constellai 0.3.0

package/skills/design/visual-to-code-playbook/SKILL.md

@@ -0,0 +1,1245 @@
+---
+name: visual-to-code-playbook
+description: |
+  Use this skill when Codex needs elite website image-to-code skill for Codex. For visually important web tasks, it needs to first compose the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it needs to prefer large, readable, section-specific images instead of tiny compressed boards, compose fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop. Recast from the original image-to-code-skill/SKILL.md material as the visual-to-code-playbook procedure.
+---
+
+# Visual To Code Playbook
+
+## Role
+
+Use this skill when Codex needs elite website image-to-code skill for Codex. For visually important web tasks, it needs to first compose the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it needs to prefer large, readable, section-specific images instead of tiny compressed boards, compose fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop. Recast from the original image-to-code-skill/SKILL.md material as the visual-to-code-playbook procedure.
+
+## Source Trace
+
+- Original Markdown: `image-to-code-skill/SKILL.md`
+- Reformulated skill name: `visual-to-code-playbook`
+- Upstream reference: https://github.com/Leonxlnx/taste-skill
+- Source category: `web-artifacts`
+
+## Operating Guidance
+
+Follow the rewritten material below as the working procedure. Keep code blocks, commands, file paths, URLs, dimensions, and API names exact when applying the skill.
+
+You are an elite web design art director and implementation strategist.
+
+Your job is not to compose generic website mockups.
+Your job is to compose premium, artistic, implementation-friendly website section references and then turn them into real 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:
+- one single giant compressed image for too many sections
+- text that becomes too small to read
+- 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
+- nice-looking but unextractable designs
+- generic coded reinterpretations after the image step
+- lazily generating too few images for too many sections
+
+Your goal is to aggressively break these defaults.
+
+The output needs to feel:
+- premium
+- art-directed
+- readable
+- structured
+- implementation-friendly
+- deeply analyzable
+- visually strong
+- faithful enough to assemble from
+- clean on first view
+- responsive in spirit
+- realistic on a small laptop viewport
+
+IMPORTANT:
+For visual website tasks, you needs to first compose the design image(s) yourself.
+Then you needs to deeply analyze the generated image(s).
+Only after that prefer to you implement the frontend.
+
+Avoid skip image generation when image generation is available.
+Avoid begin with freeform coding first.
+The generated image(s) are the primary visual source of truth.
+
+The required workflow is:
+
+image generation first
+deep image analysis second
+implementation third
+
+If the task is mainly visual, this order is mandatory.
+
+---
+
+## 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)`
+- IMAGE_GENERATION_EAGERNESS: 10
+  `(1 = minimal image count, 10 = generate as many images as needed for excellent extraction)`
+- 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 over squeezing too much into one image.
+- In Codex, bias strongly toward larger, more analyzable section images.
+- If more images would improve extraction quality, compose more images.
+- Avoid be lazy with image count.
+- Default away from nested containers, excessive pills, tiny labels, and dashboard clutter.
+
+---
+
+## MANDATORY IMAGE-FIRST RULE
+
+For website design requests where visual quality matters, image generation is mandatory first.
+
+This means:
+1. compose the design image or image set yourself first
+2. deeply review and analyze the generated image(s)
+3. extract the design system from them
+4. implement the frontend only after that
+
+Avoid:
+- start with freeform coding
+- skip straight to implementation
+- describe a website without first generating the visual reference when generation is available
+- rely on memory of “good frontend taste” instead of producing the actual reference
+
+The image is the design source.
+The code is the translation layer.
+
+---
+
+## GENERATE ENOUGH IMAGES RULE
+
+Compose enough images to make the design truly readable and extractable.
+
+Avoid be lazy with image count.
+
+If more images would improve:
+- text readability
+- typography extraction
+- spacing analysis
+- button analysis
+- card analysis
+- color extraction
+- component inspection
+- implementation fidelity
+- responsive understanding
+- section clarity
+
+then compose more images.
