Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/anthropics/knowledge-work-plugins/design-critiquenpx skills add anthropics/knowledge-work-plugins --skill design-critiquegit clone --depth 1 https://github.com/anthropics/knowledge-work-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/anthropics/knowledge-work-plugins/design-critique)<a href="https://agentmods.dev/skills/anthropics/knowledge-work-plugins/design-critique"><img src="https://agentmods.dev/badge/skills/anthropics/knowledge-work-plugins/design-critique.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00060 | $0.00917 |
| Opus 5 | $0.00030 | $0.00458 |
| Sonnet 5 | $0.00012 | $0.00183 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
design-critique scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-critique
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Get structured design feedback across multiple dimensions.
Usage
/design-critique $ARGUMENTS
Review the design: @$1
If a Figma URL is provided, pull the design from Figma. If a file is referenced, read it. Otherwise, ask the user to describe or share their design.
What I Need From You
- The design: Figma URL, screenshot, or detailed description
- Context: What is this? Who is it for? What stage (exploration, refinement, final)?
- Focus (optional): "Focus on mobile" or "Focus on the onboarding flow"
Critique Framework
1. First Impression (2 seconds)
- What draws the eye first? Is that correct?
- What's the emotional reaction?
- Is the purpose immediately clear?
2. Usability
- Can the user accomplish their goal?
- Is the navigation intuitive?
- Are interactive elements obvious?
- Are there unnecessary steps?
3. Visual Hierarchy
- Is there a clear reading order?
- Are the right elements emphasized?
- Is whitespace used effectively?
- Is typography creating the right hierarchy?
4. Consistency
- Does it follow the design system?
- Are spacing, colors, and typography consistent?
- Do similar elements behave similarly?
5. Accessibility
- Color contrast ratios
- Touch target sizes
- Text readability
- Alternative text for images
How to Give Feedback
- Be specific: "The CTA competes with the navigation" not "the layout is confusing"
- Explain why: Connect feedback to design principles or user needs
- Suggest alternatives: Don't just identify problems, propose solutions
- Acknowledge what works: Good feedback includes positive observations
- Match the stage: Early exploration gets different feedback than final polish
Output
## Design Critique: [Design Name]
### Overall Impression
[1-2 sentence first reaction — what works, what's the biggest opportunity]
### Usability
| Finding | Severity | Recommendation |
|---------|----------|----------------|
| [Issue] | 🔴 Critical / 🟡 Moderate / 🟢 Minor | [Fix] |
### Visual Hierarchy
- **What draws the eye first**: [Element] — [Is this correct?]
- **Reading flow**: [How does the eye move through the layout?]
- **Emphasis**: [Are the right things emphasized?]
### Consistency
| Element | Issue | Recommendation |
|---------|-------|----------------|
| [Typography/spacing/color] | [Inconsistency] | [Fix] |
### Accessibility
- **Color contrast**: [Pass/fail for key text]
- **Touch targets**: [Adequate size?]
- **Text readability**: [Font size, line height]
### What Works Well
- [Positive observation 1]
- [Positive observation 2]
### Priority Recommendations
1. **[Most impactful change]** — [Why and how]
2. **[Second priority]** — [Why and how]
3. **[Third priority]** — [Why and how]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 119 lines · 60 tokens per session scan A 3a4f260eb9f6
design-critique is a skill published in the GitHub repository anthropics/knowledge-work-plugins (23,849 stars, last pushed yesterday), licensed Apache-2.0. It adds 60 tokens to every session and 917 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
material-ui-tailwind
Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.
hallmark
Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
desktop-principles
Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.