Is the Styleseed Design Review skill free?

Yes. The skill itself is free from bitjaru/styleseed. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Styleseed Design Review SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Styleseed Design Review?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Styleseed Design Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Styleseed Design Review

Scores UI code 0-100 across 7 design axes and returns a line-cited, prioritized fix list

by bitjaru · bitjaru/styleseed

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 8f9bcc9

Fetched SKILL.md via the GitHub API/raw; frontmatter parses with name+description, and three referenced URLs (LICENSE, engine/RULESETS.md, plugin.json) all returned 200. Installed into a temp HOME cleanly (SKILL.md landed at ~/.claude/skills/styleseed-design-review/SKILL.md); no scripts, no security smells. For output I wrote a 32-line Dashboard.tsx seeded with AI-tells and produced two reviews: my baseline prose flagged most tells but gave no score, no line numbers, and no ordering, and missed the number/unit 2:1 issue and the un-carded table; the skill-rubric review scored it 38/100 F with per-category line-cited deductions and a fix list ordered by score gain (+17/+10/+9/+8).

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Styleseed Design Review does

Reviews React/Tailwind/HTML UI code against a seven-category rubric (coherence, color, hierarchy, layout, states, UX writing, motion), scores it 0-100, and returns a fix list ordered by score gain with cited line numbers. Triggers when an interface looks generic or AI-generated, when you want a pre-ship design score, or when asked to make UI look more polished. Self-contained rubric embedded in the SKILL body; it reviews and recommends but does not auto-edit.

How to install Styleseed Design Review

git clone --depth 1 https://github.com/bitjaru/styleseed.git /tmp/styleseed-design-review-src
mkdir -p ~/.claude/skills
cp -R /tmp/styleseed-design-review-src/skills/styleseed-design-review ~/.claude/skills/styleseed-design-review
# Self-contained: the full rubric lives in SKILL.md, no deps, no scripts, no API keys.
# Skill lives in a subdir of the repo; the full 74-rule reference and components stay in the cloned repo but are not required to run the review.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Styleseed Design Review

/styleseed-design-review Scores UI code 0-100 across 7 design axes and returns a line-cited, prioritized fix list

It also activates on plain-language prompts like these:

Why does this React UI look AI-generated
Score this Tailwind page before I ship it
Make this interface look designed, not generated

Frequently asked questions

Is the Styleseed Design Review skill free?: Yes. The skill itself is free from bitjaru/styleseed. SkillProof publishes the install command and an independent test verdict at no cost.
Does Styleseed Design Review work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md via the GitHub API/raw; frontmatter parses with name+description, and three referenced URLs (LICENSE, engine/RULESETS.md, plugin.json) all returned 200. Installed into a temp HOME cleanly (SKILL.md landed at ~/.claude/skills/styleseed-design-review/SKILL.md); no scripts, no security smells. For output I wrote a 32-line Dashboard.tsx seeded with AI-tells and produced two reviews: my baseline prose flagged most tells but gave no score, no line numbers, and no ordering, and missed the number/unit 2:1 issue and the un-carded table; the skill-rubric review scored it 38/100 F with per-category line-cited deductions and a fix list ordered by score gain (+17/+10/+9/+8).
What is the Styleseed Design Review SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Styleseed Design Review?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Styleseed Design Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.