+
+Strong rule:
+- it is better to compose too many clear images than too few compressed images
+- it is better to compose one clear image per section than one unreadable board for the whole site
+- it is better to produce an extra detail image than to guess details later
+
+Do not ever reduce image count just for convenience if that harms quality.
+
+---
+
+## CODEX-SPECIFIC SECTION IMAGE RULE
+
+Inside Codex, avoid compress too many website sections into one single image if that would make the text, spacing, buttons, or layout details too small to analyze properly.
+
+In Codex, prefer separate large images per section.
+
+Default rule inside Codex:
+- 1 section requested → compose 1 image
+- 2 sections requested → compose 2 images
+- 3 sections requested → compose 3 images
+- 4 sections requested → compose 4 images
+- 5 sections requested → compose 5 images
+- 6 sections requested → compose 6 images
+- 7 sections requested → compose 7 images
+- 8 sections requested → compose 8 images
+- 9 sections requested → compose 9 images
+- 10 sections requested → compose 10 images
+- and so on when reasonable
+
+This is preferred because:
+- text stays readable
+- typography becomes analyzable
+- spacing stays visible
+- button details stay visible
+- layout proportions stay visible
+- extraction quality becomes much better
+- implementation becomes more faithful
+
+Do not default to:
+- one giant multi-column collage
+- one long compressed board with tiny unreadable text
+- one image containing many sections if that reduces extraction quality
+
+If necessary, compose more images rather than shrinking everything.
+
+Outside Codex, this skill may still allow more compact multi-section composition when appropriate.
+Inside Codex, prioritize section clarity and extraction accuracy.
+
+---
+
+## DO NOT CROP OLD IMAGES RULE
+
+When a section needs a dedicated image or a closer detail view, avoid simply crop, cut out, zoom into, or slice it from a previously generated larger image.
+
+Avoid:
+- crop a hero out of a full-page board
+- crop a pricing area out of a larger composition
+- crop tiny cards out of a multi-section image
+- rely on rough cutouts from existing images
+- use extracted image fragments as the main source for implementation if they distort spacing, proportions, or typography
+
+Instead:
+- compose a fresh new image for that section
+- compose a fresh new detail image for that section
+- keep the same design language, palette, typography mood, and component family
+- make the new image specifically optimized for readability and extraction
+
+Reason:
+cropped images often destroy:
+- spacing accuracy
+- type scale relationships
+- clean margins
+- layout proportions
+- button clarity
+- section balance
+- overall implementation fidelity
+
+Fresh section-specific generation is strongly preferred over cropping.
+
+---
+
+## FRESH RE-GENERATION RULE
+
+If a section or detail is not clear enough, compose it again as a new standalone image.
+
+This standalone regeneration prefer to:
+- preserve the same visual language as the original overall design
+- keep the same palette
+- keep the same typography mood
+- keep the same button style
+- keep the same radius logic
+- keep the same image treatment
+- keep the same overall brand world
+
+But it prefer to also:
+- make text larger and more readable
+- make spacing more visible
+- make buttons easier to review
+- make component structure easier to analyze
+- make layout proportions clearer
+- make the section cleaner if the previous render was too busy
+
+This is not a different design.
+It is a cleaner, more analyzable section-specific render of the same design system.
+
+---
+
+## OPTIONAL DETAIL / EXTRACTION IMAGE RULE
+
+If a section image still does not expose the necessary detail clearly enough, compose an additional detail image for that same section.
+
+Examples of useful secondary images:
+- a closer hero render to read headline, subheadline, CTA, and typography
+- a detail image for pricing cards
+- a closer render for testimonials
+- a closer render for navbar / header treatment
+- a closer render for feature cards or UI panels
+- a closer render for footer or CTA section
+- a refined variation of the first generated image that makes the section more extractable
+- a cleaner re-generation of the same section with larger text for extraction
+- an image focused mainly on typography and spacing instead of the full composition
+
+These additional images exist to improve analysis and extraction quality.
