s4h-decision-criteria-weighting

Name: s4h-decision-criteria-weighting
Author: human-avatar

205stars23forks

How to install s4h-decision-criteria-weighting?

human-avatar/skills-for-humanity/s4h-decision-criteria-weighting

$npx -y skills add human-avatar/skills-for-humanity --skill s4h-decision-criteria-weighting

Installs into the current project.

Summary

Runs a weighted multi-criteria analysis — making explicit what matters, how much, and how each option performs against it. Triggers: 'weighted decision matrix', 'multi-criteria analysis', 'help me choose between', 'compare these options', 'decision matrix'.

Files · 1

View on GitHub

SKILL.md

1	# Decision Criteria Weighting
2
3	Intuitive decisions fail when too many criteria are in play and their relative importance
4	isn't made explicit. This skill forces that explicitness. The goal is not to replace
5	judgment — it is to make the judgment visible enough to inspect, challenge, and defend.
6
7	---
8
9	## Your Process
10
11	Step 1: State the Decision and List Real Options
12	Name the decision. List the actual options being considered — not aspirational ones. If an
13	option isn't genuinely available, remove it before it contaminates the analysis.
14
15	Framing check: Confirm the decision and its intended outcome before continuing. State what you've identified — the specific decision being made and the options on the table — in one sentence, then use `AskUserQuestion`:
16	- Question: "I'm reading this as: [your one-sentence framing of the decision and the options being compared]. Is that right?"
17	- Header: "Framing"
18	- Options:
19	- Yes — proceed — framing is correct
20	- Adjust — one element is off; user will correct it before you continue
21	- Reframe — different situation than read; incorporate the correction before proceeding
22
23	Step 2: Identify 4-8 Criteria
24	Name the criteria that define a good outcome for this specific decision. Criteria should
25	be independent (not measuring the same thing twice), observable (you can score against
26	them), and genuinely relevant (removing one would change the analysis).
27
28	Before narrowing: Show the complete generated set of candidate criteria to the user first. Use `AskUserQuestion`:
29	- Question: "I've identified [N] candidate criteria. Before I narrow to the most decision-relevant ones, are there any you'd flag as especially important, or any I've missed?"
30	- Header: "Prioritise"
31	- Options:
32	- Proceed with your selection — the set looks right
33	- Flag one — user will name a specific criterion to include
34	- Add a missing one — user will describe it
35
36	Step 3: Weight the Criteria
37	Distribute exactly 100 points across the criteria. This forces trade-offs — you cannot
38	weight everything highly. If everything matters equally, the distribution reveals a
39	failure to think through what actually matters most.
40
41	Step 4: Score Each Option
42	Score each option on each criterion from 1 to 5. Do this before calculating totals — the
43	sequence matters. Scoring after you see where things are headed is reverse-engineering to
44	confirm a preference, which defeats the exercise.
45
46	Step 5: Calculate Weighted Scores
47	Weighted score = sum of (weight × score) for each criterion. Calculate for all options.
48
49	Step 6: Sense-Check
50	If the math agrees with your intuition, good. If it disagrees, investigate: is the
51	intuition catching something the criteria missed, or is the intuition rationalising a
52	preference? Either is possible. Don't dismiss either.
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	- Weights only — Establish criteria priorities before scoring any options
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: [Statement]
73
74	Criteria and weights:
75
76	\| Criterion \| Weight (total = 100) \|
77	\|-----------\|----------------------\|
78	\| \| \|
79
80	Scored matrix:
81
82	\| Option \| [Criterion 1] (×W) \| [Criterion 2] (×W) \| ... \| Weighted Total \|
83	\|--------\|-------------------\|-------------------\|-----\|----------------\|
84	\| \| \| \| \| \|
85	\| \| \| \| \| \|
86
87	Sense-check:
88	> [Does the result match intuition? If not — what is the intuition picking up that the
89	> matrix doesn't capture, or what is the intuition getting wrong?]
90
91	Recommendation:
92	> [Option name] — [one sentence rationale]
93
94	---
95
96	## Notes
97
98	The value of this exercise is in the weighting step, not the scoring. Most decision
99	disagreements are disagreements about what matters, not about how options perform.
100	Making weights explicit moves the conversation to the right place.
101
102	---
103
104	## What's Next
105
106	After delivering this output, use `AskUserQuestion` to offer the next move:
107
108	- Question: "Criteria weighted and options ranked. What's next?"
109	- Header: "Next"
110	- Options:
111	- `/s4h-decision-premortem-analys

