s4h-analogy-boundary-testing

Name: s4h-analogy-boundary-testing
Author: human-avatar

205stars23forks

How to install s4h-analogy-boundary-testing?

human-avatar/skills-for-humanity/s4h-analogy-boundary-testing

$npx -y skills add human-avatar/skills-for-humanity --skill s4h-analogy-boundary-testing

Installs into the current project.

Summary

Finds where an analogy breaks down before it's relied upon. Analogies fail silently — the damage happens when decisions are made on a mapping that doesn't hold in the relevant dimension. Triggers: 'stress-test this analogy', 'where does this comparison break', 'does this really a

Files · 1

View on GitHub

SKILL.md

1	# Analogy Boundary Testing
2
3	Analogies are tools, not truths. The danger is not using an analogy — it is using one past
4	its boundary. Analogies fail silently: the flaw is invisible until a decision has been made
5	that depended on the part that didn't hold. This skill finds the boundary before that
6	happens.
7
8	---
9
10	## Your Process
11
12	Step 1: State the Analogy
13	Write it explicitly: "X is like Y." Name the analogy being tested, the domain it comes
14	from, and the claim being made on the basis of it.
15
16	Framing check: Confirm the specific analogy before continuing. State what you've identified — the source domain, target domain, and the claim being made — in one sentence, then use `AskUserQuestion`:
17	- Question: "I'm reading this as: [your one-sentence framing of the analogy and the claim it supports]. 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 analogy or claim than read; incorporate the correction before proceeding
23
24	Step 2: List Similarities
25	What does the analogy capture correctly? List every genuine parallel — the aspects where
26	the structural correspondence is real. This is not validation; it's establishing what the
27	analogy is good for before finding what it isn't.
28
29	Step 3: List Differences
30	Every meaningful divergence between X and Y is a potential failure point. List them
31	systematically: different actors, different dynamics, different constraints, different
32	feedback mechanisms, different scales, different reversibility. Be thorough — incomplete
33	difference-listing is the most common failure mode here.
34
35	Step 4: Test Each Difference Against the Decision
36	Before narrowing: Show the complete list of differences from Step 3 to the user first. Use `AskUserQuestion`:
37	- Question: "I've identified [N] differences. Before I filter to those relevant to your decision, are there any you'd flag as especially important, or any I've missed?"
38	- Header: "Prioritise"
39	- Options:
40	- Proceed with your selection — the set looks right
41	- Flag one — user will name a specific difference to include
42	- Add a missing one — user will describe it
43
44	For each decision or conclusion being made on the basis of this analogy: which differences
45	are relevant to that specific decision? A difference that doesn't affect the conclusion is
46	harmless. A difference that does affect it invalidates the reasoning.
47
48	Step 5: Does the Conclusion Still Hold?
49	For each relevant difference identified in Step 4: if this difference is real, does the
50	conclusion derived from the analogy still follow? If not, the analogy cannot support that
51	conclusion.
52
53	Step 6: State Safe Scope
54	Where can this analogy be validly relied upon? What does it illuminate, and what decisions
55	can it inform? State the boundary clearly.
56
57	---
58
59	## Human Check-in
60
61	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:
62
63	- Question: "My read: [your 1–2 sentence interpretation]. How do you want to proceed?"
64	- Header: "Scope"
65	- Options:
66	- Full analysis — Complete all steps, reasoning shown throughout
67	- Key findings only — Bottom-line output, skip step-by-step detail
68	- Breaking points only — Where the analogy fails, not where it holds
69	- Reframe — The read is off; correct it and the analysis will follow the corrected framing
70
71	Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.
72
73	## Output Format
74
75	Analogy: [X is like Y — domain and claim]
76
77	Similarities (what the analogy captures correctly):
78	> [Bulleted list]
79
80	Differences (potential failure points):
81	> [Bulleted list — be thorough]
82
83	Relevant differences for this decision:
84
85	\| Difference \| Relevant to decision? \| Effect on conclusion \|
86	\|------------\|----------------------\|----------------------\|
87	\| \| \| \|
88	\| \| \| \|
89
90	Conclusion validity:
91	> [Does the analogy support the conclusion? Yes / Partially / No — with reason]
92
93	Safe scope — what this analogy validly applies to:
94	> [Bounded statement]
95
96	---
97
98	## Notes
99
100	The most useful output is the safe scope statement — a positive claim about where the
101	analogy is reliable. Discarding an analogy entirely because it has limits wastes the
102	genuine insight it contains.
103
104	---
105
106	## What's Next
107
108	After delivering this output, use `AskUserQuestion` to offer the next move:
109
110	- Question: "Analogy boundaries