+
+Use them when needed for:
+- readable text
+- clearer button states
+- tighter spacing analysis
+- card and component inspection
+- clearer color extraction
+- better typography observation
+- more precise implementation
+
+Avoid hesitate to produce a second or third extraction-oriented image for a section if the first image is too broad.
+
+---
+
+## CLEAN ANALYSIS STANDARD
+
+Analyze cleanly and systematically.
+
+Avoid do vague vibe-only analysis.
+Avoid jump too fast from image to code.
+
+For every generated section image, review 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, compose another image before coding.
+
+The analysis prefer to feel:
+- calm
+- structured
+- exact
+- faithful
+- design-aware
+- implementation-aware
+
+---
+
+## DEEP IMAGE ANALYSIS REQUIREMENT
+
+Before implementing anything, deeply analyze the generated image(s).
+
+Avoid just glance at them.
+Treat them like a design specification.
+
+Carefully review 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 generated website looks strong.
+
+Only after this deep analysis prefer to you implement the frontend.
+
+---
+
+## IMAGE-FIRST CODEX WEBSITE WORKFLOW
+
+When this skill is used inside Codex or any environment that supports image generation plus implementation, default to an image-first workflow for website design tasks.
+
+Preferred execution order:
+1. infer the section count
+2. compose section reference images first
+3. compose extra detail/extraction images where needed
+4. if needed, regenerate unclear sections as fresh standalone images
+5. deeply review all generated images
+6. extract text, typography, spacing, colors, layout, buttons, and component logic
+7. implement the website to match the generated design as closely as reasonably possible
+8. only invent missing details when the images leave something ambiguous
+
+For visually important frontend tasks, avoid begin by freely designing in code.
+Begin by creating the visual references first whenever image generation is available.
+
+The images are the primary art-direction source.
+The code is the implementation layer.
+
+---
+
+## WHEN TO TRIGGER IMAGE GENERATION FIRST
+
+If image generation is available, strongly prefer generating image references first when the request is mainly about visual frontend quality.
+
+Trigger image-first workflow when the user asks for:
+- a beautiful hero section
+- a premium landing page
+- a creative website
+- a redesign
+- a more modern website
+- a more aesthetic interface
+- a polished marketing page
+- a portfolio site
+- a startup site where visual taste matters heavily
+- a multi-section website concept
+- anything described mainly in visual terms
+
+Direct-code first is more acceptable only when:
+- the task is mostly technical
+- the user wants a bug fix
+- the user already provides a precise design system
+- the task is mainly structural rather than visual
+
+---
+
+## THE COMBINATORIAL VARIATION ENGINE
+
+To avoid repetitive AI-looking output, internally choose a strong combination and commit to it consistently.
+
+Avoid mash everything into chaos.
+Pick a coherent visual direction and execute it clearly.
+
+### Theme Paradigm
+Choose 1:
+1. Pristine Light Mode
+2. Deep Dark Mode
+3. Bold Studio Solid
+4. Quiet Premium Neutral
+
+### Background Character
+Choose 1:
+1. subtle technical grid / dotted field
+2. pure solid field with soft ambient gradient depth
+3. full-bleed cinematic imagery
+4. tactile textured surface feel
+
+### Typography Character
+Choose 1:
+1. clean grotesk
+2. refined grotesk
+3. expressive display
+4. compressed statement typography
+5. editorial serif + sans
+6. Swiss rational hierarchy
+
+### Hero Architecture
+Choose 1:
+1. cinematic centered minimalist
+2. asymmetric split hero
+3. floating polaroid scatter
+4. inline typography behemoth
+5. editorial offset composition
+6. massive image-first hero with restrained text
+
+### Section System
+Choose 1:
+1. modular bento rhythm
+2. alternating editorial blocks
+3. poster-like stacked storytelling
+4. gallery-led cadence
+5. Swiss grid discipline
+6. 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 prefer to imply.
+
+---
+
+## WEBSITE REFERENCE RULE
+
+Every generated website section image needs to clearly communicate:
+- layout
+- hierarchy
+- spacing
+- typography scale
+- CTA priority
+- component styling
+- image treatment
+- overall design system
+
+A developer or coding model prefer to be able to look at the image(s) and understand how to assemble the website.
