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 tranfu-labs/tranfu-skills --skill visual-design-producergit clone --depth 1 https://github.com/tranfu-labs/tranfu-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/tranfu-labs/tranfu-skills/visual-design-producer)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/visual-design-producer"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/visual-design-producer/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/tranfu-labs/tranfu-skills/visual-design-producer"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/visual-design-producer.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 | $0.00153 | $0.01703 |
| Opus 5 | $0.00077 | $0.00851 |
| Sonnet 5 | $0.00031 | $0.00341 |
| Haiku 4.5 | $0.00015 | $0.00170 |
Grade A, and why
visual-design-producer 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 9d 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.
Visual Design Producer
Purpose
Produce original visual artifacts from the best available production input. Use a Producer Handoff first when present, use Visual DNA as abstract design direction when present, and operate from the user brief alone when no Visual DNA exists. Output HTML by default and add secondary formats only when requested.
Required Inputs
Require at least one production input:
Producer HandoffVisual DNA Design Systemor JSON/tokens representation- Standalone user brief or context
Optional:
- Target artifact type, when it is not obvious from the brief
- Brand context or brand guide
- Brand mode:
brandlessorbrand-on - Desired number of variations
- Specific output formats
- Required dimensions, platform, or channel
- Existing copy, content, or information architecture
If no production input exists, ask for the missing brief before producing.
Input Priority
Follow this priority exactly:
- If
Producer Handoffis present, use it as the primary production brief. - If absent but
Visual DNAis present, infer production direction from Visual DNA. - If no Visual DNA is present, operate in standalone production mode from the user brief.
Do not ask for Visual DNA when the user is clearly asking for standalone production.
Clarification Rule
Default to action. Ask at most one focused question only when missing information blocks production or would change the core artifact. If a safe assumption is available, state it briefly and continue.
Workflow
CREATE A TODO LIST FOR THE TASKS BELOW:
- Resolve the production input using the
Input Prioritysection. - Read any real target context the user provides, such as product code, screenshots, URLs, assets, copy, data, information architecture, or brand material. Treat Visual DNA as direction, not a substitute for this context.
- Read the Visual DNA and JSON/tokens when present. If tokens are missing, continue when the Markdown system has enough concrete design rules; ask only when token-level detail is essential.
- Read the new design brief and target artifact type. Infer missing noncritical details; ask one focused clarification question only when the route cannot be chosen safely.
- Resolve brand mode using
references/brand-integration-slot.md. - Select the artifact route using
references/artifact-router.md. - Create a new medium-specific visual system from the production input, new brief, real target context, and optional brand context.
- Generate original layout and visual directions. Do not treat source samples as templates.
- Produce HTML by default, following
references/html-engineering-spec.md. - Add user-requested secondary formats such as slide outline, CSS variables, copyable prompt, or export notes.
- Run the anti-slop quality gate in
references/anti-slop-quality-gate.md. - Deliver the HTML artifact, secondary outputs if any, and a brief quality-gate summary.
What ships with it
9 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.
- 9d ago First seen · 167 lines · 153 tokens per session scan A 984b51aedca5
visual-design-producer is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 153 tokens to every session and 1,703 once invoked, about $0.0008 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 2026-09-03.
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-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
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.