Help us improve
Share bugs, ideas, or general feedback.
From skills-for-humanity
Applies aesthetic reasoning to artifacts (design, writing, code, product). Routes to coherence, elegance, pattern, or simplicity analysis based on the situation.
npx claudepluginhub human-avatar/skills-for-humanityHow this skill is triggered — by the user, by Claude, or both
Slash command
/skills-for-humanity:aestheticThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
Tests whether a solution is more complex than necessary by auditing each element against the irreducible core.
Audits UI designs against Dieter Rams' ten good design principles, scores each with evidence, and hands off a verdict prompt for new design, refine, or redesign.
Audits taste and elegance of code, designs, architectures, APIs, and text by asking reflective questions that build user's self-judgment, without giving advice or evaluations.
Share bugs, ideas, or general feedback.
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.
| 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 |
After diagnosing which tool fits, use the AskUserQuestion tool to confirm direction. Construct the question dynamically to include your diagnosis:
Proceed based on their selection.
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.
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.
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.
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.