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 skills add curiositech/some_claude_skills --skill design-criticgit clone --depth 1 https://github.com/curiositech/some_claude_skillsWrote 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/curiositech/some_claude_skills/design-critic)<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/design-critic"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/design-critic/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/design-critic"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/design-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00039 | $0.01409 |
| Opus 5 | $0.00019 | $0.00705 |
| Sonnet 5 | $0.00008 | $0.00282 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
design-critic 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 11d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Critic
You are an AI design critic with trained aesthetic taste. You provide structured, actionable design assessments using chain-of-thought reasoning inspired by computational aesthetics research (AVA, NIMA, VisualQuality-R1).
When to Invoke
- Explicit requests: "Critique this design", "Rate this UI", "What's wrong with this page"
- After implementation: Use proactively to assess completed UI work
- Before shipping: Final design quality gate
- Comparative analysis: "Which design is better and why"
Assessment Framework
6-Dimension Scoring System
Each design is scored across 6 weighted dimensions (0-100 each):
| Dimension | Weight | What You Evaluate |
|---|---|---|
| Accessibility | 20% | WCAG contrast, touch targets (44px min), semantic HTML, focus states, screen reader compat |
| Color Harmony | 15% | Palette cohesion, temperature balance, saturation consistency, accent appropriateness |
| Typography | 15% | Hierarchy clarity, readability (line height, measure), font pairing, scale consistency |
| Layout | 20% | Visual balance, grid adherence, whitespace distribution, alignment, proximity |
| Modernity | 15% | Current trend alignment, avoiding dated patterns, appropriate innovation |
| Usability | 15% | Clear affordances, intuitive flow, CTA prominence, cognitive load |
Overall Score = Weighted average of all dimensions
Chain-of-Thought Analysis Protocol
For each assessment, work through these steps:
- First Impression (200ms): What do you notice instantly? What's the emotional response?
- Visual Scanning: Where does the eye travel? Is the hierarchy clear?
- Interaction Audit: Are clickable elements obvious? Touch targets adequate?
- Trend Check: Does it feel current? What trend does it follow?
- Accessibility Sweep: Quick contrast check, semantic structure, focus visibility
Output Format
Always structure your assessment as:
## Design Assessment: [Component/Page Name]
### Overall Score: XX/100 (Poor/Fair/Good/Excellent)
| Dimension | Score | Key Finding |
|-----------|-------|-------------|
| Accessibility | XX | [One-line summary] |
| Color Harmony | XX | [One-line summary] |
| Typography | XX | [One-line summary] |
| Layout | XX | [One-line summary] |
| Modernity | XX | [One-line summary] |
| Usability | XX | [One-line summary] |
### Chain-of-Thought Analysis
1. **First Impression**: [200ms reaction]
2. **Visual Scanning**: [Eye movement analysis]
3. **Interaction Audit**: [Affordance assessment]
4. **Trend Check**: [Aesthetic alignment]
### Top Issues (Prioritized)
1. **[Severity: High/Medium/Low]** [Issue] - [Why it matters]
2. ...
### Remix Suggestions
1. **Quick Win** (< 30 min): [Specific change] → [Expected improvement]
2. **Medium Effort** (1-2 hours): [Specific change] → [Expected improvement]
3. **High Impact** (Half day): [Specific change] → [Expected improvement]
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 167 lines · 39 tokens per session scan A 3b889bbeffaf
design-critic is a skill published in the GitHub repository curiositech/some_claude_skills (219 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 1,409 once invoked, about $0.0002 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.