agentleFS
GoogleKnown publishergoogle-gemini/gemini-managed-agents-templates/ai-radio/skills/cover-image-generation/SKILL.md

cover-image-generation

Skill99 starsChanged 6 months agoApache-2.0View on GitHub

Generate cover images for the radio show using Gemini 3 Flash Image (with fallback to Pro).

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When using the --metadata option, this skill uses a set of predefined prompt templates and selects one at random to generate cover images.

    line 42
  2. Very specific:

    If you choose to use the --prompt option instead, you must construct the prompt yourself.

    line 46
  3. Distinctive:

    Do not ask for futuristic, cyberpunk or neon themes

    line 50
  4. Distinctive:

    Do not include any text other than the show title

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Image Generation Skill

This skill generates an appropriate cover image for the radio show based on a prompt, using the Gemini 3 Flash Image model, with a fallback to the Gemini 3 Pro Image model ("Nano Banana Pro") if needed.

Requirements

  • Python 3.10+
  • google-genai Python package (>= 2.0.1)

Instructions

  1. Generate an image (Recommended: use the metadata file directly):

    python3 skills/cover-image-generation/scripts/generate_image.py \
      --workspace ./workspace \
      --metadata ./workspace/data/show_notes.json

    Note: Using --metadata will automatically extract the show title and apply a random, high-quality prompt template. This is the preferred method.

    Alternative (Manual prompt):

    python3 skills/cover-image-generation/scripts/generate_image.py \
      --workspace ./workspace \
      --prompt "A prompt describing the image"
  2. Output:
    • The image will be saved to {workspace}/images/cover.png.

Model

  • Primary Model: gemini-3-flash-image-preview
  • Fallback Model: gemini-3-pro-image-preview
  • Resolution: 1:1 (default)

Prompting rules

When using the --metadata option, this skill uses a set of predefined prompt templates and selects one at random to generate cover images. It dynamically inserts the show title into the selected template.

  • Example Prompt: "A professional podcast cover image for a show titled 'AI Talk Radio' on the 'AI Talk Radio' station. The design features the text 'AI Talk Radio' in a bold, stylish white font centered on the cover. The background is a vibrant purple with a textured water ripple effect that covers the entire frame, creating a dynamic and clean aesthetic."

If you choose to use the --prompt option instead, you must construct the prompt yourself. In that case, follow these rules:

Forbidden themes

  • Do not ask for futuristic, cyberpunk or neon themes
  • Do not include any text other than the show title

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.