imagegen-frontend-web
Skill3 starsChanged 45 days agoMITView on GitHub
Generate premium horizontal website design-reference images for landing pages, marketing sites, and product pages. Use when the requested deliverable is web design imagery or when an image-first implementation workflow needs upstream section concepts. Produce images only, one standalone image per page section; do not write frontend code or mobile-app screens.
We split this skill into the rules it gives an agent
12 rules. 0 are common, 11 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 67 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Create a coherent set of implementation-ready website section images, not a compressed mood board.
- Distinctive: line 13
Never combine multiple sections into one tall board or tiny overview.
- Distinctive: line 14
Keep one palette, typography system, material language, and narrative spine across the set.
- Distinctive: line 25
Check legibility, realistic content density, CTA clarity, cross-section consistency, and composition variety.
- Distinctive: line 29
Keep the hero clean and readable.
- Distinctive: line 31
Do not repeat left-text/right-image layouts throughout the page.
- Distinctive: line 32
Use real visual hierarchy instead of filling every section with cards, badges, pills, or KPI tiles.
- Distinctive: line 33
Avoid generic AI-purple gradients, empty glass panels, fake dashboards, placeholder copy, and decorative noise.
- Distinctive: line 34
Use background imagery, texture, typography, and negative space intentionally.
- Distinctive: line 35
Keep all visible text short, plausible, and comfortably readable at the output resolution.
- Distinctive: line 39
Read only the relevant section of references/full-guide.md:
- Very specific: line 47
Use rg -n "<heading>" references/full-guide.md.
“Common” is measured: kept by at least 6 in 10 of the 67 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Frontend Web Image Direction
Create a coherent set of implementation-ready website section images, not a compressed mood board.
Output contract
- Generate one separate horizontal image for every requested section.
- Never combine multiple sections into one tall board or tiny overview.
- Keep one palette, typography system, material language, and narrative spine across the set.
- Make each image large enough to inspect and recreate accurately.
- Generate fresh section images; do not crop earlier outputs to simulate missing views.
- Return images only. Do not write code.
Workflow
- Infer audience, conversion goal, section list, brand constraints, and required visual tone.
- Define a compact design bible: palette, type character, imagery, surfaces, grid, CTA language, and recurring motif.
- Assign each section a distinct composition and purpose before generating.
- Generate sections individually in narrative order while carrying the same design bible forward.
- Check legibility, realistic content density, CTA clarity, cross-section consistency, and composition variety.
Composition rules
- Keep the hero clean and readable; match headline scale to copy length and leave the main CTA visible.
- Vary composition anchors: centered, split, off-grid, full-bleed, product-led, editorial, or data-led as the story requires.
- Do not repeat left-text/right-image layouts throughout the page.
- Use real visual hierarchy instead of filling every section with cards, badges, pills, or KPI tiles.
- Avoid generic AI-purple gradients, empty glass panels, fake dashboards, placeholder copy, and decorative noise.
- Use background imagery, texture, typography, and negative space intentionally; not every section needs a container.
- Keep all visible text short, plausible, and comfortably readable at the output resolution.
Detailed reference
Read only the relevant section of references/full-guide.md:
- Variation system and composition choices: search
COMBINATORIAL VARIATION ENGINE. - Hero constraints: search
HERO MINIMALISM RULES. - Section counting and sizing: search
IMAGE COUNT & PAGE SLICING. - Anti-slop, type, density, and material rules: search the corresponding heading.
- Standard page packs or examples: search
DEFAULT SITE PACKSorEXAMPLE INTERPRETATIONS.
Use rg -n "<heading>" references/full-guide.md; do not load the full guide unless the brief genuinely needs the complete art-direction system.
Other versions70 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 70
- caorushizi/mediago★ 9.3ksame name
- mxyhi/ok-skills★ 509same name
- hamzafarooq/claude-code-starter★ 145same name
- hushh-labs/hushh-research★ 39same name
- kresogalic8/unwatched★ 35same name
- jmxt3/gitscape.ai★ 33same name
- fathomise/MailFathom★ 20same name
- Krzysztof318/MailFathom★ 20same name
- ivanrvpereira/.agents★ 19same name
- rylsherdamz-rgb/stellar-forge★ 17same name
60 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use design-taste-frontend-v1, find-animation-opportunities and 8 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
HK-hubSkilldesign-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
Also in 30 projects that use this
wxyhgkSkillfind-animation-opportunities
Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use improve-animations or review-animations instead.
Also in 6 projects that use this
VercelSkillemil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
Also in 11 projects that use this
cal1888Skillpick-ui-library
Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.
Also in 4 projects that use this
arkanSkillreview-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
Also in 6 projects that use this
attentiondotnetSkillanimation-vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and wants the right word to prompt an AI or designer with. For naming an effect, not designing or building one.
Also in 5 projects that use this
In this repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/bro-skills.mdcCursor rule
- .agents/skills/llms.txtllms.txt
- brandkitSkill
- bro-mcp-loopSkill
- ci-security-scanning-with-strixSkill
- design-taste-frontendSkill
- fix-security-vulnerabilities-with-strixSkill
- full-output-enforcementSkill
- gpt-tasteSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- image-to-codeSkill
- industrial-brutalist-uiSkill
- managed-pentesting-with-strixSkill
- minimalist-uiSkill
- penetration-testing-with-strixSkill
- ponytailSkill
- redesign-existing-projectsSkill
- speckit.ai-engineerSkill
- speckit.analyzeSkill
- speckit.architectureSkill
- speckit.backendSkill
- speckit.backlogSkill
- speckit.checkerSkill
- speckit.checklistSkill
- speckit.clarifySkill
- speckit.constitutionSkill
- speckit.contentSkill
- speckit.databaseSkill
- speckit.dddSkill
- speckit.debugSkill
- speckit.devopsSkill
- speckit.diffSkill
- speckit.event-realtimeSkill
- speckit.frontendSkill
- speckit.game-embeddedSkill
- speckit.game-native-jsSkill
- speckit.geoSkill
- speckit.identity-accessSkill
- speckit.identitySkill
- speckit.implementSkill
- speckit.mapSkill
- speckit.migrateSkill
- speckit.payment-fintechSkill
- speckit.planSkill
- speckit.quizmeSkill
- speckit.reviewerSkill
- speckit.roadmapSkill
- speckit.securitySkill
- speckit.seoSkill
- speckit.specifySkill
- speckit.sre-observabilitySkill
- speckit.statusSkill
- speckit.tasksSkill
- speckit.taskstoissuesSkill
- speckit.testerSkill
- speckit.uatSkill
- The first 60 shown.
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.

