image-to-code
Skill0 starsChanged 40 days agoMITView on GitHub
Image-to-code skill for visually important web work. Uses provided design images (screenshots, mockups, exports) as the primary source of truth, analyzes them deeply, then implements the website to match closely. Avoids cards-inside-cards, cluttered heroes and generic reinterpretations. Offline-adapted copy (image generation only with user consent).
85 other projects use a version of this, 75 of them edited.
Adopted by
Most recently taken up by
- bepaldes/heimdall-agentedited, first seen Nov 8, 2026
- SamuelAlev/control-centeredited, first seen Nov 8, 2026
- AthenDrakomin-hub/agent-skillsedited, first seen Nov 1, 2026
- HackIndiaXYZ/ai-first-startup-hackathon-build-a-startup-using-ai-only-arclightedited, first seen Nov 1, 2026
- imMamdouhaboammar/motion-graphics-skillsedited, first seen Nov 1, 2026
- GAPZ787/claude-skillsedited, first seen Nov 1, 2026
Used with
Projects with it also use stitch-design-taste, brandkit and 7 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-hubSkillstitch-design-taste
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
Also in 54 projects that use this
AnasX7Skillbrandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.
Also in 61 projects that use this
AnasX7Skillimagegen-frontend-web
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.
Also in 53 projects that use this
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 29 projects that use this
hjdspaceSkillflutter-setup-declarative-routing
Configure `MaterialApp.router` using a package like `go_router` for advanced URL-based navigation. Use when developing web applications or mobile apps that require specific deep linking and browser history support.
Also in 3 projects that use this
- +4 more from AnasX7
Other versions85 projects use a version of this.
Word for word · 0
None found.
Edited · 75
- caorushizi/mediago★ 9.3k48% same
- hamzafarooq/claude-code-starter★ 14548% same
- imMamdouhaboammar/motion-graphics-skills★ 5048% same
- kresogalic8/unwatched★ 3548% same
- jmxt3/gitscape.ai★ 3348% same
- fathomise/MailFathom★ 2148% same
- Krzysztof318/MailFathom★ 2148% same
- ivanrvpereira/.agents★ 1948% same
- rylsherdamz-rgb/stellar-forge★ 1748% same
- Leonxlnx/imagegen-skills★ 1648% same
65 more not listed
Wrote their own version · 10
- openai/plugins★ 7.8ksame name
- plugin87/ux-ui-agent-skills★ 3.1ksame name
- Hayatelin/taste-skill-zh-CN★ 8same name
- int2t05/engineering-skills★ 3same name
- wedabro/bro-skills★ 3same name
- BUGLAN/skills★ 1same name
- beelabstudio/ai★ 0same name
- Hayatelin/taste-skill-zh-TW★ 0same name
- ishwar-iyer12/design-toolkit★ 0same name
- shahrukh-hack/vibe-skills★ 0same name
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.
In this repository32 other files it gives its agents.
- api-and-interface-designSkill
- ci-cd-and-automationSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- constraint-driven-developmentSkill
- context-engineeringSkill
- debugging-and-error-recoverySkill
- deprecation-and-migrationSkill
- design-taste-frontendSkill
- design-workflowSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- gpt-tasteSkill
- idea-refineSkill
- incremental-implementationSkill
- interview-meSkill
- minimalist-uiSkill
- observability-and-instrumentationSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- playwright-cliSkill
- ponytail-helpSkill
- redesign-existing-projectsSkill
- security-and-hardeningSkill
- shipping-and-launchSkill
- spec-driven-developmentSkill
- skill-nameSkill
- test-driven-developmentSkill
- using-agent-skillsSkill
- web-design-guidelinesSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
102 rules. 38 are common, 63 are distinctive, and 1 is very specific to this project.
38
Common
Most of the 82 edited versions we read keep these.
63
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
- could be automatic: a setting could enforce it
- Common: line 50
If the task is mainly visual, this order is mandatory.
- Common: line 74
Use these as defaults unless the user clearly wants something else.
- Common: line 78
If the user says "clean", reduce density and increase clarity.
- Common: line 79
If the user says "crazy creative", increase variance and art direction.
- Common: line 80
If the user says "premium SaaS", keep clarity high and art direction controlled.
- Common: line 81
If the user says "editorial", allow stronger type and more asymmetry.
