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 zaidmukaddam/skills --skill think-like-a-design-engineergit clone --depth 1 https://github.com/zaidmukaddam/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/zaidmukaddam/skills/think-like-a-design-engineer)<a href="https://agentmods.dev/skills/zaidmukaddam/skills/think-like-a-design-engineer"><img src="https://agentmods.dev/badge/skills/zaidmukaddam/skills/think-like-a-design-engineer/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/zaidmukaddam/skills/think-like-a-design-engineer"><img src="https://agentmods.dev/badge/skills/zaidmukaddam/skills/think-like-a-design-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 70 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00197 | $0.03819 |
| Opus 5 | $0.00098 | $0.01910 |
| Sonnet 5 | $0.00039 | $0.00764 |
| Haiku 4.5 | $0.00020 | $0.00382 |
Grade A, and why
think-like-a-design-engineer 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 12d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Think like a design engineer
The role is defined by a short loop. One person decides how something should work, builds it in the real medium, looks at the result, and changes it, without translating the idea through anyone else. Everything follows from that loop being short: fidelity is higher because nothing is lost in handoff, decisions are cheap to revisit, and the person who imagined the states is the person downstream of them.
The second thing to hold: the unit of ownership is the outcome, not the artifact. A finished mock, a merged diff, and a passing build are all intermediate. The question is whether the thing someone uses is right.
The third: the interface is not only the pixels. The words in the button, the path through it with a keyboard, and the state it shows when there is no data are all part of the same object, and a design engineer owns them together rather than passing them to someone else.
The moves
Decide the intent before touching pixels
Three answers come before layout, color, or type, and they should be specific enough to be wrong:
- Who is this person? Not "users." Someone at a particular moment. A teacher at 7am is not an on-call engineer at midnight, and the interface for one is wrong for the other.
- What must they accomplish? The verb. Approve the payment. Find the broken deploy. This decides what leads, what follows, and what hides.
- What should it feel like? In words that carry information. "Clean and modern" is what every generated answer says, so it constrains nothing. "Cold like a terminal," "dense like a trading floor," and "warm like a notebook" each rule things out.
Intent has to be systemic to count. Declaring "warm" and then shipping cold grays means the intent stayed in the prose and never reached the code. Check the tokens, surfaces, borders, semantic colors, and type against the stated feel, and change whatever disagrees.
Name the defaults you are rejecting
The strongest patterns hide in the parts that feel structural rather than designed. Typography reads like a container when it is the design. Navigation reads like scaffolding when it is the product. Token names read like implementation detail, but --ink and --parchment describe a world while --gray-700 describes nothing.
What ships with it
2 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.
- 12d ago First seen · 169 lines · 197 tokens per session scan A b7c815270333
think-like-a-design-engineer is a skill published in the GitHub repository zaidmukaddam/skills (18 stars, last pushed 16d ago), licensed MIT. It adds 197 tokens to every session and 3,819 once invoked, about $0.0010 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
animation-principles
Apply animation principles — easing, staging, follow-through — to one specific UI motion. Use when tuning how an animation feels. For product-wide duration and easing tokens use motion-system (design-systems); for a full interaction spec use micro-interaction-spec.
refactoring-ui
Audit and fix visual hierarchy, spacing, color, and depth in web UIs. Use when the user mentions "my UI looks off" (or amateur/unprofessional), "fix the design", "Tailwind styling", "color palette", "visual hierarchy", "design system", "spacing scale", or "component styling". Also trigger when building consistent…