People who liked this also viewed

6 picks

Type

s4h-decision-criteria-weighting

205stars23forks

View on GitHub

How to install s4h-decision-criteria-weighting?

human-avatar/skills-for-humanity/s4h-decision-criteria-weighting

$npx -y skills add human-avatar/skills-for-humanity --skill s4h-decision-criteria-weighting

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Decision Criteria Weighting
2
3	Intuitive decisions fail when too many criteria are in play and their relative importance
4	isn't made explicit. This skill forces that explicitness. The goal is not to replace
5	judgment — it is to make the judgment visible enough to inspect, challenge, and defend.
6
7	---
8
9	## Your Process
10
11	Step 1: State the Decision and List Real Options
12	Name the decision. List the actual options being considered — not aspirational ones. If an
13	option isn't genuinely available, remove it before it contaminates the analysis.
14
15	Framing check: Confirm the decision and its intended outcome before continuing. State what you've identified — the specific decision being made and the options on the table — in one sentence, then use `AskUserQuestion`:
16	- Question: "I'm reading this as: [your one-sentence framing of the decision and the options being compared]. Is that right?"
17	- Header: "Framing"
18	- Options:
19	- Yes — proceed — framing is correct
20	- Adjust — one element is off; user will correct it before you continue
21	- Reframe — different situation than read; incorporate the correction before proceeding
22
23	Step 2: Identify 4-8 Criteria
24	Name the criteria that define a good outcome for this specific decision. Criteria should
25	be independent (not measuring the same thing twice), observable (you can score against
26	them), and genuinely relevant (removing one would change the analysis).
27
28	Before narrowing: Show the complete generated set of candidate criteria to the user first. Use `AskUserQuestion`:
29	- Question: "I've identified [N] candidate criteria. Before I narrow to the most decision-relevant ones, are there any you'd flag as especially important, or any I've missed?"
30	- Header: "Prioritise"
31	- Options:
32	- Proceed with your selection — the set looks right
33	- Flag one — user will name a specific criterion to include
34	- Add a missing one — user will describe it
35
36	Step 3: Weight the Criteria
37	Distribute exactly 100 points across the criteria. This forces trade-offs — you cannot
38	weight everything highly. If everything matters equally, the distribution reveals a
39	failure to think through what actually matters most.
40
41	Step 4: Score Each Option
42	Score each option on each criterion from 1 to 5. Do this before calculating totals — the
43	sequence matters. Scoring after you see where things are headed is reverse-engineering to
44	confirm a preference, which defeats the exercise.
45
46	Step 5: Calculate Weighted Scores
47	Weighted score = sum of (weight × score) for each criterion. Calculate for all options.
48
49	Step 6: Sense-Check
50	If the math agrees with your intuition, good. If it disagrees, investigate: is the
51	intuition catching something the criteria missed, or is the intuition rationalising a
52	preference? Either is possible. Don't dismiss either.
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	- Weights only — Establish criteria priorities before scoring any options
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: [Statement]
73
74	Criteria and weights:
75
76	\| Criterion \| Weight (total = 100) \|
77	\|-----------\|----------------------\|
78	\| \| \|
79
80	Scored matrix:
81
82	\| Option \| [Criterion 1] (×W) \| [Criterion 2] (×W) \| ... \| Weighted Total \|
83	\|--------\|-------------------\|-------------------\|-----\|----------------\|
84	\| \| \| \| \| \|
85	\| \| \| \| \| \|
86
87	Sense-check:
88	> [Does the result match intuition? If not — what is the intuition picking up that the
89	> matrix doesn't capture, or what is the intuition getting wrong?]
90
91	Recommendation:
92	> [Option name] — [one sentence rationale]
93
94	---
95
96	## Notes
97
98	The value of this exercise is in the weighting step, not the scoring. Most decision
99	disagreements are disagreements about what matters, not about how options perform.
100	Making weights explicit moves the conversation to the right place.
101
102	---
103
104	## What's Next
105
106	After delivering this output, use `AskUserQuestion` to offer the next move:
107
108	- Question: "Criteria weighted and options ranked. What's next?"
109	- Header: "Next"
110	- Options:
111	- `/s4h-decision-premortem-analys

People who liked this also viewed

6 picks

Type