Skip to main content
skill CX Codex

soviet-storybook-grotesque — Claude Code skill: setup & overview

soviet-storybook-grotesque transforms photos into strange retro storybook drawings with shaky ink lines, faded watercolor, and nonsensical English rhymes.

MIT 190 installs ★ 635 updated 2026-09-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add agentara/skills --skill soviet-storybook-grotesque -a claude-code
Open on GitHub

What soviet-storybook-grotesque does

This skill builds a precise image prompt that turns any reference photo into an unsettling old-print storybook illustration. Instead of copying every detail, it captures only core anchors: pose, subject count, clothes, and essential props. Everything else gets redesigned with shaky linework, pale washes, uneven paper texture, and intentionally clumsy character anatomy.

Each drawing includes an absurd handwritten rhyme embedded directly in the artwork. If your image model fails to render letters cleanly, the workflow guides the agent to reserve a blank caption box so you can add the sketchy handwriting using an image editor.

Feeding an actual reference picture is mandatory because the workflow stops immediately to ask for one if it is missing. Clean vector styles, cute faces, 3D polish, and realistic textures are explicitly forbidden in the prompt rules.

What it helps with

  • Stylize a photo into an unsettling storybook drawing
  • Write an absurd handwritten English caption for graphics
  • Strip cute and realistic tropes from image generation prompts
  • Recreate the look of vintage misregistered print and faded watercolor

Example prompts for the agent

  • Turn this photo into an unsettling vintage book illustration with a silly rhyme
  • Redraw this portrait as an awkward grotesque cartoon with faded watercolor
  • Apply the weird storybook style to this scene but leave the caption area blank

How to install soviet-storybook-grotesque

1Skills CLI (Vercel)

npx skills add agentara/skills --skill soviet-storybook-grotesque -a claude-code

2Manually: put the files in place

~/.claude/skills/soviet-storybook-grotesque/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/soviet-storybook-grotesque/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about soviet-storybook-grotesque

How to install soviet-storybook-grotesque in Claude Code?

Run npx skills add agentara/skills --skill soviet-storybook-grotesque -a claude-code. The definition will be placed in ~/.claude/skills/soviet-storybook-grotesque/SKILL.md.

What does soviet-storybook-grotesque do?

It prepares detailed prompts that guide image models to re-render photos as nervous, awkward cartoon art with dirty paper textures and strange rhyming captions.

How does it handle unreadable AI text?

It suggests creating the artwork with an empty caption space and adding the shaky handwritten text afterward in an image editor.

Source text

SKILL.md · MIT
---
name: soviet-storybook-grotesque
description: Transform a user-provided photo or image into a strange vintage Soviet or Eastern European children's book illustration with grotesque humorous cartoon energy, shaky ink, faded watercolor, dirty paper texture, awkward anatomy, nervous absurd expressions, sparse composition, and an absurd handwritten English rhyme. Use this skill when the user asks to turn a photo into an unsettling old children's book illustration, 1980s Eastern European illustration, weird Soviet cartoon book art, grotesque watercolor storybook art, or clumsy absurd illustrated caption style. Do NOT trigger for polished fantasy art, cute children's illustration, modern vector art, realistic portraits, anime, clean editorial illustration, or generic vintage filters.
---

# Soviet Storybook Grotesque

Transform the user's photo into a deliberately awkward, funny, slightly unsettling old-print children's book illustration.

## Workflow

1. Check for a source photo or image. If none is present, ask the user to provide one.
2. Identify only the visual anchors needed from the photo: subject count, broad pose, main action, key clothing, props, and obvious setting.
3. Use an image-generation or image-editing model with the photo as the visual reference. Preserve the source's basic subject roles and composition, but stylize aggressively.
4. Add a short absurd English caption inside the image unless the user explicitly asks for no text. Make it clumsy, handwritten, confusingly rhymed, and only loosely related to the image.
5. Review the result against the negative constraints. If it looks polished, cute, modern, realistic, decorative, or too detailed, regenerate or revise toward roughness and emptier space.

