Communitygithub.com

NeverSight/learn-skills.dev

Use for frontend/UI builds, redesigns, polish, or extensions. Before coding, generate a UI reference image, then closely match it instead of inventing a new direction.

What is learn-skills.dev?

learn-skills.dev is a Codex agent skill that use for frontend/UI builds, redesigns, polish, or extensions. Before coding, generate a UI reference image, then closely match it instead of inventing a new direction.

Works with~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/adamholter/hive-mind-landing-page/frontend-from-generated-image

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Frontend From Generated Image

Use this skill for any task that includes a frontend, screen, page, component set, dashboard, landing page, app shell, modal, chat UI, or other visible interface.

When the task is an iteration on an existing UI rather than a full redesign, treat the current UI as an important constraint.

This skill is intentionally strict: the generated or user-provided image is not a moodboard. It is the target. The implementation should look like a faithful translation of the image into working code.

Core rule

Before writing frontend code:

  1. Use the imagegen skill and the built-in OpenAI image generation tool.
  2. If iterating on an existing UI, first gather reference screenshots of the current experience unless the user explicitly wants a full redesign.
  3. Generate or accept at least one UI design reference image for the requested interface.
  4. Treat the reference image as the design source of truth, while preserving existing-product constraints when the task is iterative.
  5. Implement the frontend by copying the image's layout, hierarchy, spacing, typography, color relationships, asset placement, and overall composition as closely as practical in real code.
  6. Verify with screenshots and refine until the rendered result visibly matches the reference.

Do not skip the image-generation step unless the user explicitly tells you not to.

Workflow

  1. Read the product/task requirements and infer the key UI surfaces that need to exist.
  2. If the task is modifying an existing frontend, collect reference screenshots of the current UI first.
  3. Unless the user asked for a full redesign, use those screenshots as reference inputs and constraints for the design-generation prompt.
  4. Write a design-generation prompt for the interface.
  5. Generate the reference image with the built-in OpenAI image tool.
  6. Inspect the result and write a concrete visual brief before coding:
    • layout structure
    • alignment and spacing
    • type scale
    • component shapes
    • color palette
    • background treatment
    • visual density
    • major asset locations and dimensions
    • element ordering and z-index/layer relationships
    • motion cues implied by the composition
  7. Build the real frontend to match that image closely. Work one section or screen at a time when the reference contains multiple sections.
  8. Capture a screenshot of the implementation at the same viewport/aspect ratio as the reference.
  9. Compare screenshot to reference and fix mismatches in layout, spacing, scale, color, asset placement, and typography before moving on.
  10. If the generated image is weak, generate another one and use the stronger reference.

Prompting guidance for the image

When prompting the image model:

  • Describe the product type and exact screen to render.
  • Ask for a polished product UI mockup, not an abstract moodboard.
  • Specify the platform when relevant: desktop web app, mobile app, landing page, chat tool, admin panel, etc.
  • Include the desired tone and brand feel.
  • Ask for clear hierarchy, refined spacing, and realistic interface composition.
  • Request a full-screen UI screenshot/mockup perspective.
  • If the tool already has an established product direction, preserve it rather than reinventing it.
  • If iterating on an existing UI, provide the current UI screenshots as references whenever the image workflow supports that.
  • For iterative work, prompt for an improved version of the current design rather than a replacement design, unless the user explicitly asked for a full redesign.

Image-to-code translation rules

  • Do not rebuild illustrated/photo/3D assets with CSS, SVG primitives, gradients, or decorative divs. Use real image assets for those parts.
  • If the reference contains embedded product art, character art, photos, renderings, textures, icons, or abstract image panels, create explicit asset slots in the project and tell the user or future agent exactly where those files belong.
  • If the user supplied extracted assets, use those assets directly and clone the surrounding layout, components, typography, spacing, and effects.
  • If assets need transparent backgrounds, use the local fal-media-gen Pixelcut Background Remover workflow; do not send the user to external web tools, fake transparency with white boxes, or rebuild image assets in CSS.
  • For multi-section pages, translate one section at a time. Do not rough in all sections and hope the overall impression carries the design.
  • Preserve the exact visual hierarchy of the reference: what is biggest, what is quietest, what aligns to what, and where the eye lands first.
  • Measure proportions from the reference when possible: viewport coverage, section height, image aspect ratios, column widths, gutters, nav height, button height, and card density.
  • Use CSS variables or design tokens for colors, spacing, radii, and shadows that visibly repeat in the reference.
  • Avoid adding extra explanatory copy, extra cards, extra badges, or extra decoration that is not present in the reference.
  • When text in the generated image is unreadable or nonsensical, replace it with concise realistic copy while preserving the same line lengths, weight, hierarchy, and density.

