agentleFS
lorena-bordonaba-paulorena-bordonaba-pau/youtube-agent/.claude/skills/youtube-banner-spec/SKILL.md

youtube-banner-spec

Skill2 starsChanged 49 days agoMITView on GitHub

Technical specification for a YouTube banner — 2560x1440 and the mobile safe zone. Triggered when generating, reviewing or diagnosing a channel banner.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check it in the dry run: if that clause is not in the final prompt, something is wrong with the configuration.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Banner specification

WHEN

Any banner generation or review. Load it before writing the prompt: the safe zone cannot be fixed afterwards.

THE RULE THAT DECIDES EVERYTHING

The banner is uploaded at 2560x1440, but on mobile only a narrow horizontal strip across the vertical centre is visible. The top and bottom thirds are cropped away entirely.

Everything that matters — text, logo, channel name, faces, branding — goes inside that centre band. Above and below, only simple backgrounds: gradients, blurs, patterns, flat colour.

A banner that puts the channel name at the top disappears on mobile. It is the most frequent failure and the most invisible one from a desktop.

EXECUTION ORDER

  1. See the current banner before replacing it python3 tools/view_channel_packaging.py --only banner --md and open the file.
  2. Generate with the right type
    python3 tools/generate_image.py --type banner --prompt "..." --dry-run --md
    --type banner prepends the critical composition rule with the safe band. Check it in the dry run: if that clause is not in the final prompt, something is wrong with the configuration.
  3. Verify the result by opening it and checking, specifically, that with the top and bottom thirds covered you can still tell what the channel is about.
  4. Adjust dimensions without regenerating python3 tools/export_image.py --image PATH --type banner Leaves it at exactly 2560x1440. The crop is centred, so if the subject is off-centre you need to check it.

STYLE

  • Large, legible text; the banner is seen small on mobile.
  • Branding centred, inside the band.
  • The channel's palette, for consistency with the avatar. Load analyse-channel-packaging if you do not know it.

SOURCES

The image is source: generated. The dimensions after export_image are derived and verifiable in the file.

OUTPUT

  1. The banner file at exactly 2560x1440, opened and checked.
  2. Confirmation that everything important sits inside the centre band, checked with the top and bottom thirds covered.
  3. The model that generated it, named explicitly.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.