agentleFS
Sign inStart free
maroffomaroffo/claude-forge/skills/cover-image/SKILL.md

cover-image

Skill17 starsChanged 51 days agoMITView on GitHub

Generate editorial cover images from article context. Use when user wants a cover image, hero image, or editorial illustration for an article or blog post.

  • Reads credentials

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the article/context provided by the user.

    line 19
  2. Distinctive:

    Prefer architectural/technical metaphors over literal depictions

    line 33
  3. Distinctive:

    Keep the scene simple: one strong central image, not a collage

    line 34
  4. Distinctive:

    Avoid text, labels, or UI elements in the image

    line 35
  5. Very specific:

    Default output: cover.png in current directory

    line 68
  6. Distinctive:

    Default aspect ratio: 16:9 (landscape, editorial)

    line 69

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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

ABOUTME: Generate editorial cover images from article context using Gemini image generation

ABOUTME: Distills articles into hand-drawn sketch visual metaphors with ink stroke style

Cover Image Skill

Generate editorial cover images using Gemini's image generation. Distill article content into a visual metaphor rendered as a hand-drawn sketch.

Workflow

1. Understand the Article

Read the article/context provided by the user. Identify the core concept, tension, or insight that could become a visual metaphor.

2. Craft the Prompt

Build a prompt using this structure:

Black and white hand-drawn sketch, loose ink strokes, technical architectural drawing style.
[visual metaphor distilled from article context]. High contrast, minimalist, white background,
editorial tech illustration. --ar 16:9

Visual metaphor guidelines:

  • Translate abstract concepts into concrete imagery (e.g., "microservices" -> "separate buildings connected by bridges")
  • Prefer architectural/technical metaphors over literal depictions
  • Keep the scene simple: one strong central image, not a collage
  • Avoid text, labels, or UI elements in the image

3. Show Prompt for Approval

Present the crafted prompt to the user. Wait for confirmation before generating.

4. Generate

uv run ~/.claude/skills/_generate_image.py "<approved prompt>" --ar 16:9 -o cover.png

5. Report

Report the saved file path and suggest reviewing the image.

Example

Illustrative only: keep the style prefix and suffix fixed, and find the metaphor in each article's own tension rather than reusing this one.

Article about: "Why we migrated from monolith to microservices"

Prompt:

Black and white hand-drawn sketch, loose ink strokes, technical architectural drawing style.
A massive ancient stone building cracking apart, its fragments floating and reorganizing into
a constellation of small interconnected structures, linked by thin precise lines.
High contrast, minimalist, white background, editorial tech illustration. --ar 16:9

Notes

  • Requires GEMINI_API_KEY or GOOGLE_API_KEY in environment
  • Default output: cover.png in current directory
  • Default aspect ratio: 16:9 (landscape, editorial)
  • Uses shared script: ~/.claude/skills/_generate_image.py

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.

Check your setup, free