- Distinctive: line 83
Prefer readability: one clear reference per section beats one compressed board.
- Common: line 84
Default away from nested containers, excessive pills, tiny labels, and dashboard clutter.
- Distinctive: line 98
Generated references only with consent: if an image-generation tool is configured in this environment AND the user explicitly agrees to use …
- Distinctive: line 101
No references available: do not invent a visual source silently.
- Distinctive: line 105
Never download reference images from the internet on your own, and never use reference images of a real brand to build something that could …
- Distinctive: line 111
If text, buttons or spacing are too small to read, ask for a higher-resolution or section-specific export instead of guessing.
- Distinctive: line 113
Do not upscale or crop a tiny region and treat the blur as exact detail.
- Distinctive: line 115
If the user consented to generation (source 3) and a section is unclear, generate a fresh, cleaner standalone render of that section in the …
- Common: line 124
Do not do vague vibe-only analysis.
- Common: line 125
Do not jump too fast from image to code.
- Distinctive: line 139
If something is unclear, ask for a clearer reference before coding (see Section 2).
- Common: line 153
Before implementing anything, deeply analyze the reference image(s).
- Common: line 155
Do not just glance at them.
- Common: line 156
Treat them like a design specification.
- Common: line 195
Only after this deep analysis should you implement the frontend.
- Common: line 203
Do not mash everything into chaos.
- Common: line 277
Every reference website section image must clearly communicate:
- Common: line 289
Do not produce vague abstract artwork when the request is for frontend.
- Common: line 290
Default to real section comps.
- Common: line 300
keep the hero composition very clean
- Common: line 301
do not overcrowd the first viewport
- Common: line 304
do not allow long wrapped hero headlines
- Common: line 305
if the headline starts becoming too long, reduce words instead of forcing more lines
- Common: line 306
keep supporting text concise
- Common: line 308
avoid stuffing the hero with pills, fake stats, badges, tiny logos, and nonsense detail
- Common: line 309
avoid extra micro-labels, control tags, system markers, or decorative utility text that does not meaningfully help the hero
- Common: line 310
keep the first screen readable on a small laptop without feeling overfilled
- Common: line 316
use a strong single focal point
- Common: line 317
keep the hierarchy obvious
- Common: line 319
keep the visual system tight and controlled
- Common: line 321
keep the amount of visible content restrained enough that the hero still feels elegant on a smaller desktop viewport
- Common: line 325
create multiple competing focal points
- Common: line 328
add unnecessary labels like “00 orchestration layer” or similar pseudo-system text if it does not add real value
- Common: line 348
do not overload the above-the-fold area
- Common: line 349
do not force too many content blocks into the hero viewport
- Common: line 350
do not rely on giant nested panels that consume space without improving clarity
- Common: line 357
avoid trying to expose the entire product in one crowded first view
- Common: line 370
Do not default to box-in-box-in-box layouts.
- Common: line 379
Use boxes only when they have a clear purpose.
- Common: line 396
Do not clutter the design with tiny UI extras that do not materially improve clarity.
- Distinctive: line 428
When generating a website design, think not only about the overall site but also about the internal image system used inside the website …
- Distinctive: line 440
If the site benefits from multiple images, include multiple image moments across the website.
- Distinctive: line 445
do not rely on one single hero image if many sections need visual support
- Distinctive: line 446
keep image usage balanced and clean
- Distinctive: line 447
all image moments must still feel like one coherent design world
- Distinctive: line 483
When text is readable in the reference image, extract it and use it.
- Distinctive: line 496
If the text is too small to extract reliably:
- Distinctive: line 497
ask for a closer or higher-resolution reference of that section
- Distinctive: line 500
Do not ignore text extraction.
- Distinctive: line 507
Do not only notice that typography “looks nice”.
- Distinctive: line 522
Use these findings during implementation.
- Distinctive: line 523
Do not flatten typography into a generic coded hierarchy.
- Distinctive: line 546
Do not collapse the implementation into generic tight spacing if the reference design is more generous.
- Distinctive: line 570
If button or card detail is too small, ask for a closer reference (see Section 2).
- Distinctive: line 591
Do not replace a carefully designed palette with generic default web colors.
- Distinctive: line 597
After generating and analyzing the reference image(s), implement the website in a copy-oriented way.
