s4h-aesthetic

Files (1)

• SKILL.md

SKILL.md (first lines)

# Aesthetic

Applies aesthetic reasoning to any artifact — design, writing, code, product, argument. Diagnoses what kind of aesthetic question is being asked and applies the right tool.

## Which tool fits

| You need to... | Tool |
|---|---|
| Check whether parts form a unified whole | coherence-check |
| Test whether something is more complex than it needs to be | elegance-testing |
| Name the underlying structural pattern at work | pattern-detection |
| Find the simpler version while preserving what matters | simplicity-analysis |

## Routing Decision

- **Something feels off, jarring, or inconsistent** → coherence-check
- **Something feels over-engineered or baroque** → elegance-testing
- **You want to understand *why* something works (or doesn't)** → pattern-detection
- **You want to strip something back to its core** → simplicity-analysis
- **Unclear** → start with coherence-check; it usually surfaces which other question needs answering

**Framing check:** Confirm the specific artifact before routing. State what you've identified — the actual object being analyzed and the aesthetic question being asked — in one sentence, then use `AskUserQuestion`:
- **Question:** "I'm reading this as: [your one-sentence framing of the artifact and the aesthetic question]. Is that right?"
- **Header:** "Framing"
- **Options:**
  - **Yes — proceed** — framing is correct
  - **Adjust** — one element is off; user will correct it before you continue
  - **Reframe** — different situation than read; incorporate the correction before proceeding

---

## Confirm Direction

After diagnosing which tool fits, use the `AskUserQuestion` tool to confirm direction. Construct the question dynamically to include your diagnosis:

- **Question:** "My read: **[diagnosed tool]** — [one sentence on why it fits]. How would you like to proceed?"
- **Header:** "Direction"
- **Options:**
  - **Yes, run that tool** — Execute the diagnosed skill immediately using the context already provided
  - **Show all options** — List every skill in this category with one-line descriptions
  - **Quick version** — Run a lighter-weight alternative if one exists for this situation
  - **Re-diagnose** — Revisit the situation description for a different read

Proceed based on their selection.

---

## Coherence Check

*Tests whether the parts form a unified whole.*

Map all major elements of the artifact. For each: what design decision does it express? Ask: are these decisions speaking the same language — or were they made independently, without reference to each other? Name each incoherence specifically. Classify: surface incoherence (fixable with small changes) vs. structural incoherence (requires rethinking something fundamental).

**Output:** List of incoherences ranked by severity. For each: what it is, where it appears, what it conflicts with, and how to resolve it.

---

## Elegance Testing

*Tests whether something is more complex than it needs to be.*

Separate necessary complexity (required by the problem) from accidental complexity (accreted over time, added as hedging, or left over from old requirements). For each layer of complexity: could the same job be done without it? What would be lost? Apply the minimum surface principle — is every part earning its place?

**Output:** Complexity audit — each complex element classified as necessary or accidental, with a cost estimate for removing it.

---

## Pattern Detection

*Identifies the underlying formal pattern.*

Look past the surface. What structural form does this follow? Name candidate patterns. Test each: does the structure actually match, or just superficially resemble it? Once identified: what does naming the pattern unlock? What's the established playbook for this form?

**Output:** Named pattern, evidence for the identification, what the pattern predicts or implies, and the playbook it suggests.

---

## Simplicity Analysis

*Finds the simpler version while preserving what matters.*

First: what is the core? The irreducible thing this artifact must do or be. Now audit everything else against that core: does each element serve it, or distract from it? For everything that doesn't serve the core, ask whether it was added for a reason that's still valid.

**Output:** What the core is. What can go. What should stay but be simplified. The simplest version that still does the full job.

From human-avatar/skills-for-humanity, MIT.

More from human-avatar/skills-for-humanity