Agent Skill
Critique skill
critiquenexu-io/open-designdesign-templates/critique/SKILL.md
Run a 5-dimension expert design review on any HTML artifact in the project — Philosophy / Visual hierarchy / Detail / Functionality / Innovation, each scored 0–10. Outputs a single self-contained HTML report with a radar chart, evidence-backed scores, and three lists: Keep / Fix / Quick-wins. Use when the brief asks for a "design review", "design critique", "5 维度评审", "design audit", or "what's wrong with my design".
always on
107 tokname + description
once used
2,211 tokSKILL.md body
bundled files
126 KB
repo stars
103kGitHub
Install the Critique skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/nexu-io/open-design --skill critique
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/nexu-io/open-design.git /tmp/open-design mkdir -p ~/.claude/skills cp -R /tmp/open-design/design-templates/critique ~/.claude/skills/critique
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 107 tok |
| When the agent uses it | The SKILL.md instructions | 2,211 tok |
| Only if opened | 1 bundled files (26 KB) | varies |
Until it is used, critique costs about 13× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 150 skills from nexu-io/open-design would load 9,514 tokens of descriptions. Skills vs MCP study
Checks
Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Critique Skill · 5 维度专家评审
- When to use
- What you produce
- The 5 dimensions
- 1. Philosophy consistency · 哲学一致性
- 2. Visual hierarchy · 视觉层级
- 3. Detail execution · 细节执行
- 4. Functionality · 功能性
- 5. Innovation · 创新性
- Scoring discipline (read before you score)
- Workflow
- Step 1 — Acquire the artifact
- Step 2 — Read enough to score
- Step 3 — Score with evidence
- Step 4 — Build the action lists
- Step 5 — Emit the report HTML
- Output contract
- Hard rules
More skills from nexu-io/open-design
- article-magazinenexu-io/open-design
Huashu / huashu-md-html-inspired magazine article layout for turning Markdown or notes into a polished long-form HTML essay.
103k30 tok idle · 207 in use - aster-ateliernexu-io/open-design
Use this template when the user wants an artistic creative-studio website with classical imagery, cobalt skies, elegant serif typography and cinematic scrolling.
103k31 tok idle · 539 in use - audio-jinglenexu-io/open-design
Audio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or AudioCraft. Output is one MP3/WAV file saved to the project folder.
103k78 tok idle · 942 in use - blog-postnexu-io/open-design
A long-form article / blog post — masthead, hero image placeholder, article body with figures and pull quotes, author byline, related posts. Use when the brief asks for "blog", "article", "post", "essay", or "case study".
103k57 tok idle · 570 in use - build-testnexu-io/open-design
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
103k31 tok idle · 607 in use - card-twitternexu-io/open-design
Twitter quote or data card designed to pair with a post.
103k15 tok idle · 151 in use - card-xiaohongshunexu-io/open-design
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.
103k24 tok idle · 266 in use - clinical-case-reportnexu-io/open-design
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds", "case summary", or "patient presentation".
103k73 tok idle · 1,806 in use