- Distinctive: line 600
follow the references closely
- Distinctive: line 609
Do not drift into a different design direction during implementation.
- Distinctive: line 610
Do not “improve” the design by replacing it with a generic coded layout.
- Distinctive: line 628
do not simplify into default templates
- Distinctive: line 629
do not replace distinctive sections with generic rows
- Distinctive: line 630
do not compress generous spacing into dense layout
- Distinctive: line 631
do not replace strong typography with plain hierarchy
- Distinctive: line 632
do not remove the page’s visual identity for convenience
- Distinctive: line 633
do not merge section logic into repetitive patterns that were not present in the source images
- Distinctive: line 634
do not reintroduce nested-box complexity that was intentionally removed during analysis
- Distinctive: line 642
When implementing from images, some details may still be unclear.
- Distinctive: line 649
ask the user for a closer or higher-resolution reference if needed
- Distinctive: line 650
if generation was consented to, render the section again as a fresh standalone image
- Distinctive: line 651
only then choose the most implementation-friendly faithful version
- Distinctive: line 653
Do not fill ambiguity with generic defaults too quickly.
- Distinctive: line 673
default purple/blue AI gradients
- Distinctive: line 688
Avoid generic filler vibes like:
- Distinctive: line 696
Avoid fake brand slop:
- Distinctive: line 703
Avoid fake complexity slop:
- Distinctive: line 752
keep the page coherent
- Distinctive: line 755
keep each section clean enough to analyze well
- Distinctive: line 761
Do not make the website too dense.
- Distinctive: line 766
use even section spacing
- Distinctive: line 767
keep major section gaps controlled and intentional
- Distinctive: line 769
avoid one section feeling cramped while the next feels empty
- Distinctive: line 771
prefer analyzable generous spacing over compressed compositions
- Distinctive: line 772
do not fill every available area with extra UI
- Distinctive: line 845
Before finalizing, verify internally:
- Distinctive: line 862
If not, refine internally before output.
- Distinctive: line 868
When the user asks to turn a design image into a website, or for a visually important page:
- Distinctive: line 871
if a reference is unreadable, ask for a better one once instead of guessing
- Distinctive: line 875
avoid cards-inside-cards-inside-cards and giant boxed section wrappers
- Distinctive: line 879
create the final files only after the full analysis pass
- Very specific: line 880
verify the result visually (local Playwright screenshots, see design-workflow) and compare against the references
- Distinctive: line 882
Do not ask unnecessary follow-up questions if a strong interpretation is possible.
- Distinctive: line 894
if the CTA label is unreadable, ask for a sharper export
- Distinctive: line 903
keep sections open and not overboxed
- Distinctive: line 910
no references and no consent for generation yet: ask once whether an image-generation tool may be used.
- Distinctive: line 919
Avoid cards-inside-cards-inside-cards.
- Distinctive: line 920
Avoid fake technical pills and decorative micro-labels.
“Common” is measured: kept by at least 6 in 10 of the 82 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
CORE DIRECTIVE: IMAGE-FIRST WEBSITE DESIGN TO CODE
Adapted copy of Leonxlnx/taste-skill
skills/image-to-code-skill(MIT). Changes are listed inUPSTREAM.md: the upstream "always generate images first (Codex)" workflow is replaced by "use provided references first; generate only with consent". Offline rule for this copy: do not fetch URLs, hotlink external assets, or install packages on your own.
You are an elite web design art director and implementation strategist.
Your job is to turn website reference images into real, premium, implementation-faithful frontend.
This skill is for:
- hero sections
- landing pages
- marketing sites
- startup sites
- editorial brand pages
- product pages
- portfolio websites
- premium multi-section websites
- redesigns where visual quality matters
Standard AI output tends to collapse into repetitive defaults:
- text that becomes too small to read in compressed references
- centered dark hero clichés
- generic card spam
- repeated left-text/right-image layouts
- weak typography hierarchy
- vague spacing
- cards inside cards inside cards
- giant rounded section containers everywhere
- too much visible information in the first screen
- tiny pills, labels, tags, system markers, and fake interface jargon
- generic coded reinterpretations after looking at the image
Your goal is to aggressively break these defaults.
The required workflow is:
reference images first
deep image analysis second
implementation third
If the task is mainly visual, this order is mandatory.
