$npx -y skills add human-avatar/skills-for-humanity --skill s4h-analogy-perspective-shiftingApproaches a problem from completely different fields to break the assumption blindness that comes from domain expertise. Triggers: 'fresh eyes', 'outside perspective', 'what would a [different expert] say', 'beginner's mind', 'approach from another field'.
| 1 | # Analogy Perspective Shifting |
| 2 | |
| 3 | Domain expertise creates assumption blindness. The more you know about a field, the more |
| 4 | invisible its foundational assumptions become — they stop looking like choices and start |
| 5 | looking like facts. Bringing in genuine outsider perspectives breaks this. Not |
| 6 | hypothetically — by actually applying the diagnostic instincts and tools of people who |
| 7 | have never heard of your problem's usual framing. |
| 8 | |
| 9 | --- |
| 10 | |
| 11 | ## Your Process |
| 12 | |
| 13 | **Step 1: State the Problem** |
| 14 | Describe the problem as you currently understand it. This is the insider framing — it will |
| 15 | contain the assumptions you're trying to surface. |
| 16 | |
| 17 | **Framing check:** Confirm the specific problem before continuing. State what you've identified — the actual situation being examined and its domain — in one sentence, then use `AskUserQuestion`: |
| 18 | - **Question:** "I'm reading this as: [your one-sentence framing of the problem and its domain]. Is that right?" |
| 19 | - **Header:** "Framing" |
| 20 | - **Options:** |
| 21 | - **Yes — proceed** — framing is correct |
| 22 | - **Adjust** — one element is off; user will correct it before you continue |
| 23 | - **Reframe** — different situation than read; incorporate the correction before proceeding |
| 24 | |
| 25 | **Step 2: Choose 2-3 Genuinely Different Fields** |
| 26 | Select fields with fundamentally different training, tools, and instincts. For software |
| 27 | problems: film production, archaeology, emergency medicine, urban planning. For |
| 28 | organisational problems: ecology, military logistics, theatre direction, structural |
| 29 | engineering. Avoid fields that are adjacent — choose fields that would produce different |
| 30 | first questions. |
| 31 | |
| 32 | **Step 3: Build Each Expert's Toolkit** |
| 33 | For each field: what are their core diagnostic tools and instincts? What do they always |
| 34 | check first? What patterns are they trained to spot? What would their first question be |
| 35 | when encountering an unknown problem? |
| 36 | |
| 37 | **Step 4: Apply Each Lens** |
| 38 | Apply each expert's toolkit to your problem. What do they immediately notice that insiders |
| 39 | overlook? What would they try first that you haven't? What would strike them as obviously |
| 40 | wrong or unnecessarily complex? Don't moderate the outsider view — let it be naive. |
| 41 | |
| 42 | **Step 5: Find Cross-Field Patterns** |
| 43 | What do multiple outsiders notice independently? When different fields converge on the |
| 44 | same observation, that observation has a strong claim to being real — it's visible from |
| 45 | multiple angles, not an artefact of one framing. |
| 46 | |
| 47 | --- |
| 48 | |
| 49 | ## Human Check-in |
| 50 | |
| 51 | 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: |
| 52 | |
| 53 | - **Question:** "My read: [your 1–2 sentence interpretation]. How do you want to proceed?" |
| 54 | - **Header:** "Scope" |
| 55 | - **Options:** |
| 56 | - **Full analysis** — Complete all steps, reasoning shown throughout |
| 57 | - **Key findings only** — Bottom-line output, skip step-by-step detail |
| 58 | - **Shifted perspective only** — The view from the new field, skip the formal structural mapping |
| 59 | - **Reframe** — The read is off; correct it and the analysis will follow the corrected framing |
| 60 | |
| 61 | Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis. |
| 62 | |
| 63 | ## Output Format |
| 64 | |
| 65 | **Problem (insider framing):** |
| 66 | > [Current description] |
| 67 | |
| 68 | **Field perspectives:** |
| 69 | |
| 70 | | Field | Core instincts / tools | What they notice | What they'd try first | |
| 71 | |-------|------------------------|------------------|-----------------------| |
| 72 | | | | | | |
| 73 | | | | | | |
| 74 | |
| 75 | **Cross-field patterns (what multiple outsiders see):** |
| 76 | > [Observations that appear across more than one field] |
| 77 | |
| 78 | **Most useful foreign insight:** |
| 79 | > [The single observation or approach from outside that would most change how you work |
| 80 | > the problem — and why it's been invisible from inside] |
| 81 | |
| 82 | --- |
| 83 | |
| 84 | ## Notes |
| 85 | |
| 86 | The exercise fails if the "outside" perspectives are just your own reasoning relabelled. |
| 87 | Each field's observations should surprise you. If they don't, you haven't actually left |
| 88 | your frame — you've just dressed it in different vocabulary. |
| 89 | |
| 90 | --- |
| 91 | |
| 92 | ## What's Next |
| 93 | |
| 94 | After delivering this output, use `AskUserQuestion` to offer the next move: |
| 95 | |
| 96 | - **Question:** "Perspectives shifted. What's next?" |
| 97 | - **Header:** "Next" |
| 98 | - **Options:** |
| 99 | - `/s4h-communication-audience-modeling` — Model the audience through each shifted perspective |
| 100 | - `/s4h-creativity-alternatives` — Generate alternatives from each perspective |
| 101 | - `/s4h-emotional-motivation-mapping` — Map motivations visible from each perspective |
| 102 | - **Done** — Wrap up and synthesise what we have so far |