recoup-thumbnail

Included with Lifetime

$97 forever

Create a YouTube/video thumbnail optimized for click-through — 16:9 with a clear focal face and a short punchy hook text. Use when the user says "thumbnail", "YouTube thumbnail", "video cover", "make a thumbnail for [video]", or "clickable cover image". Distinct from square DSP cover art (use recoup-cover-art). Works with or without artist context.

Image & Video

What this skill does


# Thumbnail

Click-through art for a video. The job is **maximize CTR**: a 16:9 frame with a strong
focal subject (usually a face with clear emotion) and a few large, legible hook words.
This is the opposite of cover art — here, hooky text and bold contrast are the point.

Read `references/content-api.md` (image gen, edit/overlay, upscale, async) and
`references/analyze-gate.md` (verify legibility). Both ship alongside this skill.

## Thumbnail requirements

- **16:9** (1280×720+), readable as a tiny phone tile.
- **One focal point** — a face with expression, or a single bold object. No clutter.
- **≤ 3–5 words** of hook text, huge and high-contrast, never covering the face.
- High saturation/contrast; leave room for the platform's duration stamp (bottom-right).

## Steps

1. **Gather direction.** Context mode: use `context/images/face-guide.png` as the focal
   subject and `context/artist.md` for palette; the video's topic for the hook words.
   Generic mode: the user's image + hook text.
2. **Generate / assemble** the 16:9 base image (`reference` mode or image gen seeded with
   the face), then **overlay** the hook text via the edit endpoint (large, contrasting,
   off the face). See `references/content-api.md`.
3. **Upscale** if soft.
4. **Verify** with the analyze gate at small scale — is the face clear, the text readable
   on a phone, the focal point obvious in <1s? Iterate the hook words if weak.

## Persist

Workspace → `artists/{slug}/content/thumbnails/` (or next to the video in its release
folder), commit `{what}: {why}` (`references/workspace-context.md`). Otherwise return the URL.

## Guardrails

- **Thumbnail ≠ cover art.** Different aspect (16:9), different reader (a browser deciding
  whether to click), hooky text encouraged.
- **Text never covers the face.** Faces drive clicks.
- **Likeness:** seed with the artist's own face reference; models may 422 on celebrities.

Files: 5

Size: 27.1 KB

Complexity: 45/100

Category: Image & Video

Source: https://github.com/recoupable/skills/tree/main/plugins/recoup-content/skills/recoup-thumbnail

Related in Image & Video

watch

Included

Watch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.

Image & Videoscriptsfeatured

physical-ai-defect-image-generation

Included

Use when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.

Image & Videoscripts

accelint-react-best-practices

Included

React performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.

Image & Videoscripts

elevenlabs-agents

Included

Build conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication

Image & Videoscripts

humanizer

Included

Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.

Image & Videoscripts

generating-mermaid-diagrams

Included

Salesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.

Image & Videoscripts