Riso Relic logo

Riso Relic

Organization
vm0-ai
riso-relic

Pop-art retro risograph poster of a single nostalgic everyday object — saturated single-color background, bold black ink outlines, halftone/riso grain, hand-drawn doodle accents (sparkles, squiggles, dots, music notes, lightning), tiny white "SMALL OBJECTS IN TIME" banner at top, chunky retro display headline at bottom with offset black drop-shadow. Trigger when user says /riso-relic, asks for a "riso poster", a "small objects in time" illustration, or any new piece in this nostalgic pop-art relic-object style.

Overview

Publishervm0-ai
Repositoryvm0-skills
Skill nameriso-relic
Stars
76
Forks
18
Bundled files
5
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vm0-ai on GitHub. Read the source before you install it.

Installation

Install the Riso Relic AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vm0-ai/vm0-skills.git /tmp/vm0-skills
mkdir -p .claude/skills
cp -r /tmp/vm0-skills/illustration-template/riso-relic .claude/skills/riso-relic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Riso Relic in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Riso Relic on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Riso Relic is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/riso-relic — locked retro-relic risograph poster style

This skill produces single-object pop-art posters in the riso-relic house style: one nostalgic everyday object sitting dead-center on a saturated single-hue field, framed by a tiny "SMALL OBJECTS IN TIME" banner at the top and a chunky retro headline at the bottom, with hand-drawn doodle accents floating around the hero. Think mid-century sticker-pack meets risograph print zine — flat, tactile, and a little bit grainy.

Each invocation swaps only a handful of dials — every other style axis stays locked.

Prompt interpretation

The user will usually give a short brief — sometimes just an object ("rotary phone"), sometimes an object plus a vibe ("walkman, 80s mall energy"). Your job is to turn that into a full poster brief without stopping to ask:

  1. Pick a hero object from the brief. If the user only gave a vibe, pick the most evocative everyday relic for that vibe.
  2. Choose a saturated background hue that matches the object's era + mood. One color, no gradient.
  3. Pick an accent palette of 2–3 colors that pop against the background — these carry the doodles and the headline fill.
  4. Write a 1–3 word headline in chunky all-caps that captures the feeling the object gives off (e.g. RING RING, MIX TAPE, PLAY LOUD, SAY CHEESE).
  5. Pick a doodle vocabulary — which little hand-drawn marks float around the hero (sparkles, squiggles, dots, music notes, lightning, motion lines, hearts, sound-waves, ZZZs…). Pull from the object's emotional world.
  6. Hold the locked frame — banner, drop-shadow, grain, black outlines, centered composition — those never move.

Bias toward objects with high tactile nostalgia: things people held, pressed, wound, or carried. Avoid abstract concepts; avoid logos; avoid people.

Locked style axes (NEVER vary)

Composition

  • Single hero object, centered, dead-symmetric — the object owns the visual center of mass
  • Portrait canvas (recommended 1024×1536)
  • Headline reads at the bottom; small banner reads at the top; hero sits between them
  • No backgrounds, no scenery, no horizon line — the object floats on the color field

Line quality

  • Bold black ink outlines on every shape, slightly imperfect like a hand-inked stencil
  • Simple cel-shading — one or two flat shadow tones per object, never airbrushed
  • No gradients, no 3D rendering, no soft modeling — flat vector with weight

Surface

  • Riso / halftone grain overlay across the whole canvas — visible noise, tactile print feel
  • Slight ink-misregistration vibe acceptable (one accent color nudged a pixel or two)
  • The grain is the only texture — no other photo textures, no fabric, no paper-curl

Background

  • One saturated hue filling the entire canvas — no gradient, no vignette, no second color band
  • Hue is one of: hot magenta, mustard yellow, sky blue, tomato red, deep violet, kelly green, cobalt, burnt orange, chartreuse, blush pink (or a sibling)

Top banner

  • Small white rectangular banner with thin black border, centered horizontally near the top edge
  • Contains small all-caps text — default copy: "SMALL OBJECTS IN TIME"
  • Simple sans-serif, tracked-out slightly, never decorative

Headline (bottom)

  • Chunky retro display face, all-caps, thick condensed letters — 70s/80s poster vibe
  • Fill is cream-white (not pure white) with a solid offset black drop-shadow behind it
  • 1–3 words; never a full sentence

Doodle accents

  • Floating around the hero, never overlapping its silhouette
  • Drawn in the same hand-inked weight as the hero, in the accent palette
  • Vocabulary: sparkle stars (✦/✧), squiggly motion lines, scattered dots, tiny lightning bolts, music notes, hearts, sun rays, sound-wave arcs, zigzags, "ZZZ" squiggles, small triangles
  • 6–12 accent marks total — sparse enough to breathe, dense enough to feel alive

Variable axes (the five dials)

These are the only things that should change between pieces.

#AxisWhat it controlsExample values
1Hero objectThe nostalgic everyday relic that owns the canvasrotary phone · boombox · Polaroid · alarm clock · cassette · Walkman · Game Boy · lava lamp · Zippo · roller skate · soda bottle · ticket stub · CRT TV · lipstick · disposable camera
2Background hueThe single saturated color filling the canvashot magenta · mustard yellow · sky blue · tomato red · deep violet · kelly green · cobalt · burnt orange · chartreuse · blush pink
3Accent palette2–3 contrast colors for the doodles + headline fill highlightscream + teal + red · lime + hot-pink + yellow · white + coral + lemon · cream + cyan + black
4Headline copy1–3 chunky all-caps words tied to the object's feelingPLAY LOUD · RING RING · SAY CHEESE · WAKE UP · MIX TAPE · STAY TUNED · FIZZ POP · INSTANT
5Era / moodThe decade or feeling-tone the piece evokes; drives object choice and doodle vocabulary50s diner · 60s domestic · 70s vacation · 80s mall · 90s arcade · atomic age · mid-century kitchen

Brief template

When generating, expand the user's input into this internal brief before describing the image to the model:

Hero object: <one specific named object, with era>
Background: <single saturated hue>
Accents: <2–3 colors>
Headline: <1–3 words, all caps>
Banner: SMALL OBJECTS IN TIME  (override only if user explicitly asks)
Mood: <one phrase>
Doodle vocabulary: <4–6 marks pulled from the object's world>

Worked examples

Five reference pieces below — each holds the locked frame and varies the five dials.

