agentleFS
RylaispiritRylaispirit/rylai-codex-hermes-skills/skills/notion-infographic/SKILL.md

notion-infographic

Skill56 starsChanged 3 months agoMITView on GitHub

Turn articles, notes, transcripts, or research into a consistent series of clean hand-drawn infographics with concise text and visual verification.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    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:

    Create a coherent infographic series from source material.

    line 18
  2. Distinctive:

    Read the complete source before proposing images.

    line 22
  3. Distinctive:

    Write a short series plan before generation:

    line 25
  4. Distinctive:

    Add the requested aspect ratio and language.

    line 63
  5. Distinctive:

    Keep on-image text short. When exact typography matters, generate the artwork without text and add text later with a local deterministic …

    line 65
  6. Distinctive:

    Do not add a cover or summary merely to increase the count.

    line 73
  7. Distinctive:

    Use an image-generation tool, MCP server, or API configured in the active runtime.

    line 77
  8. Distinctive:

    Do not assume a runtime-specific tool name exists.

    line 78
  9. Distinctive:

    If a backend cannot preserve a consistent character, use the best approved image as a visual reference for later generations.

    line 79
  10. Distinctive:

    Every claim comes from the supplied source or is clearly labeled as interpretation.

    line 86
  11. Distinctive:

    No external logo, trademarked UI, remote asset, or creator signature appears unless the user supplied and authorized it.

    line 88

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Rylai Notes Infographic

Create a coherent infographic series from source material. This is an original Rylai workflow for Codex, Hermes, and Claude. The visual direction is a general notebook-style aesthetic and is not an official Notion product or brand asset.

Workflow

  1. Read the complete source before proposing images.
  2. Extract the central promise and the smallest set of independent supporting ideas.
  3. Honor a user-specified image count. Otherwise create three to eight images; use at most twelve.
  4. Write a short series plan before generation:
[
  {
    "file": "infographic-01.png",
    "role": "cover",
    "headline": "Short visible headline",
    "message": "One idea the image must communicate",
    "scene": "Concrete visual metaphor or diagram"
  }
]
  1. Generate images one at a time so the next prompt can correct consistency problems.
  2. Inspect every result. Regenerate images with unreadable text, accidental logos, inconsistent characters, clipped content, or a different palette.
  3. Deliver the ordered files and a one-line description of the series.

Prompt Construction

Build each prompt from a fixed style block plus one variable scene block.

Fixed style block:

Rylai notebook infographic, editorial hand-drawn linework on warm white paper,
confident imperfect marker strokes, simple flat shapes, generous whitespace,
black ink with teal, coral, and golden-yellow accents, clear visual hierarchy,
friendly human proportions, minimal decoration, no gradients, no 3D rendering,
no photorealism, no logos, no watermark.

Variable scene block:

  • State the one idea for this image.
  • Describe a concrete subject, diagram, sequence, or comparison.
  • Specify only the essential visible labels.
  • Repeat any recurring character, clothing, props, and palette exactly.
  • Add the requested aspect ratio and language.

Keep on-image text short. When exact typography matters, generate the artwork without text and add text later with a local deterministic editor.

Series Structure

  • Cover: topic and clear promise.
  • Body: one independent idea per image.
  • Summary: synthesis, checklist, or call to action when useful.

Do not add a cover or summary merely to increase the count. Merge overlapping ideas and split overloaded images.

Runtime Mapping

  • Use an image-generation tool, MCP server, or API configured in the active runtime.
  • Do not assume a runtime-specific tool name exists; verify the available capability before generation.
  • If a backend cannot preserve a consistent character, use the best approved image as a visual reference for later generations.
  • Save outputs in the user's workspace with zero-padded names such as infographic-01.png.

Quality Gate

  • The image communicates one idea within three seconds.
  • Text is readable at the target publishing size.
  • Every claim comes from the supplied source or is clearly labeled as interpretation.
  • Palette, line quality, character design, margins, and aspect ratio match across the series.
  • No external logo, trademarked UI, remote asset, or creator signature appears unless the user supplied and authorized it.

Authored by Rylai for Codex, Hermes, and Claude.

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.