vk-design-from-visual
Skill1 starsChanged 4 months agoApache-2.0View on GitHub
⚡⚡ Design from a screenshot / video / image / URL (--describe-only)
In this repository77 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- archifySkill
- banner-designSkill
- brandSkill
- chrome-devtoolsSkill
- code-reviewSkill
- computer-useSkill
- context-engine-debuggingSkill
- context-engine-exploringSkill
- context-engine-guideSkill
- context-engine-syncSkill
- debuggingSkill
- designSkill
- design-systemSkill
- docs-seekerSkill
- docxSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- kubernetesSkill
- planningSkill
- playwrightSkill
- repomixSkill
- researchSkill
- slidesSkill
- ui-ux-pro-maxSkill
- vk-askSkill
- vk-bootstrap-autoSkill
- vk-brainstormSkill
- vk-cloneSkill
- vk-contentSkill
- vk-cook-routerSkill
- vk-cookSkill
- vk-debugSkill
- vk-designSkill
- vk-docsSkill
- vk-docs-summarizeSkill
- vk-fix-fastSkill
- vk-fix-hardSkill
- vk-fixSkill
- vk-fix-sourceSkill
- vk-fix-typesSkill
- vk-fix-uiSkill
- vk-git-cmSkill
- vk-git-cpSkill
- vk-git-mergeSkill
- vk-git-prSkill
- vk-git-tagSkill
- vk-goalSkill
- vk-helpSkill
- vk-hoh-devSkill
- vk-hoh-planSkill
- vk-hoh-qaSkill
- vk-hoh-runSkill
- vk-integrate-polarSkill
- vk-integrate-sepaySkill
- vk-journalSkill
- vk-learnSkill
- vk-plan-archiveSkill
- vk-plan-fastSkill
- The first 60 shown.
The file
Files
Design From Visual
Reproduce the design in the reference material below. Auto-detect the input type — image / screenshot / PDF, video, or URL — per workflows/visual-input.md. One command for all three.
<reference>$ARGUMENTS</reference>
IMPORTANT: Activate the ui-ux-pro-max skill.
--describe-only → stop after step 3 and return the spec + plan; write no code.
Workflow
- Ingest the reference per
workflows/visual-input.md(images/PDFs read natively; video → frames; URL → screenshot, then read). - Describe in extreme detail with the
ui-ux-pro-maxskill, so a developer can implement it without ever seeing the original: design style, every element and its position, every interaction, animation, transition, color, border, icon, font family / size / weight, spacing, padding, margin, size, shape, texture, material, light, shadow, reflection, refraction, blur, glow, image, background transparency.- IMPORTANT: predict the real font name (Google Fonts) and font size — do NOT default to Inter or Poppins.
- Plan —
ui-ux-designersubagent writes an implementation plan so the final result matches the reference. Structure:skills/planning/references/plan-organization.md. - Implement the plan step by step. Pure HTML/CSS/JS unless the user specifies a stack.
- Report a brief summary; ask the user to review and approve. On approval, update
./docs/design-guidelines.mdif needed.
Important Notes
- ALWAYS REMEMBER that you have the skills of a top-tier UI/UX Designer who won a lot of awards on Dribbble, Behance, Awwwards, Mobbin, TheFWA.
- Raster-asset policy and asset verification:
workflows/visual-input.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.