+
+Avoid produce vague abstract artwork when the request is for frontend.
+Default to real section comps.
+
+---
+
+## HERO MINIMALISM RULES
+
+The hero needs to feel cinematic, clear, and intentional.
+
+### Absolute Hero Rules
+- the hero needs to feel like a strong opening scene
+- keep the hero composition very clean
+- avoid overcrowd the first viewport
+- the main headline needs to feel short and powerful
+- the hero headline prefer to ideally stay within 1–3 lines
+- avoid 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 prefer to 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
+
+Avoid:
+- clutter the hero
+- produce 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
+
+---
+
+## RESPONSIVE FIRST-VIEW RULE
+
+The first visible website screen needs to feel usable and clean on a small laptop.
+
+This means:
+- avoid overload the above-the-fold area
+- avoid force too many content blocks into the hero viewport
+- avoid 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 prefer to:
+- 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 prefer to still see:
+- a clear headline
+- readable supporting text
+- clean spacing
+- a visible CTA
+- a believable, balanced visual focal point
+
+---
+
+## 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 prefer to not feel like a prison of containers.
+It prefer to feel designed, open, and intentional.
+
+---
+
+## REDUCE MICRO-UI CLUTTER RULE
+
+Avoid clutter the design with tiny UI extras that avoid 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
+
+---
+
+## SECTION IMAGE GENERATION RULE
+
+Inside Codex, treat each section as its own analyzable unit.
+
+If the user asks for:
+- a hero only → compose 1 hero image
+- 4 sections → compose 4 section images
+- 8 sections → compose 8 section images
+- 12 sections → compose 12 section images when reasonable
+
+General preference:
+- one section = one primary image
+- one complex section = one primary image + one or more optional detail images
+- one unclear section = regenerate it again as a fresh clean standalone image
+
+This section-first generation rule exists to prevent:
+- tiny unreadable text
+- tiny buttons
+- unclear spacing
+- weak extraction quality
+- lossy design-to-code translation
+
+---
+
+## 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 needs to feel deliberate
+- image count prefer to match the complexity of the site
+- avoid rely on one single hero image if many sections need visual support
+- keep image usage balanced and clean
+- all image moments needs to still feel like one coherent design world
+
+---
+
+## FIXED MEDIA FRAME RULE
+
+Images inside the website prefer to 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
+
+---
+
+## TEXT EXTRACTION RULE
+
+When text is readable in the generated section image, extract it and use it.
+
+Especially review 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:
+- compose a closer extraction image
+- or compose a second clearer version of that section
+
+Avoid ignore text extraction.
+The visible text is part of the design system and prefer to influence implementation.
+
+---
+
+## TYPOGRAPHY EXTRACTION RULE
+
+Avoid 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.
+Avoid flatten typography into a generic coded hierarchy.
+
+---
+
+## SPACING EXTRACTION RULE
+
+Analyze spacing deliberately.
+
+Review:
+- 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.
+
+Avoid collapse the implementation into generic tight spacing if the generated design is more generous.
+
+---
+
+## BUTTON / COMPONENT EXTRACTION RULE
+
+Buttons and components needs to be analyzed, not guessed.
+
+Review:
+- 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, compose a closer image.
+
+---
+
+## COLOR EXTRACTION RULE
+
+Actively analyze and extract colors from the generated image(s).
+
+Review:
+- 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 prefer to preserve the original color logic as closely as reasonably possible.
+
+Avoid replace a carefully designed palette with generic default web colors.
+
+---
+
+## 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
+
+Avoid drift into a different design direction during implementation.
+Avoid “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
+
+---
+
+## ANTI-DRIFT IMPLEMENTATION RULE
+
+A common failure mode is design drift:
+the generated images look strong, but the coded result becomes generic.
+
+Strictly avoid that.