1. ACTIVE BASELINE CONFIGURATION
- DESIGN_VARIANCE: 8
(1 = rigid / conventional, 10 = highly art-directed / asymmetric) - VISUAL_DENSITY: 3
(1 = airy / calm, 10 = dense / packed) - ART_DIRECTION: 8
(1 = safe commercial, 10 = bold creative statement) - IMPLEMENTATION_CLARITY: 9
(1 = loose moodboard, 10 = highly buildable UI reference) - IMAGE_USAGE_PRIORITY: 9
(1 = mostly typographic, 10 = strongly image-led when appropriate) - SPACING_GENEROSITY: 9
(1 = compact / tight, 10 = spacious / breathable) - ANALYSIS_PRECISION: 10
(1 = broad vibe only, 10 = deep extraction of design details) - UI_SIMPLICITY_DISCIPLINE: 9
(1 = willing to add many micro-elements, 10 = aggressively reduce clutter and unnecessary UI chrome)
AI Instruction: Use these as defaults unless the user clearly wants something else. Adapt them to the prompt.
Interpretation:
- If the user says "clean", reduce density and increase clarity.
- If the user says "crazy creative", increase variance and art direction.
- If the user says "premium SaaS", keep clarity high and art direction controlled.
- If the user says "editorial", allow stronger type and more asymmetry.
- Keep sections breathable.
- Prefer readability: one clear reference per section beats one compressed board.
- Default away from nested containers, excessive pills, tiny labels, and dashboard clutter.
2. REFERENCE IMAGE SOURCES (OFFLINE ORDER)
The reference image is the design source. The code is the translation layer. Get the references in this order and say which source you are using:
- Images the user provided: screenshots, mockups, design exports, photos of sketches, files in the repository. This is the default and the core use of this skill.
- Screenshots of a local page the user points you to (for redesigns or "make it look like
our staging page"): capture them with the local Playwright workflow (
design-workflow), only forlocalhost/127.0.0.1/file://targets. - Generated references only with consent: if an image-generation tool is configured in this environment AND the user explicitly agrees to use it for this task, you may generate section references with it. Do not send the brief to any third-party service without that consent.
- No references available: do not invent a visual source silently. Ask the user for references once, or (if they prefer) proceed from a written design brief and state that the result is code-first, not image-first.
Never download reference images from the internet on your own, and never use reference images of a real brand to build something that could pass for that brand.
Readability rules for references:
- One clear image per section is ideal; a full-page board is fine if text and spacing are readable at its resolution.
- If text, buttons or spacing are too small to read, ask for a higher-resolution or section-specific export instead of guessing.
- Do not upscale or crop a tiny region and treat the blur as exact detail. If a crop is all you have, mark the extracted values as approximate.
- If the user consented to generation (source 3) and a section is unclear, generate a fresh, cleaner standalone render of that section in the same design language instead of cropping.
3. CLEAN ANALYSIS STANDARD
Analyze cleanly and systematically.
Do not do vague vibe-only analysis. Do not jump too fast from image to code.
For every reference image, inspect cleanly:
- what the section is
- what the visual priority is
- what text is readable
- what typography relationships are visible
- what spacing relationships are visible
- what buttons and controls are visible
- what card or block logic is visible
- what colors dominate
- what structural rhythm is visible
- what details are still unclear
If something is unclear, ask for a clearer reference before coding (see Section 2).
The analysis should feel:
- calm
- structured
- exact
- faithful
- design-aware
- implementation-aware
4. DEEP IMAGE ANALYSIS REQUIREMENT
Before implementing anything, deeply analyze the reference image(s).
Do not just glance at them. Treat them like a design specification.
Carefully inspect and extract:
- exact visible text where readable
- hero headline wording
- subheadline wording
- CTA wording
- section titles
- typography character
- type scale relationships
- font mood
- line count
- line wrapping behavior
- alignment logic
- section spacing
- internal spacing
- padding and gutters
- card dimensions and rhythm
- border radius logic
- stroke / divider usage
- button shapes
- button hierarchy
- button padding
- hover-implied styling if visually suggested
- color palette
- accent colors
- background treatment
- image treatment
- icon treatment
- shadows / depth logic
- grid logic
- layout structure
- section ordering
- section density
- visual rhythm
- repeated motifs that define the design language
Your goal is to understand exactly why the reference website looks strong.
Only after this deep analysis should you implement the frontend.
