Communitygithub.com

NeverSight/learn-skills.dev

Design de thumbnails para YouTube com dimensões específicas, regras de contraste e otimização para visualização em dispositivos móveis.

O que é learn-skills.dev?

Este skill oferece um guia completo para criar thumbnails de alto CTR (taxa de clique) para YouTube, utilizando geração de imagens por IA via CLI [inference.sh](https://inference.sh). Ele cobre especificações técnicas (1280x720 px, 16:9), o importante 'teste dos 120px' para garantir legibilidade em dispositivos móveis, e zonas seguras para posicionamento de texto e elementos-chave. Além disso, aborda estratégias de cores de alto contraste, psicologia de expressões faciais (surpresa gera maior CTR), padrões de thumbnail para diferentes tipos de conteúdo (tutoriais, listas, antes/depois) e práticas de teste A/B. O objetivo é capacitar o usuário a criar thumbnails que se destaquem no feed do YouTube e aumentem o engajamento, evitando erros comuns como excesso de texto ou baixo contraste. Suporta modelos como `falai/flux-dev-lora` e `bytedance/seedream-4-5`.

Funciona com~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/101-skills/skills/youtube-thumbnail-design

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

Instale o skill belt CLI: npx skills add belt-sh/cli

Design de Thumbnails para YouTube

Crie thumbnails de alto CTR para YouTube com geração de imagens por IA via inference.sh CLI.

Início Rápido

Requer o CLI do inference.sh (belt). Instruções de instalação

belt login

# Gere uma thumbnail
belt app run falai/flux-dev-lora --input '{
  "prompt": "YouTube thumbnail style, close-up of a person with surprised excited expression looking at a glowing laptop screen, vibrant blue and orange color scheme, dramatic studio lighting, shallow depth of field, high contrast, cinematic",
  "width": 1280,
  "height": 720
}'

Especificações

EspecificaçãoValor
Dimensões1280 x 720 px (mínimo)
Recomendado1920 x 1080 px
Proporção16:9
Tamanho máximo do arquivo2 MB
FormatosJPG, GIF, PNG

O Teste dos 120px

Sua thumbnail aparece com aproximadamente 120px de largura no celular — é assim que a maioria dos espectadores a vê primeiro.

A 120px, os espectadores devem conseguir identificar:

  1. O humor/emoção (através das cores e expressão)
  2. O assunto geral (através da composição)
  3. O texto (se houver — apenas se for grande o suficiente)

Teste: visualize sua thumbnail com 120px de largura. Se for um borrão ilegível, redesenhe.

Zonas Seguras

┌─────────────────────────────────────────────┐
│                                             │
│   ✅ SEGURO PARA TEXTO E ELEMENTOS-CHAVE    │
│                                             │
│                                             │
│                                             │
│                                             │
│                                       ┌───┐ │
│                                       │ ⏱ │ │ ← Sobreposição de timestamp
│                              ┌────────┴───┘ │    (canto inferior direito)
│   ┌────┐                     │  DURAÇÃO    │
│   │ CH │ Marcador de capítulo└──────────────│
└───┴────┴────────────────────────────────────┘
     ↑ Canto inferior esquerdo: marcadores de capítulo/progresso

Evite colocar elementos críticos em:

  • Canto inferior direito (timestamp de duração do vídeo)
  • Canto inferior esquerdo (marcadores de capítulo, barra de progresso)
  • Extremidades (o recorte varia conforme o dispositivo)

Estratégia de Cores

Pares de Alto Contraste que Funcionam

CombinaçãoHumorMelhor Para
Amarelo + PretoUrgência, atençãoTecnologia, negócios, listas
Vermelho + BrancoEnergia, excitaçãoEntretenimento, reações
Azul + LaranjaContraste profissionalEducação, tutoriais
Verde + BrancoCrescimento, dinheiroFinanças, histórias de sucesso
Roxo + AmareloPremium, criativoDesign, arte, criatividade
Branco + EscuroLimpo, minimalistaCanais de luxo, minimalistas

Regras de Cores

  • Fundo e texto/sujeito devem ser complementares ou de alto contraste
  • Evite que cores do mesmo tom se toquem (vermelho sobre laranja = borrão)
  • Use no máximo 3 cores por thumbnail
  • Sature mais que na vida real — as thumbnails competem com a interface brilhante do YouTube

Texto em Thumbnails

Quando Usar Texto

  • Listas/números: "7 Dicas", "Top 10"
  • Opiniões fortes: "PARE de Fazer Isso"
  • Resultados: "R$ 10K em 30 Dias"
  • Comparações: "vs" entre duas coisas

Quando NÃO Usar Texto

  • O título do vídeo já diz (redundante)
  • A emoção/visual conta a história
  • Você não consegue torná-lo grande o suficiente para ler a 120px

Regras de Texto

RegraMotivo
Máximo de 6 palavrasLegibilidade no tamanho de thumbnail
Equivalente mínimo a 60ptDeve ser legível a 120px de largura
Fonte sans-serif em negritoFontes finas desaparecem em tamanhos pequenos
Contorno/sombra de contrasteGarante legibilidade em qualquer fundo
Sem texto pequenoSe não é legível pequeno, corte-o

Psicologia das Expressões Faciais

Thumbnails com rostos têm CTR mais alto que thumbnails sem rosto. A expressão importa:

