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 TIKAZI/TIKAZ-AI-Skills --skill frontend-designgit clone --depth 1 https://github.com/TIKAZI/TIKAZ-AI-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/tikazi/tikaz-ai-skills/frontend-design)<a href="https://agentmods.dev/skills/tikazi/tikaz-ai-skills/frontend-design"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/frontend-design/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/tikazi/tikaz-ai-skills/frontend-design"><img src="https://agentmods.dev/badge/skills/tikazi/tikaz-ai-skills/frontend-design.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 | $0.00054 | $0.00487 |
| Opus 5 | $0.00027 | $0.00244 |
| Sonnet 5 | $0.00011 | $0.00097 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
frontend-design 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design
Designed, integrated, refactored, and continuously maintained by TIKAZ.
Inputs and routing
Accept a product goal, target users, existing interface or repository, brand constraints, required states, target viewports, and delivery boundary. Use the orchestrator for design-to-engineering work; invoke frontend-design-studio directly when art direction, implementation, critique, audit, or polish is the whole task.
TIKAZ method
- Classify the surface as
Persuade,Operate,Read, orExperience; do not apply landing-page spectacle to every product. - Write one
Design Read, three project dials (variance,motion,density), one dominant composition, and three anti-goals. - Let
frontend-design-studioown art direction and implementation. Supporting skills cannot override the approved visual world. - Build an art-direction proof: navigation, first viewport, one representative downstream section, desktop and mobile together.
- Route repository-wide change impact to
code-intelligenceand production execution toengineering-deliveryonly after the design proof is approved. - Run separate visual/product and implementation QA passes.
Completion gate
Require a committed design contract, screenshot evidence at target viewports, critical states, reduced-motion behavior, build/test evidence, component license status, and a handoff with remaining limitations.
Output, fallback, and limits
Return the surface classification, Design Read, approved visual proof, implementation or audit result, responsive evidence, license notes, and remaining limitations. If a browser, renderer, or repository runtime is unavailable, stop at the last verifiable artifact and do not call an unrendered design visually approved. Preserve existing routes, analytics, accessibility, and legal copy unless change is authorized.
Example
Use frontend-design to redesign this operations dashboard, approve a desktop/mobile proof first, then implement and verify the responsive states.
What ships with it
24 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.
- agents/openai.yaml 272 B
- assets/workflow.svg 2.4 KB
- frontend-design-studio/agents/openai.yaml 317 B
- frontend-design-studio/assets/BRIEF.template.md 2.2 KB
- frontend-design-studio/assets/DESIGN.template.md 3.8 KB
- frontend-design-studio/assets/QA.template.md 2.9 KB
- frontend-design-studio/references/commands-and-prompts.md 2.6 KB
- frontend-design-studio/references/creative-direction.md 4.2 KB
- frontend-design-studio/references/design-contract.md 3.0 KB
- frontend-design-studio/references/fusion-and-conflicts.md 3.8 KB
- frontend-design-studio/references/lifecycle-gates.md 6.7 KB
- frontend-design-studio/references/motion-and-components.md 3.6 KB
- frontend-design-studio/references/platform-adapters.md 1.4 KB
- frontend-design-studio/references/qa-and-deployment.md 3.1 KB
- frontend-design-studio/references/research-sources.md 3.9 KB
- frontend-design-studio/references/visual-critique.md 3.4 KB
- frontend-design-studio/references/workflow.md 3.3 KB
- frontend-design-studio/scripts/audit_frontend.py 6.9 KB runs code
- frontend-design-studio/scripts/manage_frontend_project.py 30 KB runs code
- frontend-design-studio/SKILL.md 11 KB
- README.md 4.0 KB
- README.zh-CN.md 2.6 KB
- references/output-contract.md 390 B
- references/routing.md 677 B
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 · 38 lines · 54 tokens per session scan A 65a5910ff9dc
frontend-design is a skill published in the GitHub repository TIKAZI/TIKAZ-AI-Skills (6 stars, last pushed 9d ago), licensed MIT. It adds 54 tokens to every session and 487 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 2026-08-31.
Other skills, from other repositories
frontend-ui-ux-system
A company-level guide for designing web interfaces and user experiences. It covers visual styles, design tokens (named values for colors, spacing, and typography), layout, interaction, accessibility, motion, and review checks.
ui-design
Unify product UI design, frontend implementation, and verification. Use when asked to design, redesign, build, or fix a web, desktop, or mobile interface; a page, dashboard, form, component, design system, responsive layout, accessibility, interface animation, or editable hero/banner/infographic within a product…
frontend-design
A design guide for building polished web interfaces such as pages, dashboards, forms, navigation, and reusable UI components. It covers HTML, CSS, JavaScript, and common frontend frameworks.
anyui-template-authoring
Author and invoke high-quality, mobile-first AnyUI HTML templates for MioChat. Guides the creation of clean, responsive cards, game interfaces, forms, story choices, and Galgame/visual novel dialogue cards rendered via extraRender in Shadow DOM. Enforces decoupled zero-round-trip async image rendering (pure CSS…
21st-dev-components
Use when the user wants to build a React site or app section from 21st.dev components, clone the structure of a reference site with 21st.dev building blocks, browse 21st.dev manually and return copied prompts/code, or says things like "build me a site like this", "use 21st.dev", "copy prompt", "component URL", "hero…
frontend-ui
Use when designing web or mobile UI, creating prototypes, directing or engineering distinctive web experiences, structuring evidence-based web narratives, applying UI/UX guidance, using 21st.dev components, Stitch, or Figma.