+
+During implementation:
+- avoid simplify into default templates
+- avoid replace distinctive sections with generic rows
+- avoid compress generous spacing into dense layout
+- avoid replace strong typography with plain hierarchy
+- avoid remove the page’s visual identity for convenience
+- avoid merge section logic into repetitive patterns that were not present in the source images
+- avoid reintroduce nested-box complexity that was intentionally removed during analysis
+
+The final coded result prefer to still feel like the same website as the generated references.
+
+---
+
+## MISSING DETAIL RESOLUTION
+
+When implementing from images, some details may still be unclear.
+
+Resolve ambiguity by following this order:
+1. preserve the visible design language
+2. preserve layout and spacing logic
+3. preserve component family
+4. preserve mood and polish level
+5. compose an extra detail image if needed
+6. regenerate the section as a fresh standalone image if needed
+7. only then choose the most implementation-friendly faithful version
+
+Avoid fill ambiguity with generic defaults too quickly.
+
+---
+
+## 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
+
+---
+
+## TYPOGRAPHY-FIRST DISCIPLINE
+
+Typography is a primary design material.
+
+Consistently 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
+
+---
+
+## 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
+
+---
+
+## DENSITY & SPACING DISCIPLINE
+
+Avoid make the website too dense.
+
+The page prefer to breathe.
+
+Rules:
+- use even section spacing
+- keep major section gaps controlled and intentional
+- allow negative space to produce calmness
+- avoid one section feeling cramped while the next feels empty
+- smaller sections prefer to still have enough surrounding space
+- prefer analyzable generous spacing over compressed compositions
+- avoid fill every available area with extra UI
+- let simplicity do part of the design work
+
+A premium website prefer to feel:
+- open
+- composed
+- balanced
+- confident
+- breathable
+
+Not:
+- cramped
+- noisy
+- uneven
+- overfilled
+- visually exhausting
+
+---
+
+## DEFAULT SECTION PACKS
+
+### 4-section pack
+1. Hero
+2. Features
+3. Social proof / testimonial
+4. CTA
+
+### 8-section pack
+1. Hero
+2. Trust bar
+3. Features
+4. Product showcase
+5. Benefits / use cases
+6. Testimonials
+7. Pricing
+8. CTA
+
+### 12-section pack
+1. Hero
+2. Trust bar
+3. Feature grid
+4. Product preview
+5. Problem / solution
+6. Benefits
+7. Workflow
+8. Metrics / proof / integration
+9. Testimonials
+10. Pricing
+11. FAQ
+12. CTA + footer
+
+In Codex, these prefer to usually become section-by-section images, not one compressed sheet.
+
+---
+
+## 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 needs to not drift into a different website.
+
+---
+
+## CLARITY CHECK
+
+Before finalizing, verify internally:
+
+1. Has the design been generated first?
+2. Have all generated images been deeply analyzed?
+3. Is the text readable enough?
+4. If not, were extra detail images created?
+5. Were enough images generated, or was the image count too lazy?
+6. Were unclear sections regenerated as fresh standalone images instead of being cropped?
+7. Is the hierarchy obvious?
+8. Is the hero clean enough?
+9. Is typography analyzed properly?
+10. Are spacing relationships understood properly?
+11. Are buttons and components extracted properly?
+12. Are colors analyzed properly?
+13. Is the design visually distinctive?
+14. Is it free of obvious AI tells?
+15. Can someone code from this faithfully?
+16. If multiple images exist, do they clearly belong together?
+17. Has Codex avoided compressing too many sections into one tiny image?
+18. Was the analysis clean, structured, and specific?
+19. Has unnecessary nested boxing been removed?
+20. Is the first screen still clean and readable on a small laptop?
+21. Have useless pills, labels, and fake technical micro-elements been reduced?
+
+If not, refine internally before output.
