agentleFS
vfarcicvfarcic/dot-ai/.claude/skills/infographic-generator/SKILL.md

infographic-generator

Skill336 starsChanged 10 months agoMITView on GitHub

Generate retro arcade style infographic prompts for documentation pages

10 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 9 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:

    Ask the user: "Which documentation page should this infographic be for?"

    line 14
  2. Distinctive:

    Read the specified documentation file to understand its content.

    line 20
  3. Distinctive:

    Create a retro arcade style prompt following this format:

    line 24
  4. Distinctive:

    When the user provides the image path:

    line 51
  5. Distinctive:

    Add the image to the documentation file at an appropriate location (usually near the top, after the title/intro)

    line 53
  6. Very specific:

    Use markdown image syntax without width constraints: !Infographic description

    line 54

“Common” is measured: kept by at least 6 in 10 of the 9 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

Generate Infographic Prompt

Generate an image AI prompt for creating a retro arcade style infographic for a documentation page.

Workflow

Step 1: Ask for the docs page

Ask the user: "Which documentation page should this infographic be for?"

Present options from the docs/ directory (use Glob to find all .md files in docs/), or let them specify a custom topic.

Step 2: Read the documentation

Read the specified documentation file to understand its content.

Step 3: Generate the image prompt

Create a retro arcade style prompt following this format:

Create a retro 8-bit pixel art infographic for "[PAGE TITLE]" from DevOps AI Toolkit.

Style: Retro arcade game aesthetic, pixel art, CRT glow effects, scanlines, neon pink/cyan on dark background, NES game instruction card style.

TOPIC: [One sentence describing what this page covers]

KEY CONCEPTS (visualize as power-ups/abilities):

[For each major section/concept in the doc, write ONE line like:]
1. [Icon emoji] [CONCEPT NAME]: [One sentence description - no bullet lists]

[Include 3-6 concepts depending on the doc's content]

Include pixel art icons, game-style UI elements, and achievement badges related to the topic.

Step 4: Present the prompt

Show the generated prompt in a code block so the user can copy it.

Then say: "Copy this prompt to your image generation AI. Once you have the image, tell me the file path and I'll add it to the documentation."

Step 5: Wait for image path

When the user provides the image path:

  1. Copy/move the image to the appropriate location in assets/images/
  2. Add the image to the documentation file at an appropriate location (usually near the top, after the title/intro)
  3. Use markdown image syntax without width constraints: ![Infographic description](../assets/images/filename.png)

Confirm the image was added to the doc.

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.