ExpressãoImpacto no CTRMelhor Para
Surpresa/choqueMais altoConteúdo de reação, revelação, descoberta
CuriosidadeAltoTutorial, guia, dicas
ExcitaçãoAltoUnboxing, reviews, anúncios
Preocupação/apreensãoMédio-altoConteúdo de aviso, erro, problema
ConfiançaMédioConselho de especialista, conteúdo de autoridade
NeutroMais baixoEvite, a menos que sua marca seja minimalista

Regras de Composição com Rostos

  • O rosto deve ocupar 30-50% da thumbnail
  • Olhos olhando para o texto ou assunto (direciona a atenção do espectador)
  • Olhos olhando para a câmera = conexão. Olhos olhando para o objeto = curiosidade.
  • Coloque o rosto de um lado (geralmente esquerdo), texto ou assunto do outro
# Gere uma thumbnail com rosto de frente
belt app run falai/flux-dev-lora --input '{
  "prompt": "close-up portrait of a man with genuinely surprised expression, mouth slightly open, raised eyebrows, looking at camera, left side of frame, vibrant teal background, dramatic rim lighting, YouTube thumbnail style, high contrast, cinematic",
  "width": 1280,
  "height": 720
}'

# Gere uma thumbnail com rosto olhando para o assunto
belt app run bytedance/seedream-4-5 --input '{
  "prompt": "person looking amazed at a glowing holographic chart showing upward growth, dramatic blue and green lighting, right side profile view, dark background, tech aesthetic, high energy",
  "size": "2K"
}'

Padrões de Thumbnail por Tipo de Conteúdo

Tutorial / Guia

belt app run falai/flux-dev-lora --input '{
  "prompt": "overhead flat lay of organized workspace with laptop showing code editor, colorful sticky notes, coffee cup, clean bright background, professional setup, tutorial style composition, warm lighting",
  "width": 1280,
  "height": 720
}'

Antes/Depois

belt app run falai/flux-dev-lora --input '{
  "prompt": "split composition, left side dark and messy disorganized desk, right side bright clean organized minimalist workspace, dramatic contrast between chaos and order, clear dividing line in center, high contrast",
  "width": 1280,
  "height": 720
}'

Review de Produto / Comparação

belt app run falai/flux-dev-lora --input '{
  "prompt": "two products facing each other with dramatic lighting and sparks between them, competition battle concept, dark background with colorful rim lighting, versus comparison style, high energy, product photography",
  "width": 1280,
  "height": 720
}'

Lista / Número

belt app run falai/flux-dev-lora --input '{
  "prompt": "dynamic arrangement of 7 different colorful objects floating in space against dark gradient background, each item distinct and clearly separated, energetic composition, vibrant saturated colors, studio lighting",
  "width": 1280,
  "height": 720
}'

Teste A/B

Teste uma variável de cada vez:

VariávelTeste A vs B
Rosto vs Sem rostoMesma composição, com/sem pessoa
ExpressãoSurpresa vs curiosidade
Esquema de coresPaleta quente vs fria
Texto vs Sem textoCom/sem sobreposição de texto
FundoClaro vs escuro
ComposiçãoSujeito virado para esquerda vs direita
# Gere a variante A
belt app run falai/flux-dev-lora --input '{
  "prompt": "..., bright yellow background, ...",
  "width": 1280, "height": 720
}' --no-wait

# Gere a variante B (mesmo prompt, fundo diferente)
belt app run falai/flux-dev-lora --input '{
  "prompt": "..., dark navy background, ...",
  "width": 1280, "height": 720
}' --no-wait

Checklist da Thumbnail

  • 1280x720 mínimo (1920x1080 preferível)
  • Abaixo de 2MB de tamanho de arquivo
  • Passa no teste dos 120px (squint test)
  • Nenhum elemento crítico no canto inferior direito (timestamp) ou inferior esquerdo (capítulo)
  • Máximo de 3 cores, alto contraste
  • Texto (se houver) tem no máximo 6 palavras, em negrito, com contorno de contraste
  • Expressão facial corresponde à energia do conteúdo (se aplicável)
  • Não duplica o título do vídeo
  • Destaca-se das thumbnails ao redor (verifique seu nicho)
  • Funciona tanto em fundo claro como escuro do YouTube

Erros Comuns

ErroProblemaCorreção
Muito textoIlegível no tamanho de thumbnailMáximo de 6 palavras ou nenhum texto
Baixo contrasteDesaparece no feedUse cores complementares
Composição poluídaO olho não sabe para onde olharUm único ponto focal
Aparência genérica de foto de stockSem personalidade, é ignoradoExpressões autênticas, ângulos únicos
Detalhes minúsculosPerdidos a 120pxFormas ousadas e simples
Mesmo estilo em todo vídeoCansaço do espectadorVarie dentro das diretrizes da marca
Thumbnail enganosaMata a confiança, prejudica a retençãoCorresponda ao conteúdo real

Skills Relacionados

npx skills add inference-sh/skills@ai-image-generation
npx skills add inference-sh/skills@image-upscaling
npx skills add inference-sh/skills@prompt-engineering

Navegue por todos os apps: belt app store

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

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

Download YouTube videos, extract/proofread/translate subtitles, and render them onto video. Use whenever the user asks to download a YouTube video with subtitles, translate video subtitles to Chinese, add subtitles/burn subtitles to a video, or do ASR transcription on video audio. Covers the full pipeline: video download → subtitle extraction → proofreading → translation → SRT generation → subtitle rendering. Also use for "下载视频加字幕", "视频翻译字幕", "把字幕烧录到视频中". For pure subtitle file creation without rendering (just SRT output), this skill handles that too — stop before Phase 5.

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.

Habilidades Relacionadas