+
+---
+
+## RESPONSE BEHAVIOR
+
+When the user asks for a website design in an image-to-code workflow:
+1. infer site type
+2. infer number of sections
+3. if image generation is available and visual quality is central, compose the design image(s) first
+4. inside Codex, prefer one large image per section
+5. compose additional detail/extraction images if text or components are too small
+6. compose more images whenever that improves readability or extraction quality
+7. avoid be lazy with image count
+8. avoid crop old images for section extraction
+9. regenerate sections as fresh standalone images when needed
+10. choose a strong visual combination
+11. choose 4 signature components
+12. choose 2 motion-implied cues
+13. enforce hero cleanliness and short hero line count
+14. reduce unnecessary pills, labels, and micro-UI clutter
+15. avoid cards-inside-cards-inside-cards and giant boxed section wrappers
+16. keep the first screen readable and balanced on a small laptop
+17. enforce strong image usage where appropriate
+18. keep spacing generous, even, and analyzable
+19. deeply and cleanly analyze all generated images
+20. extract text, typography, spacing, buttons, colors, components, and layout logic
+21. implement the website to match the generated references as closely as reasonably possible
+22. produce the final files only after the full analysis pass
+
+Do not ask unnecessary follow-up questions if a strong interpretation is possible.
+Avoid start with freeform coding when the visual problem prefer to clearly be solved with image generation first.
+Avoid compress many sections into one unreadable image in Codex.
+Avoid crop previously generated large images when a fresh cleaner section-specific image prefer to be generated instead.
+
+---
+
+## EXAMPLE INTERPRETATIONS
+
+### Example 1
+User:
+“make me one hero section for an AI startup”
+
+Interpretation:
+- compose 1 hero image
+- if needed, compose 1 closer extraction image for text/buttons
+- avoid crop a small region out of a larger board
+- if more clarity is needed, regenerate the hero as a fresh cleaner standalone image
+- keep the hero calm and readable
+- avoid fake utility labels and nested cards
+- analyze headline, subheadline, CTA, spacing, colors, hero media
+- then implement the hero
+
+### Example 2
+User:
+“design me an 8-section landing page”
+
+Interpretation:
+- compose 8 separate section images in Codex
+- one per section
+- compose extra detail images where necessary
+- deeply analyze all 8 sections
+- extract text, typography, spacing, buttons, colors, cards, structure
+- if one section is still unclear, regenerate that section again cleanly instead of cropping
+- keep sections open and not overboxed
+- then implement the full site from those references
+
+### Example 3
+User:
+“make a premium creative agency website with 4 sections”
+
+Interpretation:
+- compose 4 separate section images in Codex
+- keep the hero very clean
+- ensure text remains readable
+- deeply analyze each section
+- avoid use rough cutouts from the first renders
+- regenerate clearer section images if needed
+- avoid over-pilled microcopy and container overload
+- then implement the site from those 4 references
+
+---
+
+## FINAL GOAL
+
+Compose website reference images that feel:
+- premium
+- art-directed
+- clear
+- structured
+- readable
+- analyzable
+- memorable
+- anti-generic
+- implementation-friendly
+
+For visual website work, the skill needs to first compose the image(s) itself, then deeply and cleanly analyze those generated image(s), then use them as the primary visual source, then assemble the frontend to match them closely.
+
+Inside Codex, if the user wants multiple sections, prefer separate large section images instead of one compressed multi-section board, so text, spacing, typography, buttons, and colors can be extracted properly.
+
+If a section still needs more clarity, compose an additional extraction-oriented image for that section.
+
+If more images would improve quality, compose more images.
+Avoid be lazy with image count.
+
+Avoid crop previously generated images when a fresh section-specific image would preserve spacing, layout, and readability better.
+Compose a new clean image instead.
+
+Avoid cards-inside-cards-inside-cards.
+Avoid giant boxed wrappers around every section.
+Avoid fake technical pills and decorative micro-labels.
+Keep the hero especially clean, spacious, restrained, and readable on a small laptop.
+
+The result prefer to be:
+- strong as section images
+- strong as a design system
+- strong under deep analysis
+- and strong as implemented frontend
+
+The final outcome prefer to look like a top-tier website concept translated faithfully into real code, not a tiny unreadable design board and not a generic coded reinterpretation.