agentleFS
TIKAZITIKAZI/TIKAZ-Codex-Visual-Content/xiaohei-article-illustrator/SKILL.md

xiaohei-article-illustrator

Skill0 starsChanged 3 months agoMITView on GitHub

Art-direct concise hand-drawn Chinese article illustrations from an article thesis using a small dark character, white space, sparse color annotations, visual metaphor, shot cards, and publishing-size QA. Use for conceptual article images, workflow metaphors, knowledge posts, and explanatory editorial illustrations.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    Very specific

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

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

    Use a mostly white hand-drawn field, one small dark character as guide rather than mascot wallpaper, and sparse red/orange/blue annotations …

    line 23
  2. Distinctive:

    Keep Chinese labels short and verified.

    line 24
  3. Distinctive:

    Do not imitate a living artist or copy an upstream example image.

    line 28

≈ “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

Xiaohei Article Illustrator

Designed, integrated, independently refactored, and continuously maintained by TIKAZ.

TIKAZ Edition

  • Type: original art-direction workflow; no reference images or generator-specific assets are bundled.
  • TIKAZ contribution: thesis-to-shot translation, metaphor selection, character role limits, label budget, accessibility text, and consistency QA.

Inputs

Accept the article or thesis, audience, publishing ratio and size, required message, factual labels, preferred delivery format, and any established character references.

Workflow

  1. Extract the article's single message, audience, publishing ratio, and what the image must explain rather than decorate.
  2. Choose one mechanism or metaphor and write a shot card: message, scene, composition, character action, labels, palette, forbidden elements, and alt text.
  3. Use a mostly white hand-drawn field, one small dark character as guide rather than mascot wallpaper, and sparse red/orange/blue annotations only where they clarify causality.
  4. Keep Chinese labels short and verified. Avoid large title text unless requested.
  5. Generate or draw with the tool available in the user's environment; do not assume a particular image provider.
  6. Review at publishing size for message recognition, text accuracy, hierarchy, cropping, character consistency, and accessible alternative text.

Do not imitate a living artist or copy an upstream example image. Translate desired qualities into composition, line, palette, and narrative constraints.

Output contract

Return the thesis, chosen metaphor, shot card, exact labels, composition and palette rules, forbidden elements, alt text, source and license notes, and final asset or editable production specification.

Validation and fallback

Review at publishing size and compare every label plus factual claim with the source. If no drawing or image tool is available, return a self-contained SVG/HTML composition plan or production-ready shot card. Do not claim a visual was created when only a prompt exists.

Example and limits

Use xiaohei-article-illustrator to turn this article into one white-background hand-drawn metaphor, with short verified Chinese labels and accessible alt text.

Do not imitate a living artist or copy an upstream example image. Translate desired qualities into composition, line, palette, and narrative constraints.

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.