thumbnail-concept-generator

thumbnail-concept-generator is a skill for Claude Code, Codex from nicepkg/ai-workflow. It costs 49 tokens per session (2,040 once invoked), scanned A, original, MIT.

A planning aid that creates visual briefs for video thumbnails. It describes the composition, text, colours, and emotional direction for thumbnails on YouTube, TikTok, and similar platforms.

In plain words
What is it for?
Generating thumbnail concepts, briefing a designer, and exploring ways to improve how a video is presented in search or feeds.
Why use it?
A thumbnail needs to communicate quickly, especially on small screens. A written brief helps creators or designers agree on the visual idea before making it.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nicepkg/ai-workflow/thumbnail-concept-generator
Any agent
npx skills add nicepkg/ai-workflow --skill thumbnail-concept-generator
Clone the repo
git clone --depth 1 https://github.com/nicepkg/ai-workflow

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for thumbnail-concept-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicepkg/ai-workflow/thumbnail-concept-generator.svg)](https://agentmods.dev/skills/nicepkg/ai-workflow/thumbnail-concept-generator)
Your own site
<a href="https://agentmods.dev/skills/nicepkg/ai-workflow/thumbnail-concept-generator"><img src="https://agentmods.dev/badge/skills/nicepkg/ai-workflow/thumbnail-concept-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.02040
Opus 5 $0.00024 $0.01020
Sonnet 5 $0.00010 $0.00408
Haiku 4.5 $0.00005 $0.00204

Measured 2d ago against content hash 3e419316ca9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

thumbnail-concept-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

workflows/video-creator-workflow/.claude/skills/thumbnail-concept-generator/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Thumbnail Concept Generator

Create click-worthy thumbnail concepts that maximize CTR.

Thumbnail Psychology

📊 THUMBNAIL IMPACT:
- 90% of top-performing videos have custom thumbnails
- Thumbnails are responsible for ~50% of a video's click-through rate
- Viewers decide in <2 seconds whether to click

KEY PRINCIPLE: Thumbnail must work at SMALL sizes (mobile, sidebar)

Thumbnail Elements

1. Faces & Emotions

EMOTION SCALE (from most to least effective):
1. 😱 Shock/Surprise - Wide eyes, open mouth
2. 🤔 Curiosity - Raised eyebrow, intrigued look
3. 😄 Joy/Excitement - Genuine smile, energy
4. 😤 Frustration/Anger - Visible emotion
5. 🤯 Mind-blown - Exaggerated reaction
6. 😢 Sadness - For emotional content

FACE RULES:
- Eyes should be visible and expressive
- Face takes up 30-50% of thumbnail
- Direct eye contact with camera
- Avoid sunglasses/obstructions

2. Text Overlay

TEXT RULES:
- Maximum 3-4 words
- Large, bold, readable at small size
- Contrasting colors (white on dark, dark on light)
- Don't repeat the title exactly
- Use outline/shadow for readability

EFFECTIVE TEXT:
✅ "IT WORKED" / "$10K" / "DON'T BUY" / "vs"
❌ "Watch this video to see what happens when I try..."

3. Color Psychology

RED: Urgency, excitement, warning
YELLOW: Attention, energy, optimism
BLUE: Trust, calm, professional
GREEN: Growth, money, nature
ORANGE: Enthusiasm, creativity
PURPLE: Luxury, creativity
BLACK: Premium, serious, drama
WHITE: Clean, simple, contrast

4. Composition Rules

RULE OF THIRDS: Place key elements at intersection points
Z-PATTERN: Eye travels Z-shape (top-left → top-right → bottom-left → bottom-right)
CONTRAST: Main subject must pop from background
NEGATIVE SPACE: Don't overcrowd - let elements breathe

Thumbnail Templates by Video Type

Tutorial/How-To

┌─────────────────────────────────────┐
│  [RESULT/OUTCOME]   │    FACE      │
│  Text: "EASY"       │  (excited/   │
│  or "5 MIN"         │  helpful)    │
│                     │              │
│  [Tool/Product      │              │
│   being used]       │              │
└─────────────────────────────────────┘

Elements:
- Split screen or diagonal divide
- Before/After if applicable
- Tool/product clearly visible
- Helpful/excited facial expression

Read the full file on GitHub · 293 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 293 lines · 49 tokens per session scan A 3e419316ca9a

Subscribe to this mod's changes

thumbnail-concept-generator is a skill published in the GitHub repository nicepkg/ai-workflow (282 stars, last pushed 7mo ago), licensed MIT. It adds 49 tokens to every session and 2,040 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.