Create high-CTR YouTube video thumbnails (1280×720, 16:9) — creator reaction faces, object heroes, before/after splits, bold-text hooks, tutorial UI shots — with duration-badge safe zone, 3-element rule, and mobile-size readability. Use when the deliverable is a cover image for a YouTube video and the goal is click-through rate. Do not use for paid ad creatives or non-YouTube platform covers. Do not use for artistic posters, movie/book/album covers.
Scanned 8/20/2026
Install via CLI
openskills install DeepKolor/deepkolor-agent-skills---
name: youtube-thumbnail-agent
description: "Create high-CTR YouTube video thumbnails (1280×720, 16:9) — creator reaction faces, object heroes, before/after splits, bold-text hooks, tutorial UI shots — with duration-badge safe zone, 3-element rule, and mobile-size readability. Use when the deliverable is a cover image for a YouTube video and the goal is click-through rate. Do not use for paid ad creatives or non-YouTube platform covers. Do not use for artistic posters, movie/book/album covers."
homepage: https://deepkolor.ai
author: DeepKolor
license: MIT
tags: [image-generation, youtube, thumbnail, video]
version: lite
---
# YouTube Thumbnail Agent
> **Lite edition** — routing and core rules for agent discovery. Full prompt templates, platform playbooks, and production workflows run on [DeepKolor](https://deepkolor.ai).
Click-optimized 1280×720 thumbnails — face + hook text, bold text hooks, or product hero layouts.
## When to use
See `description` in frontmatter — the agent loads it at startup for routing.
## Workflow
- Always 16:9; keep subject and hook text in safe zones (avoid bottom-right duration badge area).
- High contrast, readable at small size; one clear focal point.
- Use image-to-image when preserving a real face, product, or screenshot.
## Defaults
aspectRatio=16:9, resolution=1K
## Tool: `create_image_task`
```ts
{
prompt: string,
scene: "text-to-image" | "image-to-image",
aspectRatio?: string,
imageUrls?: string[],
resolution?: "1K"
}
```
Available when your agent runtime exposes DeepKolor generation tools. Otherwise use this skill as a prompt-engineering guide and adapt tool names to your stack.
## Boundaries
- YouTube thumbnails only — not general posters or paid ad banners.
## Output
After generation, reply briefly: what was created, key parameters, and one useful next step. Return a full prompt only when the user explicitly asks.
## Full version
Production-grade references (SOPs, templates, platform rules) ship inside [DeepKolor](https://deepkolor.ai) — not in this public lite package.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.