good-css specimens

Good-css specimens provides opinionated modern CSS techniques packaged as an agent skill for AI agents.

Good-css specimens offers opinionated modern CSS techniques borrowed from experts, packaged as an agent skill. It is built for Claude Code, Codex, Cursor, and any other agent that reads skills. The platform features 47 live specimens across eight categories, including foundations, layout, spacing and shape, text and media, interaction, motion, show and hide, and scroll and viewport. It relies entirely on plain CSS with zero packages or class names to adopt. Users can install it as an agent skill or point their agent directly at the site.

good-css specimens at a glance

Best for: Software engineer
Runs on: Web
Pricing: Free
Released: October 2026
Category: AI coding tool
Website: good-css.com

Key features

Install as an agent skill
Browse 47 live specimens
Explore 8 CSS categories
Use plain CSS techniques
Apply modern reset rules
Utilize logical properties
Implement OKLCH color

Use it for

Equipping AI coding agents with modern CSS expertise
Applying expert-borrowed CSS techniques to projects
Adopting modern reset rules and logical properties

Alternatives to good-css specimens

Agent Skills — Encodes senior-engineer workflows and quality gates into 24 skills.
Pristine — Polishes web UI to a high standard using AI agent commands.
Agentation — It translates clicks into CSS selectors and source paths for agents.
Code Animation Prompts — It provides 341 code animation styles and 193 reference stills for AI coding assistants.
Greptile — Catches multi-file bugs by reviewing beyond the diff
jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
Skills — Provides specific agent skills for UI polish, color systems, and accessibility reviews.
Reviewer Agent — It uses a separate AI model to review code and prevent premature agent stopping.
Web Quality Skills — Optimizes web projects using Lighthouse audits and Core Web Vitals data.
Website Rebuild Skill — Provides line-level code traceability and automated multi-layer pixel accuracy.
Crit — It keeps human feedback localized and precise for AI agent code iterations.
agent.reviews — Real tool reviews written directly by coding agents after task completion.

All good-css specimens alternatives