People who liked this also viewed

6 picks

Type

s4h-analogy-boundary-testing

205stars23forks

View on GitHub

How to install s4h-analogy-boundary-testing?

human-avatar/skills-for-humanity/s4h-analogy-boundary-testing

$npx -y skills add human-avatar/skills-for-humanity --skill s4h-analogy-boundary-testing

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Analogy Boundary Testing
2
3	Analogies are tools, not truths. The danger is not using an analogy — it is using one past
4	its boundary. Analogies fail silently: the flaw is invisible until a decision has been made
5	that depended on the part that didn't hold. This skill finds the boundary before that
6	happens.
7
8	---
9
10	## Your Process
11
12	Step 1: State the Analogy
13	Write it explicitly: "X is like Y." Name the analogy being tested, the domain it comes
14	from, and the claim being made on the basis of it.
15
16	Framing check: Confirm the specific analogy before continuing. State what you've identified — the source domain, target domain, and the claim being made — in one sentence, then use `AskUserQuestion`:
17	- Question: "I'm reading this as: [your one-sentence framing of the analogy and the claim it supports]. 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 analogy or claim than read; incorporate the correction before proceeding
23
24	Step 2: List Similarities
25	What does the analogy capture correctly? List every genuine parallel — the aspects where
26	the structural correspondence is real. This is not validation; it's establishing what the
27	analogy is good for before finding what it isn't.
28
29	Step 3: List Differences
30	Every meaningful divergence between X and Y is a potential failure point. List them
31	systematically: different actors, different dynamics, different constraints, different
32	feedback mechanisms, different scales, different reversibility. Be thorough — incomplete
33	difference-listing is the most common failure mode here.
34
35	Step 4: Test Each Difference Against the Decision
36	Before narrowing: Show the complete list of differences from Step 3 to the user first. Use `AskUserQuestion`:
37	- Question: "I've identified [N] differences. Before I filter to those relevant to your decision, are there any you'd flag as especially important, or any I've missed?"
38	- Header: "Prioritise"
39	- Options:
40	- Proceed with your selection — the set looks right
41	- Flag one — user will name a specific difference to include
42	- Add a missing one — user will describe it
43
44	For each decision or conclusion being made on the basis of this analogy: which differences
45	are relevant to that specific decision? A difference that doesn't affect the conclusion is
46	harmless. A difference that does affect it invalidates the reasoning.
47
48	Step 5: Does the Conclusion Still Hold?
49	For each relevant difference identified in Step 4: if this difference is real, does the
50	conclusion derived from the analogy still follow? If not, the analogy cannot support that
51	conclusion.
52
53	Step 6: State Safe Scope
54	Where can this analogy be validly relied upon? What does it illuminate, and what decisions
55	can it inform? State the boundary clearly.
56
57	---
58
59	## Human Check-in
60
61	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:
62
63	- Question: "My read: [your 1–2 sentence interpretation]. How do you want to proceed?"
64	- Header: "Scope"
65	- Options:
66	- Full analysis — Complete all steps, reasoning shown throughout
67	- Key findings only — Bottom-line output, skip step-by-step detail
68	- Breaking points only — Where the analogy fails, not where it holds
69	- Reframe — The read is off; correct it and the analysis will follow the corrected framing
70
71	Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.
72
73	## Output Format
74
75	Analogy: [X is like Y — domain and claim]
76
77	Similarities (what the analogy captures correctly):
78	> [Bulleted list]
79
80	Differences (potential failure points):
81	> [Bulleted list — be thorough]
82
83	Relevant differences for this decision:
84
85	\| Difference \| Relevant to decision? \| Effect on conclusion \|
86	\|------------\|----------------------\|----------------------\|
87	\| \| \| \|
88	\| \| \| \|
89
90	Conclusion validity:
91	> [Does the analogy support the conclusion? Yes / Partially / No — with reason]
92
93	Safe scope — what this analogy validly applies to:
94	> [Bounded statement]
95
96	---
97
98	## Notes
99
100	The most useful output is the safe scope statement — a positive claim about where the
101	analogy is reliable. Discarding an analogy entirely because it has limits wastes the
102	genuine insight it contains.
103
104	---
105
106	## What's Next
107
108	After delivering this output, use `AskUserQuestion` to offer the next move:
109
110	- Question: "Analogy boundaries

People who liked this also viewed

6 picks

Type