Systems Lab

Agent skill

youtube-thumbnail

Design a legible YouTube thumbnail whose visual promise is supported by the actual video.

activeSelf-containedInstructions only159 words

Filed under Onboarding, retention and expansion.

From timscheuerai/gtm-architecture-template · 51 skill entries · 13 · pushed 2026-09-17

What it does when it runs

Design a legible YouTube thumbnail whose visual promise is supported by the actual video.

Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about youtube-thumbnail

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗
git clone --depth 1 --filter=blob:none --sparse https://github.com/timscheuerai/gtm-architecture-template.git /tmp/gtm-architecture-template
git -C /tmp/gtm-architecture-template sparse-checkout set ".agents/skills/youtube-thumbnail"
mkdir -p ~/.claude/skills/youtube-thumbnail
cp -R "/tmp/gtm-architecture-template/.agents/skills/youtube-thumbnail/." ~/.claude/skills/youtube-thumbnail/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

The skill

Source on GitHub ↗

Reproduced in full from timscheuerai/gtm-architecture-template/blob/2c312c9398064ad3730c786647293458cb89632c/.agents/skills/youtube-thumbnail/SKILL.md, which is licensed MIT (repository). 159 words, 1 heading.

Make the thumbnail promise visible

Read the video's actual content, target viewer, title and context/brand/BRAND.md. Identify one concrete idea, contrast or outcome the video can fulfill. Use authentic supplied faces/screenshots where the brief calls for them.

Sketch a few distinct compositions, then choose the one that reads clearly at small size. Text should add information to the title, not repeat all of it. Do not invent result screenshots, endorsements or emotionally misleading scenes.

Use the available design/image tool and the actual brand rules. Verify current platform dimensions, file size and format requirements before claiming upload readiness. Keep editable source or the generation/edit brief with the export.

Inspect the thumbnail at full and small sizes for readability, cropping, contrast and factual accuracy. Use brand-review for a requested independent visual review, without spawning agents unless authorized by the user/environment.

Return the export and editable source, actual dimensions and any unverified upload constraint. Thumbnail creation alone does not upload or publish.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what youtube-thumbnail does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.