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 wedabro/bro-skills --skill design-taste-frontendgit clone --depth 1 https://github.com/wedabro/bro-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/wedabro/bro-skills/design-taste-frontend)<a href="https://agentmods.dev/skills/wedabro/bro-skills/design-taste-frontend"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/design-taste-frontend/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/wedabro/bro-skills/design-taste-frontend"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/design-taste-frontend.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 | $0.00080 | $0.00895 |
| Opus 5 | $0.00040 | $0.00447 |
| Sonnet 5 | $0.00016 | $0.00179 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
design-taste-frontend 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Taste Frontend
Ship polished frontend code that fits the brief and the existing project. Treat every rule as contextual, not as a style preset.
Scope and precedence
- Use
image-to-codewhen an existing reference image must be reconstructed or the task explicitly requires an image-first workflow. - Use
imagegen-frontend-webwhen the deliverable is design imagery only. - Use
redesign-existing-projectswhen auditing and broadly upgrading an existing interface is the primary task. - Use this skill for new builds and focused frontend implementation work.
- Preserve the project's framework, design system, conventions, and working behavior unless the user requests a migration.
Workflow
- Inspect the brief, repository, existing UI, assets, dependencies, and responsive behavior.
- State one short design read: page kind, audience, visual direction, and implementation foundation.
- Choose a restrained system for type, color, spacing, radius, imagery, and motion. Reuse existing tokens and installed packages first.
- Implement the smallest coherent change that covers the whole page or requested surface.
- Verify desktop and mobile layout, interaction states, reduced motion, contrast, overflow, and build/tests.
Ask one clarifying question only when two materially different design directions remain plausible. Otherwise infer and proceed.
Non-negotiables
- Avoid templated defaults: purple glow, centered dark-mesh hero, repeated three-card rows, excessive glass, and uniform section rhythms.
- Keep one visual language per page: one palette, one radius system, one icon family, and consistent type hierarchy.
- Always prefer existing framework/theme classes such as
p-4,text-lg,gap-4, androunded-mdover arbitrary values. Usegap-4as the primary gap; smaller or larger gap classes require a clear hierarchy reason. Fixed-pixel exceptions are limited to hairline borders, blur/shadow tuning, and very small precision radii; promote repeated exceptions to named tokens. - Use cards only when grouping or elevation carries meaning. Prefer spacing, dividers, and composition otherwise.
- Give each section a distinct job and vary layout families; never repeat split-image rows more than twice consecutively.
- Keep the hero visible on a small laptop: concise headline, short supporting copy, and primary CTA above the fold.
- Use real or generated visual assets when imagery matters. Do not fake product screenshots with decorative divs.
- Use factual copy. Label sample data and never invent precise metrics, specifications, awards, or customer claims.
- Implement loading, empty, error, hover, focus, and active states when the surface requires them.
- Use CSS Grid for structural layouts and explicit mobile fallbacks for every multi-column section.
- Respect
prefers-reduced-motion; add motion only when it communicates hierarchy, story, feedback, or state. - Check installed dependencies before importing. Prefer native CSS and the existing stack over new packages.
- Audit visible copy, CTA contrast, focus states, navigation wrapping, overflow, and image alt text before finishing.
What ships with it
1 file 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 · 60 lines · 80 tokens per session scan A b2d275c34f85
design-taste-frontend is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 80 tokens to every session and 895 once invoked, about $0.0004 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
web-design-engineer
Build or redesign polished browser-rendered visual artifacts with HTML/CSS/JavaScript/React: pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations. Use for visual front-end creation, design-system exploration, design critique, or explicit browser acceptance / QA of a web artifact.…
webflow-mcp:interactions
Create, update, list, and delete Webflow IX3 interactions (GSAP animations) through Webflow MCP. Use when the user wants click/hover/load/scroll/mouse-move animations, interaction timelines, or datainteractionstool / createinteraction payloads. Requires beta MCP + ff-ix3-interaction-apis during dogfood.
webflow-mcp:flowkit-naming
Apply Flowkit CSS naming system in Webflow. Use when creating classes, auditing existing naming, or building new components following Flowkit conventions. Flowkit is Webflow's official CSS framework with utility-first approach. Runs headlessly against a page ID — no Designer connection required, except for the…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build landing pages, websites, dashboards, web components, or any frontend UI. Generates creative, polished code that avoids generic AI aesthetics.
ardot-style-guide
A design-system workflow for choosing and applying colors, fonts, spacing, and page layouts in Ardot projects.
slop-eval
Objectively evaluate a UI/web design against the pols.dev anti-slop design law: detect catalogued slop tells with cited evidence, score 8 weighted axes (color, type, components, layout, motion, execution, signature, cohesion), and emit a Slop Report with a 0–100 Slop Index and grade. Use when the user asks to…