific failure mode to include
48	- Add a missing one — user will describe it
49
50	Identify the 3-5 most significant failure modes (highest probability × severity). For
51	each: what single action, taken now, most reduces the probability or severity of this
52	failure?
53
54	---
55
56	## Human Check-in
57
58	Before proceeding, use the `AskUserQuestion` tool. State your interpretation of the situation in 1–2 sentences — what is being analyzed and what the core question is — then ask:
59
60	- Question: "My read: [your 1–2 sentence interpretation]. How do you want to proceed?"
61	- Header: "Scope"
62	- Options:
63	- Full analysis — Complete all steps, reasoning shown throughout
64	- Key findings only — Bottom-line output, skip step-by-step detail
65	- Top 3 failure modes only — Highest probability × severity combinations, skip the full inventory
66	- Reframe — The read is off; correct it and the analysis will follow the corrected framing
67
68	Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.
69
70	## Output Format
71
72	Decision and intended outcome:
73	> [Statement + timeline + measurable success definition]
74
75	Failure modes (all generated):
76
77	\| Failure mode \| Type (Execution / Assumption / Unknown) \| Probability \| Severity \|
78	\|-------------\|----------------------------------------\|-------------\|----------\|
79	\| \| \| \| \|
80	\| \| \| \| \|
81
82	Top 3-5 failure modes with pre-emptive actions:
83
84	\| Failure mode \| Why it's significant \| Pre-emptive action \|
85	\|-------------\|---------------------\|-------------------\|
86	\| \| \| \|
87	\| \| \| \|
88
89	Assumption inventory (things that must be true for this to work):
90	> [Bulleted list — these are the highest-leverage unknowns to validate early]
91
92	---
93
94	## Notes
95
96	Assumption failures are the most dangerous category because they are invisible until
97	something breaks. The pre-mortem's most durable output is often the assumption inventory —
98	which assumptions, if wrong, would make the entire direction invalid?
99
100	---
101
102	## What's Next
103
104	After delivering this output, use `AskUserQuestion` to offer the next move:
105
106	- Question: "Failure mod

People who liked this also viewed

6 picks

Type