Example 1 — boombox · hot magenta · "PLAY LOUD" (80s mall energy)

boombox · hot magenta · PLAY LOUD

  • Hero: chunky 1980s stereo cassette boombox, two big speakers, antenna up
  • Background: hot magenta
  • Accents: cream + lime green + yellow
  • Doodles: sparkle stars, music notes, lightning bolts, scattered dots
  • Headline: PLAY LOUD

Example 2 — rotary phone · mustard yellow · "RING RING" (60s domestic)

rotary phone · mustard yellow · RING RING

  • Hero: 1960s rotary dial telephone, curly cord, finger dial
  • Background: mustard yellow
  • Accents: cream + tomato red + teal
  • Doodles: sound-wave arcs near handset, zigzags, sparkles, scattered dots, lightning
  • Headline: RING RING

Example 3 — Polaroid · sky blue · "SAY CHEESE" (70s vacation)

Polaroid · sky blue · SAY CHEESE

  • Hero: boxy Polaroid-style instant camera, rainbow stripe, blank photo ejecting
  • Background: sky blue
  • Accents: white + coral pink + lemon yellow
  • Doodles: tiny sun, hearts, zigzags, motion lines, sparkles
  • Headline: SAY CHEESE

Example 4 — twin-bell alarm clock · tomato red · "WAKE UP" (morning rush)

twin-bell alarm clock · tomato red · WAKE UP

  • Hero: vintage twin-bell mechanical alarm clock, hands at 7:00
  • Background: tomato red
  • Accents: cream + cyan + black
  • Doodles: sound-wave arcs around the bells, "ZZZ" squiggles, sparkles, dots
  • Headline: WAKE UP

Example 5 — cassette tape · deep violet · "MIX TAPE" (80s nostalgia)

cassette tape · deep violet · MIX TAPE

  • Hero: 80s compact cassette, visible spools, hand-scrawled "SIDE A" label
  • Background: deep violet
  • Accents: lime green + hot pink + yellow
  • Doodles: music notes, hearts, lightning, sparkles, zigzags
  • Headline: MIX TAPE

Anti-patterns

  • ❌ Two or more hero objects — the frame is a one-object poster; never a still-life
  • ❌ A scene background (a desk, a wall, a horizon) — the field must be a single flat color
  • ❌ Gradient background, vignette, or a second color band — flat saturated hue only
  • ❌ Photorealism, 3D modeling, soft airbrushed shading — must read as flat vector + grain
  • ❌ Doodle accents overlapping the hero — they orbit, they never collide
  • ❌ Headline in a thin / modern / serif face — must be chunky retro display
  • ❌ Headline without the offset black drop-shadow
  • ❌ More than ~12 accent marks — the canvas should still breathe
  • ❌ Headline that is a full sentence — keep to 1–3 punchy words
  • ❌ Modern / digital objects (smartphones, AirPods, laptops) — defeats the "relic" feel
  • ❌ Adding a human face or figure — the object is the only protagonist

Output evaluation checklist

Before declaring a piece done, verify:

  • Exactly one hero object, centered, dead-symmetric
  • Saturated single-hue background fills the entire canvas
  • Top banner present with "SMALL OBJECTS IN TIME" (or user-specified copy)
  • Bottom headline in chunky retro all-caps with offset black drop-shadow
  • 6–12 doodle accents in the accent palette, floating, not overlapping the hero
  • Visible halftone / riso grain across the canvas
  • Bold black ink outlines on hero and all accents
  • No gradients, no photoreal textures, no second background color, no scenery

Portability note

This style is designed to be model-agnostic at the semantic level — the spec describes what the image must look like, not which model produces it. It generates cleanly on broad-distribution image models (GPT-Image-2, Flux, Qwen-Image, Seedream 5). Higher-fidelity poster faces (clean type, accurate halftone) are easier on GPT-Image-2 at high quality and 1024×1536 portrait size. If a model struggles with the inline banner text, allow the banner to render as a small clean rectangle and overlay the "SMALL OBJECTS IN TIME" copy in post — the rest of the style should still hold.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Riso Relic AI skill do?

Pop-art retro risograph poster of a single nostalgic everyday object — saturated single-color background, bold black ink outlines, halftone/riso grain, hand-drawn doodle accents (sparkles, squiggles, dots, music notes, lightning), tiny white "SMALL OBJECTS IN TIME" banner at top, chunky retro display headline at bottom with offset black drop-shadow. Trigger when user says /riso-relic, asks for a "riso poster", a "small objects in time" illustration, or any new piece in this nostalgic pop-art relic-object style.

Why use Riso Relic on TypingMind?

Because you install it once and use it with any model. Riso Relic is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Riso Relic in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vm0-ai/vm0-skills/tree/main/illustration-template/riso-relic. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Riso Relic?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Riso Relic?

As many as you like. As long as a model supports skills, you can use Riso Relic with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Riso Relic AI skill free?

It is published on GitHub by vm0-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