docsor1212

Aesthete Agent — Data skill for Claude Code

Data community

Mechanically validated frontend aesthetics for AI agents: 89-palette evidence library, OKLCH generation, WCAG/APCA contrast, color-blind-safe data colors, AI-slop detection, theme packs, W3C design to.

How to install Aesthete Agent

This entry records only its repository, not the path inside it, so there is no exact command to give. Open docsor1212/aesthete-agent and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Aesthete Agent does

Alternatives in Data

Biopython — Bioinformatics tools with BioPython library 6.4k ★
Motion Skills — 50 open-source skills that teach your AI coding agent to make motion graphics, animation & video — kinetic typ 477 ★
Chart Design — Design a chart or data visualization — selects the right chart type, applies accessible color palettes, adds a 309 ★

README

English | 简体中文 | Online demo

aesthete-agent

**Mechanically validated frontend aesthetics for AI agents.** An agent skill (and MCP server) that plans, validates, and exports color systems — so your agent stops shipping purple-gradient AI slop and starts shipping palettes that pass WCAG, survive color-blindness, and read as designed.

[![install](https://img.shields.io/badge/install-npx%20skills%20add%20docsor1212%2Faesthete--agent-blue)](https://github.com/docsor1212/aesthete-agent) [![license](https://img.shields.io/badge/license-MIT-green)](LICENSE) [![palette library](https://img.shields.io/badge/palette%20library-119%20curated-orange)](#the-evidence-library) [![tests](https://img.shields.io/badge/tests-39%20passing-brightgreen)](tests/)

Why

LLMs choose colors badly for measurable reasons: they treat hex codes as text, they regress to the median of their training data (the frontend-tutorial median is purple/indigo), and they cannot see the colors they emit. `aesthete-agent` fixes this the engineering way — **outsource taste to process**:

an evidence library of 119 curated palettes filtered by objective quality gates (flat lightness → rejected; no readable text pair → rejected; color-blind collisions / slop signatures → flagged),
mechanical gates on every decision: a 5-dimension scorecard, exact WCAG 2.2 boundaries (APCA optional), three color-blindness simulations, AI-slop signature detection, a gradient ban (any gradient = P0), and an HTML delivery linter,
a six-step method (manifesto → register check → source → roles → validate → five-lens review) that turns "make it pretty" into a reproducible pipeline,
a preference profile (profile.json) that learns from every accept/reject verdict and mechanically down-ranks what the user rejects.