$npx -y skills add human-avatar/skills-for-humanity --skill s4h-aesthetic-coherence-checkTests whether the parts of something form a unified whole — finding the jarring inconsistencies that accumulate when different contributors work without a shared vision. TRIGGERS: 'coherence check', 'does this feel unified', 'something feels off', 'inconsistent', 'check the whole
| 1 | # Aesthetic Coherence Check |
| 2 | |
| 3 | Incoherence is the default product of collaboration without a shared vision. Each part |
| 4 | may be locally defensible — sensible in isolation, reasonable given what that contributor |
| 5 | was optimising for — while the whole communicates nothing clearly. A perceptive reader |
| 6 | or user feels this before they can name it. This skill makes the incoherence legible |
| 7 | so it can be fixed. |
| 8 | |
| 9 | --- |
| 10 | |
| 11 | ## Your Process |
| 12 | |
| 13 | **Step 1: State the Artefact and Its Intended Identity** |
| 14 | What is being examined — a product, document, strategy, brand, presentation, process? |
| 15 | What identity or effect is it supposed to produce? "Should feel authoritative but |
| 16 | approachable" or "Should communicate a single strategic bet" or "Should make a |
| 17 | first-time user feel capable in under three minutes." The intended identity is the |
| 18 | standard everything else will be measured against. |
| 19 | |
| 20 | **Framing check:** Confirm the specific artefact and its intended identity before continuing. State what you've identified — the actual object being analyzed and the identity or effect it is supposed to produce — in one sentence, then use `AskUserQuestion`: |
| 21 | - **Question:** "I'm reading this as: [your one-sentence framing of the artefact and its intended identity]. Is that right?" |
| 22 | - **Header:** "Framing" |
| 23 | - **Options:** |
| 24 | - **Yes — proceed** — framing is correct |
| 25 | - **Adjust** — one element is off; user will correct it before you continue |
| 26 | - **Reframe** — different situation than read; incorporate the correction before proceeding |
| 27 | |
| 28 | **Step 2: Examine Each Part** |
| 29 | Break the artefact into its major components. For each: what does it communicate? |
| 30 | What does it prioritise implicitly — speed vs depth, confidence vs humility, |
| 31 | complexity vs accessibility? What does it assume about the audience or context? |
| 32 | Extract these qualities as observations, not evaluations. |
| 33 | |
| 34 | **Step 3: Compare Parts to Each Other** |
| 35 | Where do assumptions conflict across parts? A section written for technical readers |
| 36 | next to one written for executives. A formal tone in one component, casual in another. |
| 37 | A design that prioritises simplicity in navigation but complexity in content. Name |
| 38 | the specific conflict, not just that something feels inconsistent. |
| 39 | |
| 40 | **Step 4: Compare Parts to the Whole** |
| 41 | Which parts are faithful to the intended identity? Which stray — and in what |
| 42 | direction? Is the straying random (different contributors with different instincts) |
| 43 | or directional (a competing version of what the thing should be is quietly winning |
| 44 | in parts of it)? |
| 45 | |
| 46 | **Step 5: Identify the Most Jarring Inconsistencies** |
| 47 | **Before narrowing:** Show the complete set of inconsistencies identified across Steps 3 and 4 to the user first. Use `AskUserQuestion`: |
| 48 | - **Question:** "I've identified [N] inconsistencies. Before I select the most damaging, are there any you'd flag as especially important, or any I've missed?" |
| 49 | - **Header:** "Prioritise" |
| 50 | - **Options:** |
| 51 | - **Proceed with your selection** — the set looks right |
| 52 | - **Flag one** — user will name a specific inconsistency to include |
| 53 | - **Add a missing one** — user will describe it |
| 54 | |
| 55 | Find 2-3 specific moments where the lack of coherence is most damaging — where a |
| 56 | perceptive reader or user would feel something is wrong, even if they can't say why. |
| 57 | Prioritise by impact on the intended identity. |
| 58 | |
| 59 | **Step 6: Recommended Adjustments** |
| 60 | For each jarring inconsistency: what specific change — to which part, in which |
| 61 | direction — would bring it into alignment with the intended identity? |
| 62 | |
| 63 | --- |
| 64 | |
| 65 | ## Human Check-in |
| 66 | |
| 67 | 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: |
| 68 | |
| 69 | - **Question:** "My read: [your 1–2 sentence interpretation]. How do you want to proceed?" |
| 70 | - **Header:** "Scope" |
| 71 | - **Options:** |
| 72 | - **Full analysis** — Complete all steps, reasoning shown throughout |
| 73 | - **Key findings only** — Bottom-line output, skip step-by-step detail |
| 74 | - **Incoherence only** — Where the parts fail to form a whole, skip confirming what works |
| 75 | - **Reframe** — The read is off; correct it and the analysis will follow the corrected framing |
| 76 | |
| 77 | Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis. |
| 78 | |
| 79 | ## Output Format |
| 80 | |
| 81 | **Intended Identity:** [what the artefact is supposed to be/feel/communicate] |
| 82 | |
| 83 | **Parts Assessed** |
| 84 | |
| 85 | | Part | What It Communicates | What It Prioritises | What It Assumes | |
| 86 | |---|---|---|---| |
| 87 | | [component] | [signal it sends] | [implicit value] | [audience/context assumption] | |
| 88 | |
| 89 | **Inconsistencies** |
| 90 | |
| 91 | | Inconsistency | What Conflicts | Why It Jars | Recommended Adjustment | |
| 92 | | |