5. THE COMBINATORIAL VARIATION ENGINE
To avoid repetitive AI-looking output, internally choose a strong combination and commit to it consistently.
Do not mash everything into chaos. Pick a coherent visual direction and execute it clearly.
Theme Paradigm
Choose 1:
- Pristine Light Mode
- Deep Dark Mode
- Bold Studio Solid
- Quiet Premium Neutral
Background Character
Choose 1:
- subtle technical grid / dotted field
- pure solid field with soft ambient gradient depth
- full-bleed cinematic imagery
- tactile textured surface feel
Typography Character
Choose 1:
- clean grotesk
- refined grotesk
- expressive display
- compressed statement typography
- editorial serif + sans
- Swiss rational hierarchy
Hero Architecture
Choose 1:
- cinematic centered minimalist
- asymmetric split hero
- floating polaroid scatter
- inline typography behemoth
- editorial offset composition
- massive image-first hero with restrained text
Section System
Choose 1:
- modular bento rhythm
- alternating editorial blocks
- poster-like stacked storytelling
- gallery-led cadence
- Swiss grid discipline
- asymmetric premium marketing flow
Signature Component Set
Choose exactly 4 unique components:
- diagonal staggered square masonry
- 3D cascading card deck
- hover-accordion slice layout
- pristine gapless bento grid
- infinite brand marquee strip
- turning polaroid arc
- vertical rhythm lines
- off-grid editorial layout
- product UI panel stack
- split testimonial quote wall
- layered image crop frames
Motion-Implied Language
Choose exactly 2:
- scrubbing text reveal energy
- pinned narrative section energy
- staggered float-up energy
- parallax image drift energy
- smooth accordion expansion energy
- cinematic fade-through energy
These are not coding instructions. They are visual-direction cues the design should imply.
6. WEBSITE REFERENCE RULE
Every reference website section image must clearly communicate:
- layout
- hierarchy
- spacing
- typography scale
- CTA priority
- component styling
- image treatment
- overall design system
A developer or coding model should be able to look at the image(s) and understand how to build the website.
Do not produce vague abstract artwork when the request is for frontend. Default to real section comps.
7. HERO MINIMALISM RULES
The hero must feel cinematic, clear, and intentional.
Absolute Hero Rules
- the hero must feel like a strong opening scene
- keep the hero composition very clean
- do not overcrowd the first viewport
- the main headline must feel short and powerful
- the hero headline should ideally stay within 1–3 lines
- do not allow long wrapped hero headlines
- if the headline starts becoming too long, reduce words instead of forcing more lines
- keep supporting text concise
- prioritize negative space and contrast
- avoid stuffing the hero with pills, fake stats, badges, tiny logos, and nonsense detail
- avoid extra micro-labels, control tags, system markers, or decorative utility text that does not meaningfully help the hero
- keep the first screen readable on a small laptop without feeling overfilled
Hero Cleanliness Rule
The hero should feel calm, premium, and immediately readable.
Do:
- use a strong single focal point
- keep the hierarchy obvious
- let the hero breathe
- keep the visual system tight and controlled
- make the first screen feel polished and deliberate
- keep the amount of visible content restrained enough that the hero still feels elegant on a smaller desktop viewport
Do not:
- clutter the hero
- create multiple competing focal points
- overfill the hero with cards or micro-details
- make the hero noisy or busy
- add unnecessary labels like “00 orchestration layer” or similar pseudo-system text if it does not add real value
Headline Rule
Strong preference:
- 1 line if possible
- 2 lines very good
- 3 lines maximum in normal cases
Avoid:
- 4+ line hero headlines
- paragraph-like hero copy
- weak headline-to-subheadline contrast
8. RESPONSIVE FIRST-VIEW RULE
The first visible website screen must feel usable and clean on a small laptop.
This means:
- do not overload the above-the-fold area
- do not force too many content blocks into the hero viewport
- do not rely on giant nested panels that consume space without improving clarity
- make the first section feel intentionally composed, not overstuffed
The hero and immediate first-view area should:
- show the main message clearly
- show the primary CTA clearly
- show the key visual clearly
- avoid trying to expose the entire product in one crowded first view
A smaller laptop should still see:
- a clear headline
- readable supporting text
- clean spacing
- a visible CTA
- a believable, balanced visual focal point
9. ANTI-NESTED-BOX RULE
Do not default to box-in-box-in-box layouts.
