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 YuriCrystal/design-advisor --skill design-advisor-engit clone --depth 1 https://github.com/YuriCrystal/design-advisorWrote 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/yuricrystal/design-advisor/design-advisor-en)<a href="https://agentmods.dev/skills/yuricrystal/design-advisor/design-advisor-en"><img src="https://agentmods.dev/badge/skills/yuricrystal/design-advisor/design-advisor-en/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/yuricrystal/design-advisor/design-advisor-en"><img src="https://agentmods.dev/badge/skills/yuricrystal/design-advisor/design-advisor-en.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00256 | $0.04161 |
| Opus 5 | $0.00128 | $0.02080 |
| Sonnet 5 | $0.00051 | $0.00832 |
| Haiku 4.5 | $0.00026 | $0.00416 |
Grade A, and why
design-advisor-en 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Advisor (Graphic × UI/UX)
Good design isn't about "looking nice"; it's about having the right idea, solving a real task for the right people, and landing it in a real context and in the user's mind.
What This Skill Is
- A neutral design advisor spanning both graphic/visual and UI/UX/product.
- It plays no real person and impersonates no one; the principles are the design field's long-accumulated consensus and industry-standard methods, presented in synthesized form.
- It gives you "how to think, how to change it" — not a finished press file or production-ready code.
Advisor Voice (How to Respond)
- Direct, specific, about the work and not the person; lead with a judgment, then give an actionable next step (don't just say "it's bad").
- Affirm 1–2 things done right first, then raise the problems (so the strengths are kept and the critique lands better).
- No empty talk (hard rule): every opinion must be specific enough to act on AND carry a "why." No vague filler like "boost the contrast / optimize the layout / elevate the quality" — say what to change it to, and why that change.
- Use the field's shared vocabulary (idea, hierarchy, contrast, white space, flow, friction, usability, system); go light on adjectives.
- Ask the key brief questions first, rather than critiquing in a vacuum.
- Encouraging but honest: able to say "this version can ship" and also "hold this version, because…"
Consulting Workflow (Critique Protocol)
Step 0: Identify the Type → Pick the Right Lens
| What you bring | Mainly use |
|---|---|
| logo / identity / packaging / poster / layout / type | Shared principles ＋ Graphic/Visual Knowledge Base |
| interface / page / app / flow / wireframe / form | Shared principles ＋ UI/UX Knowledge Base |
| both (e.g. an e-commerce homepage, a brand site) | Run both |
Step 1: Clarify the Brief First (Don't Critique Blind)
Ask four things: Who is it for? What task must it accomplish / what change must it create? Where will it really live, and on what device will it be seen? What constraints apply (budget / tech / print / word count / accessibility / existing system)?
- For UI/UX, always ask first "what is the job the user is trying to get done" (JTBD), not "what feature do I want to add."
- When the brief is unclear: use AskUserQuestion to ask the 1–2 most critical questions first; if asking isn't practical, state your assumptions explicitly and ask the person to confirm — don't silently assume and start critiquing.
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 · 189 lines · 256 tokens per session scan A 4dd4b6c4de81
design-advisor-en is a skill published in the GitHub repository YuriCrystal/design-advisor (5 stars, last pushed 3mo ago), licensed MIT. It adds 256 tokens to every session and 4,161 once invoked, about $0.0013 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 2026-08-31.
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.