$npx -y skills add human-avatar/skills-for-humanity --skill s4h-aesthetic-elegance-testingTests whether a solution is more complex than it needs to be — distinguishing necessary complexity from accidental complexity that accreted over time. TRIGGERS: 'elegance test', 'is this too complex', 'over-engineered', 'is there a simpler way', 'does this feel right'.
| 1 | # Aesthetic Elegance Testing |
| 2 | |
| 3 | Complexity is the default outcome of design by committee, incremental revision, and |
| 4 | deference to edge cases. Each addition is locally defensible. The cumulative result is |
| 5 | a system no one would have designed on purpose. Elegance is not simplicity for its own |
| 6 | sake — it is the property of a solution where every element earns its place and nothing |
| 7 | obscures the core. This skill tests for that property. |
| 8 | |
| 9 | --- |
| 10 | |
| 11 | ## Your Process |
| 12 | |
| 13 | **Step 1: State the Solution** |
| 14 | Describe the design, plan, system, or solution in enough detail to evaluate its parts. |
| 15 | If it's a process, name the steps. If it's a system, name the components. If it's a |
| 16 | strategy, name the moves. |
| 17 | |
| 18 | **Framing check:** Confirm the specific solution before continuing. State what you've identified — the actual artifact being tested and its apparent purpose — in one sentence, then use `AskUserQuestion`: |
| 19 | - **Question:** "I'm reading this as: [your one-sentence framing of the solution and what it is meant to accomplish]. 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: Define the Irreducible Core** |
| 27 | What is the minimum that does the job? State in one sentence what the solution must |
| 28 | accomplish to succeed. Every element that doesn't directly serve this core is a |
| 29 | candidate for removal. If you can't state the core in one sentence, the solution may |
| 30 | not have one — which is itself a finding. |
| 31 | |
| 32 | **Step 3: Element Audit** |
| 33 | For each component, mechanism, layer, or step: is it necessary for the core job, or |
| 34 | did it accrete over time to handle edge cases, satisfy stakeholder requests, hedge |
| 35 | against unlikely scenarios, or address problems that may not exist? Label each |
| 36 | clearly: **necessary** or **accreted**. |
| 37 | |
| 38 | **Step 4: Concept Count** |
| 39 | How many distinct concepts must a new person learn to understand and use this |
| 40 | solution fully? Elegant solutions have fewer. Count them explicitly. Compare against |
| 41 | the irreducible minimum — the number of concepts required if every accreted element |
| 42 | were removed. The gap is the complexity overhead. |
| 43 | |
| 44 | **Step 5: Thirty-Second Explanation Test** |
| 45 | Can you explain the solution in 30 seconds to someone intelligent but unfamiliar |
| 46 | with it? Attempt the explanation. If it requires more than 30 seconds, complexity |
| 47 | may be genuine — or it may be a sign the design hasn't been thought through clearly |
| 48 | enough to be simple. Both are worth knowing. |
| 49 | |
| 50 | **Step 6: Sources of Unnecessary Complexity** |
| 51 | For each accreted element: what introduced it, and what would removing it cost? Some |
| 52 | removals are free — the element was pure noise. Some involve real trade-offs — the |
| 53 | element serves a secondary purpose worth naming. Distinguish them explicitly. |
| 54 | |
| 55 | --- |
| 56 | |
| 57 | ## Human Check-in |
| 58 | |
| 59 | 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: |
| 60 | |
| 61 | - **Question:** "My read: [your 1–2 sentence interpretation]. How do you want to proceed?" |
| 62 | - **Header:** "Scope" |
| 63 | - **Options:** |
| 64 | - **Full analysis** — Complete all steps, reasoning shown throughout |
| 65 | - **Key findings only** — Bottom-line output, skip step-by-step detail |
| 66 | - **Accidental complexity only** — What could be removed without losing anything that matters |
| 67 | - **Reframe** — The read is off; correct it and the analysis will follow the corrected framing |
| 68 | |
| 69 | Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis. |
| 70 | |
| 71 | ## Output Format |
| 72 | |
| 73 | **Core Job:** [one sentence — what the solution must accomplish to succeed] |
| 74 | |
| 75 | **Element Audit** |
| 76 | |
| 77 | | Element | Necessary or Accreted | Rationale | |
| 78 | |---|---|---| |
| 79 | | [component/mechanism/step] | [necessary / accreted] | [why it does or doesn't serve the core] | |
| 80 | |
| 81 | **Concept Count:** [n currently required] vs [n at irreducible minimum] — overhead: [gap] |
| 82 | |
| 83 | **30-Second Explanation Test:** [pass / fail — include the actual attempt] |
| 84 | |
| 85 | **Sources of Unnecessary Complexity** |
| 86 | |
| 87 | | Accreted Element | How It Was Introduced | Cost of Removal | |
| 88 | |---|---|---| |
| 89 | | [element] | [origin] | [what is lost if removed] | |
| 90 | |
| 91 | **Recommended Simplifications:** [specific removals or reductions, with trade-offs named] |
| 92 | |
| 93 | --- |
| 94 | |
| 95 | ## Notes |
| 96 | |
| 97 | The question is not "can we defend every element" but "does every element earn its |
| 98 | place." Elements that can be defended are not the same as elements that are necessary |
| 99 | — hold the higher bar. Elegance is achieved not when there is nothing left to add, |
| 100 | but when there is nothing left to remove. |