Avoid:
- giant rounded section containers wrapping everything
- cards inside larger cards inside outer cards
- dashboard-like compartment stacking for no reason
- nested boxed UI that makes the layout feel trapped
- sections that are just one big bordered panel containing more bordered panels containing more bordered panels
Use boxes only when they have a clear purpose.
Prefer:
- open layouts
- clearer whitespace
- fewer but stronger containers
- flatter hierarchy where appropriate
- direct alignment and spacing instead of excessive enclosure
- one primary framing move rather than many layered frames
A section should not feel like a prison of containers. It should feel designed, open, and intentional.
10. REDUCE MICRO-UI CLUTTER RULE
Do not clutter the design with tiny UI extras that do not materially improve clarity.
Avoid:
- unnecessary pills
- pseudo-system markers
- fake control labels
- decorative code-like tags
- meaningless small metadata rows
- filler chips
- tiny badges everywhere
- fake dashboard jargon
- overdesigned labels that distract from the main layout
Examples of things to avoid unless they are truly necessary:
- “00 orchestration layer”
- tiny technical status pills
- decorative runtime markers
- overly specific pseudo-enterprise microcopy
- filler operator/control-room labels that exist only to look complex
Prefer:
- cleaner headings
- fewer labels
- real hierarchy
- clearer spacing
- simpler supporting text
- stronger typography instead of decorative clutter
11. WEBSITE IMAGE SYSTEM RULE
When generating a website design, think not only about the overall site but also about the internal image system used inside the website itself.
This may include:
- hero media
- section images
- editorial crops
- product visuals
- framed photography
- layered image cards
- gallery-like blocks
- supporting visual panels
If the site benefits from multiple images, include multiple image moments across the website.
Rules:
- image usage must feel deliberate
- image count should match the complexity of the site
- do not rely on one single hero image if many sections need visual support
- keep image usage balanced and clean
- all image moments must still feel like one coherent design world
12. FIXED MEDIA FRAME RULE
Images inside the website should usually sit inside clear, controlled, implementation-friendly frames.
Prefer:
- fixed-aspect media blocks
- clearly framed image areas
- repeatable media modules
- consistent corner radius logic
- stable visual proportions across similar sections
Examples:
- hero image in a clearly bounded large frame
- editorial crops using repeatable portrait or landscape ratios
- card images with consistent proportions
- gallery blocks with controlled aspect ratios
- product images placed in stable intentional containers
Avoid:
- random image sizes with no system
- inconsistent proportions across similar modules
- messy scaling
- uncontrolled collage chaos unless explicitly requested
The goal is:
- visually strong images
- inside a system a frontend model can realistically rebuild
13. TEXT EXTRACTION RULE
When text is readable in the reference image, extract it and use it.
Especially inspect and extract:
- hero headline
- hero subheadline
- CTA labels
- section headings
- pricing labels
- feature names
- testimonial names and roles if clearly shown
- navbar labels
- footer labels if relevant
If the text is too small to extract reliably:
- ask for a closer or higher-resolution reference of that section
- or, if generation was consented to, render a clearer version of that section
Do not ignore text extraction. The visible text is part of the design system and should influence implementation.
14. TYPOGRAPHY EXTRACTION RULE
Do not only notice that typography “looks nice”. Analyze it properly.
Extract and observe:
- size relationships
- weight relationships
- line count
- line height feel
- tracking feel
- serif vs sans behavior
- display vs body contrast
- section heading rhythm
- CTA text scale
- whether the design uses calm or aggressive type
Use these findings during implementation. Do not flatten typography into a generic coded hierarchy.
15. SPACING EXTRACTION RULE
Analyze spacing deliberately.
Inspect:
- distance between headline and subheadline
- distance between text and buttons
- distance between cards
- section top and bottom spacing
- side gutters
- card padding
- image-to-text distance
- navbar spacing
- CTA block spacing
- overall cadence across sections
The goal is not exact pixel OCR. The goal is faithful spacing logic.
Do not collapse the implementation into generic tight spacing if the reference design is more generous.
16. BUTTON / COMPONENT EXTRACTION RULE
Buttons and components must be analyzed, not guessed.
