Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Thumbnail Maker

ASecurity

Design high-CTR video thumbnails with composition, text, emotion, and platform-specific optimization.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgoexpresstesting

Works with

cli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill thumbnail-maker --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Thumbnail Maker?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Thumbnail Maker
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-thumbnail-maker/badge)](https://www.skillsdirectory.com/skills/aicodedecode-thumbnail-maker)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: thumbnail-maker
description: Design high-CTR video thumbnails with composition, text, emotion, and platform-specific optimization.
category: video
---

## Overview

The thumbnail is the video's packaging: paired with the title, it wins or loses
the click before a
single frame plays. High-performing thumbnails follow learnable patterns — clear
focal point,
readable emotion, minimal bold text, high contrast — while avoiding the
clickbait that destroys
trust. This skill covers thumbnail strategy, design, and testing.

## When to use

- Designing YouTube/video thumbnails

- Improving click-through rate on existing videos

- Creating thumbnail templates for a channel

- A/B testing thumbnail variations

- Adapting thumbnails for Shorts, courses, or ads

## Core concepts

- - - **Thumbnail + title = one unit.** They work together, not redundantly. If
  the title says it, the
  thumbnail should show it (or tease it) — never repeat the title verbatim on
the thumbnail. Design
  them as a pair.
- - - **The 3-element rule.** Focal subject (face/object, large) + emotion or
  intrigue (expression,
  contrast, before/after) + minimal text (3-5 words max, huge). Every additional
element dilutes the
  click.
- - - **Faces and emotion.** Human faces with clear emotions outperform abstract
  graphics in most
  niches — expressive, looking at camera (or at the focal object). The emotion
should match the
  video's promise.
- - - **Contrast and readability at 120px.** Thumbnails display tiny (especially
  on mobile). Test at
  actual feed size: is the subject clear? Is the text readable? High contrast,
saturated colors,
  simple backgrounds win the small-size war.
- - - **Curiosity gap, not clickbait.** Tease the payoff ("I tried X for 30
  days") without lying about
  it. The thumbnail makes a promise the video must keep — betrayal tanks watch
time and trust, which
  the algorithm punishes harder than low CTR.
- - - **Brand consistency.** Recognizable style (color treatment, layout, font)
  builds channel
  identity — viewers spot your videos in a crowded feed. Templates with flexible
zones balance
  consistency and freshness.

## Practical workflow

1. 1. 1. **Know the video's promise.** One sentence: why should someone click?
   The thumbnail visualizes
   this promise — the most compelling frame, result, or question from the video.
2. 2. 2. **Design thumbnail + title together.** Draft 3 title options, sketch 3
   thumbnail concepts.
   Check the pair: does the thumbnail add information or intrigue the title
doesn't? Cut redundancy.
3. 3. 3. **Compose boldly.** Large subject (fill 60%+ of frame), simple
   uncluttered background (blur or
   solid color), 3-5 word text max in heavy weight with outline/shadow, high
saturation and
   contrast.
4. 4. 4. **Test at size.** View at 120px wide (mobile feed size) and in dark
   mode. If it's muddy or
   unreadable, simplify — remove elements until it reads instantly.
5. 5. 5. **Build channel templates.** 2-3 layout templates (talking head,
   comparison, listicle) with
   locked brand elements. New thumbnails start from templates — speed plus
recognition.
6. 6. 6. **A/B test.** Test variations (YouTube's Test & Compare or manual
   swaps): change one variable
   (text vs no text, face vs object, color). Run 1-2 weeks, judge on CTR and
watch time together —
   CTR alone can mislead.
7. 7. 7. **Audit and refresh.** Quarterly: which thumbnails underperform?
   Refresh top-traffic videos'
   thumbnails first — small CTR gains on high-impression videos compound
enormously.

## Common pitfalls

- - - **Clickbait.** Shocking thumbnails for mundane videos. Short-term CTR
  spike, long-term trust and
  retention collapse — the algorithm notices.
- - - **Text overload.** Paragraphs on a thumbnail. At feed size it's gray mush
  — 3-5 words,
  billboard-sized, or no text at all.
- - - **Cluttered composition.** Five elements fighting for attention. One focal
  point, ruthlessly
  protected.
- - - **Ignoring mobile.** Designing on a 27" monitor, never checking the 120px
  reality. Most views
  are mobile — design for the small screen first.
- - - **Title-thumbnail redundancy.** Thumbnail text repeating the title
  word-for-word. Wasted space
  that could tease, intrigue, or show.
- - - **Inconsistent channel look.** Every thumbnail a different style — no
  recognition in the feed.
  Templates aren't boring; they're branding.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

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', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →