$npx -y skills add human-avatar/skills-for-humanity --skill s4h-analogy-domain-transferImports solutions from unrelated domains by finding structural similarities between your problem and solved problems elsewhere. Triggers: 'cross-domain analogy', 'what solves this elsewhere', 'find a parallel problem', 'look outside this field', 'borrow a solution'.
| 1 | # Analogy Domain Transfer |
| 2 | |
| 3 | Your field has blind spots that your field created. The best solutions to structural |
| 4 | problems often exist already — in biology, military strategy, architecture, sport, logistics, |
| 5 | emergency medicine — because the underlying problem is not domain-specific. The work is |
| 6 | abstraction: strip away the domain details until the pattern is visible, then find where |
| 7 | that pattern is already solved. |
| 8 | |
| 9 | --- |
| 10 | |
| 11 | ## Your Process |
| 12 | |
| 13 | **Step 1: Abstract the Problem to Structural Essence** |
| 14 | Describe the problem without any domain vocabulary. What is actually happening? What are |
| 15 | the actors, their relationships, the failure mode, the goal? The moment you can describe |
| 16 | it without industry jargon, you can search for it anywhere. |
| 17 | |
| 18 | **Framing check:** Confirm the specific problem being transferred before continuing. State what you've identified — the actual challenge, its actors, and the failure mode or goal — in one sentence, then use `AskUserQuestion`: |
| 19 | - **Question:** "I'm reading this as: [your one-sentence framing of the problem stripped of domain vocabulary]. Is that right?" |
| 20 | - **Header:** "Framing" |
| 21 | - **Options:** |
| 22 | - **Yes — proceed** — framing is correct |
| 23 | - **Adjust** — one element is off; user will correct it before you continue |
| 24 | - **Reframe** — different situation than read; incorporate the correction before proceeding |
| 25 | |
| 26 | **Step 2: Search Candidate Domains** |
| 27 | Consider where this structural pattern appears: biology (systems, adaptation, immunity), |
| 28 | military (logistics, command, deception), architecture (load, flow, resilience), sport |
| 29 | (coordination, pressure, strategy), gaming (rules, incentives, escalation), logistics |
| 30 | (sequencing, bottlenecks, routing), medicine (diagnosis, triage, recovery). |
| 31 | |
| 32 | **Step 3: Extract the Core Mechanism** |
| 33 | For each candidate domain: what is the actual mechanism that solves the problem? Not the |
| 34 | surface story — the operational logic. How does it work, step by step? |
| 35 | |
| 36 | **Step 4: Map Mechanism Back** |
| 37 | Translate the mechanism into your problem. What plays what role? What would be the |
| 38 | equivalent of each element? This is where analogies either click or reveal themselves as |
| 39 | superficial. |
| 40 | |
| 41 | **Step 5: Test Where the Analogy Holds and Breaks** |
| 42 | Every analogy breaks somewhere. Where does the mechanism still work when mapped? Where does |
| 43 | it stop working? The break points tell you where to be careful and where the insight ends. |
| 44 | |
| 45 | --- |
| 46 | |
| 47 | ## Human Check-in |
| 48 | |
| 49 | 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: |
| 50 | |
| 51 | - **Question:** "My read: [your 1–2 sentence interpretation]. How do you want to proceed?" |
| 52 | - **Header:** "Scope" |
| 53 | - **Options:** |
| 54 | - **Full analysis** — Complete all steps, reasoning shown throughout |
| 55 | - **Key findings only** — Bottom-line output, skip step-by-step detail |
| 56 | - **One domain transfer** — The single most structurally similar domain, fully developed |
| 57 | - **Reframe** — The read is off; correct it and the analysis will follow the corrected framing |
| 58 | |
| 59 | Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis. |
| 60 | |
| 61 | ## Output Format |
| 62 | |
| 63 | **Problem (abstracted — no domain vocabulary):** |
| 64 | > [Structural description] |
| 65 | |
| 66 | **Candidate domains and mechanisms:** |
| 67 | |
| 68 | | Domain | Analogous problem | Core mechanism | Strength of match | |
| 69 | |--------|------------------|----------------|-------------------| |
| 70 | | | | | | |
| 71 | | | | | | |
| 72 | |
| 73 | **Best mapping:** |
| 74 | - Domain element → Your problem element (for each key pair) |
| 75 | |
| 76 | **Where the analogy holds:** |
| 77 | > [Specific aspects] |
| 78 | |
| 79 | **Where the analogy breaks:** |
| 80 | > [Specific aspects — don't skip this] |
| 81 | |
| 82 | **Insight to import:** |
| 83 | > [The actionable mechanism translated back into your problem] |
| 84 | |
| 85 | --- |
| 86 | |
| 87 | ## Notes |
| 88 | |
| 89 | A weak abstraction in Step 1 produces weak domain matches. If the domains found feel |
| 90 | obvious or already-familiar, the abstraction still contains domain assumptions — strip |
| 91 | further. |
| 92 | |
| 93 | --- |
| 94 | |
| 95 | ## What's Next |
| 96 | |
| 97 | After delivering this output, use `AskUserQuestion` to offer the next move: |
| 98 | |
| 99 | - **Question:** "Domain transfer complete. What's next?" |
| 100 | - **Header:** "Next" |
| 101 | - **Options:** |
| 102 | - `/s4h-logic-check` — Validate that the transfer holds and conclusions follow |
| 103 | - `/s4h-analogy-boundary-testing` — Test where the analogy breaks down |
| 104 | - `/s4h-creativity-alternatives` — Use the transferred ideas to generate new alternatives |
| 105 | - **Done** — Wrap up and synthesise what we have so far |