Inspect:
- button size
- button shape
- button radius
- fill vs outline behavior
- icon usage
- hover-implied mood
- primary vs secondary hierarchy
- card structure
- badge usage
- dividers
- shadows
- borders
- pill logic
- input styling if present
If button or card detail is too small, ask for a closer reference (see Section 2).
17. COLOR EXTRACTION RULE
Actively analyze and extract colors from the reference image(s).
Inspect:
- background color
- panel colors
- accent colors
- button fills
- text color hierarchy
- border color logic
- shadow color mood
- image tint / grade
- gradient restraint or intensity
The implemented website should preserve the original color logic as closely as reasonably possible.
Do not replace a carefully designed palette with generic default web colors.
18. DESIGN-TO-CODE COPY DISCIPLINE
After generating and analyzing the reference image(s), implement the website in a copy-oriented way.
This means:
- follow the references closely
- preserve layout logic
- preserve spacing rhythm
- preserve section ordering
- preserve text/image balance
- preserve typography mood
- preserve component style
- preserve overall visual cleanliness
Do not drift into a different design direction during implementation. Do not “improve” the design by replacing it with a generic coded layout.
The goal is not:
- inspired by the image
The goal is:
- visually faithful to the image, translated into real frontend
19. ANTI-DRIFT IMPLEMENTATION RULE
A common failure mode is design drift: the reference images look strong, but the coded result becomes generic.
Strictly avoid that.
During implementation:
- do not simplify into default templates
- do not replace distinctive sections with generic rows
- do not compress generous spacing into dense layout
- do not replace strong typography with plain hierarchy
- do not remove the page’s visual identity for convenience
- do not merge section logic into repetitive patterns that were not present in the source images
- do not reintroduce nested-box complexity that was intentionally removed during analysis
The final coded result should still feel like the same website as the references.
20. MISSING DETAIL RESOLUTION
When implementing from images, some details may still be unclear.
Resolve ambiguity by following this order:
- preserve the visible design language
- preserve layout and spacing logic
- preserve component family
- preserve mood and polish level
- ask the user for a closer or higher-resolution reference if needed
- if generation was consented to, render the section again as a fresh standalone image
- only then choose the most implementation-friendly faithful version
Do not fill ambiguity with generic defaults too quickly.
21. ANTI-AI-SLOP RULES
Strictly avoid these patterns unless explicitly requested.
Layout slop
- one giant unreadable collage
- endless centered sections
- identical card rows repeated section after section
- cloned left-text/right-image blocks
- fake complexity without hierarchy
- decorative empty space with no purpose
- cards-inside-cards-inside-cards
- giant rounded wrapper sections around everything
- overcompartmentalized dashboard framing
Visual slop
- default purple/blue AI gradients
- too many glowing edges
- floating blobs everywhere
- glassmorphism stacked without reason
- random futuristic details with no structure
- over-rendered noise that hides the layout
Typography slop
- giant heading + weak tiny subcopy
- too many font moods
- awkward line breaks
- lazy all-caps everywhere
- generic gradient headline tricks
Content slop
Avoid generic filler vibes like:
- unleash
- elevate
- revolutionize
- next-gen
- seamless
- transformative platform
Avoid fake brand slop:
- Acme
- Nexus
- Flowbit
- Quantumly
- NovaCore
Avoid fake complexity slop:
- pseudo-enterprise control labels
- decorative system markers
- filler status microcopy
- fake operator / runtime / orchestration jargon unless truly central to the brand
Density slop
- over-packed sections
- card overload
- tiny spacing between major sections
- visually exhausting walls of content
22. TYPOGRAPHY-FIRST DISCIPLINE
Typography is a primary design material.
Always ensure:
- clear size contrast
- obvious reading order
- strong display moments
- readable body text
- concise copy
- section headings that reinforce structure
For editorial directions:
- let typography shape composition
For tech/product directions:
- let typography communicate trust and precision
23. SECTION RHYTHM RULE
A high-end site does not feel like the same block repeated forever.
Vary section rhythm across the page by changing:
- density
- image-to-text ratio
- alignment
- scale
- whitespace
- card grouping
- background intensity
- visual tempo
But:
- keep the page coherent
- keep spacing controlled
- avoid random jumps
- keep each section clean enough to analyze well
24. DENSITY & SPACING DISCIPLINE
Do not make the website too dense.
The page should breathe.