## Style Recipe

Use these ingredients directly in the image prompt:

- Thin shaky black ink lines, careless sketchy linework, uneven contours, and old-print roughness.
- Awkward anatomy, elongated limbs, weird proportions, stiff hands, uncomfortable facial expressions, and nervous absurd body language.
- Grotesque humorous cartoon energy: ridiculous rather than adorable, tense rather than cozy.
- Pale faded watercolor washes, washed-out muted colors, uneven coloring, dirty paper texture, and slightly misregistered print texture.
- Sparse composition with lots of empty paper space.
- Minimal random background details: small strange doodles, crooked objects, loose marks, stray patterns, or irrelevant tiny props.
- An authentically old Eastern European children's book illustration feeling from the 1980s, without referencing a specific living artist.

## Caption Direction

Write one or two short lines of absurd English. It should rhyme imperfectly, feel confused, and be slightly related to the image without explaining it.

Examples of caption logic:

```text
The uncle ate thunder, the teapot said soon,
my left shoe saluted a boiled little moon.
```

```text
Three knees for breakfast, one hat for the rain,
the window forgot how to whisper again.
```

Render the caption as part of the illustration: clumsy handwritten letters, uneven baseline, shaky spacing, imperfect ink, and no clean digital typography. If exact text is important and the image model cannot render it reliably, generate the artwork with a blank caption area, then add the caption afterward with an image-editing tool while matching the rough handwritten style.

## Negative Constraints

Avoid:

- Cute, charming, polished, cozy, pretty, glossy, aesthetic, or modern results.
- Realistic rendering, photographic texture, cinematic lighting, high detail, smooth anatomy, clean faces, or professional character-design polish.
- Slick vector art, anime, Pixar-like style, clean children's book cuteness, clean poster design, decorative maximalism, or saturated modern palettes.
- Dense backgrounds. Keep the environment minimal, strange, and loose.
- Faithful beauty retouching. The transformation should be strange, absurd, nervous, and intentionally clumsy.

## Prompt Template

```text
Transform the attached photo into a strange vintage Soviet / Eastern European children's book illustration from the 1980s. Preserve the basic subject count, pose, action, and key props from the photo, but redraw everything as an intentionally clumsy grotesque cartoon.

Use thin shaky black ink lines, awkward anatomy, elongated limbs, weird proportions, stiff hands, nervous uncomfortable facial expressions, chaotic movement, and ridiculous absurd energy. Make it funny and slightly unsettling rather than cute. Use pale faded watercolor washes, dirty yellowed paper texture, uneven coloring, washed-out muted colors, rough old-print texture, careless sketchy linework, and lots of empty space.

Keep the background minimal and random, with a few small strange doodles or crooked irrelevant details. Do not make it polished, aesthetic, modern, cute, detailed, realistic, glossy, cinematic, anime, vector, or clean.

Add a clumsy handwritten English caption inside the illustration: "[ABSURD RHYMING CAPTION]". The lettering should look shaky, uneven, and hand-drawn as part of the old illustration.
```

© agentara · MIT · agentara/skills

Similar skills

All skills for Design →

From the same set20

The whole set →
presentation-design presentation-design creates a 6-slide presentation storyboard as a single 3:2 composite image. Useful for concept validation and pitch deck visuals via image generation models. CX Codex +1 250installs article-to-html article-to-html turns Markdown or a document from the conversation into one self-contained HTML file. Use it for a static article page, not slides or a backend. CX Codex +1 220installs doctor-strange doctor-strange runs multi-branch causal scenario simulations using subagents and records synthetic projections into persistent assistant memory. CX Codex +1 212installs mega-goal-prompt mega-goal-prompt interviews you step by step to build a structured /goal mega prompt for autonomous tasks in Claude Code or Codex CLI. CX Codex +1 195installs feature-dev-loop feature-dev-loop orchestrates multi-step feature development: planning, subagent reviews, TDD execution, and HTML acceptance reports. CX Codex +1 187installs publish-research-site The publish-research-site skill turns a topic or thesis into an interactive, image-rich site backed by citations, then deploys it with Vercel CLI. Use it to publish a research report or an interactive story. CX Codex +1 142installs torn-paper-collage-poster Generates image-generation prompts and workflows for editorial torn-paper collage posters with ripped edges, tape, and stamps. CX Codex +1 135installs engineering-small-prs engineering-small-prs turns a large feature, refactor or migration into small pull requests, with a merge order and a rollback plan. CX Codex +1 133installs

Project sponsors

Companies that keep this analytics open