Implementation guidance

  • Copy the generated image, do not merely "take inspiration from it."
  • For iterative work, preserve the recognizable product structure and only change what the task calls for.
  • Match the big decisions first: composition, scale, contrast, and layout rhythm.
  • Then match the smaller decisions: radii, borders, shadows, gaps, card proportions, and type treatment.
  • Preserve usability and accessibility while translating the image into production code.
  • If the generated image includes impossible or unclear details, infer the closest practical implementation without changing the visual direction more than necessary.

Fidelity checklist

Before calling the implementation done, check these against the reference image:

  • Same viewport framing: hero/section height, first-fold composition, and visible next-section hint when applicable.
  • Same macro layout: column count, alignment, negative space, overlap, asymmetry, and section rhythm.
  • Same visual weight: heading scale, supporting text scale, button prominence, image size, and card density.
  • Same color relationships: background, text contrast, accent amount, borders, shadows, and gradients.
  • Same component geometry: radii, stroke weights, padding, gaps, and icon/button sizes.
  • Same asset behavior: images use correct aspect ratio, cropping, object position, transparency, and layering.
  • Same responsive intent: mobile should feel like a faithful adaptation, not a different design.
  • No accidental additions: remove default nav text, generic feature cards, filler badges, random icons, and decorative effects that were not in the reference.

If the screenshot does not match, keep iterating. Name the top mismatches, patch them, and screenshot again.

Priority over default design behavior

If another frontend skill suggests inventing a fresh visual direction, this skill takes priority for UI direction. The generated image should anchor the design.

Deliverable behavior

For frontend tasks covered by this skill, the expected flow is:

  1. Generate the reference image.
  2. Extract or prepare any needed assets and define their project paths.
  3. Build the UI to match the reference section-by-section or screen-by-screen.
  4. Verify the implementation visually with screenshots.
  5. Refine toward the reference until the main mismatches are resolved.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

NeverSight/learn-skills.dev

Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory

NeverSight/learn-skills.dev

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

NeverSight/learn-skills.dev

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

NeverSight/learn-skills.dev

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

NeverSight/learn-skills.dev

ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization

NeverSight/learn-skills.dev

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

NeverSight/learn-skills.dev

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

NeverSight/learn-skills.dev

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

NeverSight/learn-skills.dev

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

NeverSight/learn-skills.dev

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

NeverSight/learn-skills.dev

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

NeverSight/learn-skills.dev

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

NeverSight/learn-skills.dev

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

NeverSight/learn-skills.dev

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

NeverSight/learn-skills.dev

Configure and use the hosted YouTube Data MCP end-to-end with minimal user input. Use when users want the agent to verify Node.js and `npx`, configure MCP server config (Windows/macOS, Cursor/Codex/OpenClaw/OpenCode), request API key at setup time, run post-install capability discovery (`tools/list` and `get_patch_notes`), and then strongly recommend helper skill and Python setup for full local document and spreadsheet workflows.

NeverSight/learn-skills.dev

Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects. Use when user requests animation, motion, scroll effects, parallax, hero animations, gestures, drag interactions, spring physics, whileHover effects, whileInView animations, animated UI, micro-interactions, page transitions, or layout animations. Generates production TypeScript/JSX code with accessibility (prefers-reduced-motion) and performance validation (≥60fps). Supports entrance animations, gesture interactions (hover/tap/drag), scroll-based reveals, and layout transitions using spring physics and natural timing. Do NOT use for CSS-only transitions (use native CSS), static sites without JavaScript, Vue animations (use motion-v variant instead), or SVG/Canvas complex animations (GSAP better suited).

NeverSight/learn-skills.dev

Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.

NeverSight/learn-skills.dev

FFmpeg commands for video/audio conversion, trimming, compression, and processing. Use when user mentions "ffmpeg", "convert video", "compress video", "extract audio", "trim video", "gif from video", "video codec", "transcode", "screen recording", "merge videos", "video to mp4", "reduce file size", or any media processing task.

NeverSight/learn-skills.dev

Vim keybindings, motions, text objects, and operators for efficient text editing. Use when user asks about "vim commands", "vim motions", "text objects", "vim keybindings", "vim cheat sheet", "learn vim", "vim in VS Code", or any Vim editing tasks.

NeverSight/learn-skills.dev

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

Related Skills