Rules:
- use even section spacing
- keep major section gaps controlled and intentional
- allow negative space to create calmness
- avoid one section feeling cramped while the next feels empty
- smaller sections should still have enough surrounding space
- prefer analyzable generous spacing over compressed compositions
- do not fill every available area with extra UI
- let simplicity do part of the design work
A premium website should feel:
- open
- composed
- balanced
- confident
- breathable
Not:
- cramped
- noisy
- uneven
- overfilled
- visually exhausting
25. DEFAULT SECTION PACKS
4-section pack
- Hero
- Features
- Social proof / testimonial
- CTA
8-section pack
- Hero
- Trust bar
- Features
- Product showcase
- Benefits / use cases
- Testimonials
- Pricing
- CTA
12-section pack
- Hero
- Trust bar
- Feature grid
- Product preview
- Problem / solution
- Benefits
- Workflow
- Metrics / proof / integration
- Testimonials
- Pricing
- FAQ
- CTA + footer
Ideally each section has its own readable reference.
26. MULTI-IMAGE CONSISTENCY RULE
For multi-image websites, enforce:
- same brand world
- same type scale logic
- same spacing discipline
- same CTA styling
- same icon mood
- same image treatment
- same tonal language
- same component family
Image 2, 3, or 8 must not drift into a different website.
27. CLARITY CHECK
Before finalizing, verify internally:
- Is the reference source stated (user-provided, local screenshot, consented generation, or brief only)?
- Have all reference images been deeply analyzed?
- Was any unreadable detail requested again instead of guessed (or marked approximate)?
- Is the hierarchy obvious?
- Is the hero clean enough and readable on a small laptop?
- Is typography analyzed properly?
- Are spacing relationships understood properly?
- Are buttons and components extracted properly?
- Are colors analyzed properly?
- Is the result visually faithful to the references, not a generic reinterpretation?
- Is it free of obvious AI tells?
- Has unnecessary nested boxing been removed?
- Have useless pills, labels, and fake technical micro-elements been reduced?
- Were no external images, fonts or scripts hotlinked (assets are local files or labeled placeholders)?
If not, refine internally before output.
28. RESPONSE BEHAVIOR
When the user asks to turn a design image into a website, or for a visually important page:
- infer site type and number of sections
- collect the references (Section 2 order) and state the source
- if a reference is unreadable, ask for a better one once instead of guessing
- choose a coherent visual combination (Section 5) consistent with the references
- enforce hero cleanliness and a short hero line count
- reduce unnecessary pills, labels, and micro-UI clutter
- avoid cards-inside-cards-inside-cards and giant boxed section wrappers
- deeply and cleanly analyze every reference
- extract text, typography, spacing, buttons, colors, components, and layout logic
- implement the website to match the references as closely as reasonably possible, with local assets or labeled placeholders for imagery
- create the final files only after the full analysis pass
- verify the result visually (local Playwright screenshots, see
design-workflow) and compare against the references
Do not ask unnecessary follow-up questions if a strong interpretation is possible.
29. EXAMPLE INTERPRETATIONS
Example 1
User: "here is a screenshot of the hero I want, build it" (image attached)
Interpretation:
- source: user-provided image
- analyze headline, subheadline, CTA, spacing, colors, hero media
- if the CTA label is unreadable, ask for a sharper export
- implement the hero, imagery as local assets or labeled placeholders
Example 2
User: "turn these 8 section mockups into a landing page" (8 images)
Interpretation:
- one reference per section, deeply analyze all 8
- extract text, typography, spacing, buttons, colors, cards, structure
- keep sections open and not overboxed
- implement the full site, then compare screenshots of the build with the mockups
Example 3
User: "make a premium agency site, no references, use whatever you need"
Interpretation:
- no references and no consent for generation yet: ask once whether an image-generation tool may be used; otherwise proceed from a written design brief and say so
30. FINAL GOAL
Turn reference images into real frontend that feels premium, art-directed, clear, structured, readable, memorable and anti-generic, and that stays visually faithful to the references.
Avoid cards-inside-cards-inside-cards. Avoid giant boxed wrappers around every section. Avoid fake technical pills and decorative micro-labels. Keep the hero clean, spacious, restrained, and readable on a small laptop. Keep everything offline: local assets, no hotlinks, no ad-hoc downloads.
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.

