Street Portrait Artist logo

Street Portrait Artist

Community
kyungseo
street-portrait-artist

Analyze supplied portrait references into a stable impression map, then create a kind Street Caricature, Romance Watercolor portrait, or Paper-Cut Illustration with coherent feature relationships and targeted revision. Use when a real person's recognizable visual identity should be interpreted rather than traced. Do not use for graffiti or murals, restoration, face swaps, photorealistic retouching, personality inference, or imitation of a named living artist.

Overview

Publisherkyungseo
Repositoryskillstead
Skill namestreet-portrait-artist
Stars
83
Forks
17
Bundled files
10
LicenseLICENSE.txt
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.

  • 10 bundled files

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

  • Open source

    Published by kyungseo on GitHub. Read the source before you install it.

Installation

Install the Street Portrait Artist 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.
    https://github.com/kyungseo/skillstead/tree/main/skills/street-portrait-artist
  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/kyungseo/skillstead.git /tmp/skillstead
mkdir -p .claude/skills
cp -r /tmp/skillstead/skills/street-portrait-artist .claude/skills/street-portrait-artist
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Street Portrait Artist 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 Street Portrait Artist 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 Street Portrait Artist 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.

Street Artist

Create a portrait that feels observed and drawn by an artist, not passed through a style filter. Extract the subject's recognizable visual grammar once, then interpret it through one of three modes:

  • Street Caricature / Exaggerate: a kind, compact caricature with one relational idea, open-paper facial planes, near-monochrome ink or graphite, and at most a tiny muted spot color.
  • Romance Watercolor / Illuminate: a delicate watercolor portrait; choose the optional Editorial Watercolor treatment for a more observational face with loose painted surroundings.
  • Paper-Cut Illustration: a simple flat-color cartoon person with a thin paper edge inside the preserved photographic scene.

All modes must preserve the same identity relationships. They differ in how they interpret the subject. Paper-Cut Illustration preserves source proportions and placement.

Required References

Before generating or editing, read these files completely:

Then read only the selected mode reference:

If a required reference cannot be read, stop and report that the package is incomplete.

Use When

  • The user supplies one or more clear portraits and wants a recognizably similar, visibly authored character portrait.
  • The request calls for a street-fair caricature, cute caricature, hand-drawn ink portrait, delicate pen-and-watercolor portrait, lyrical character portrait, or a drawn paper-cut person inside a photographic setting.
  • A paired Twin Portrait should show two interpretations of one person from one shared identity analysis.

Do Not Use When

  • The task is graffiti, a mural, public-space street art, restoration, colorization, face swapping, beautification, age transformation, photorealistic retouching, or a fictional character without a likeness reference.
  • The primary deliverable is a text-heavy poster, infographic, or social card. This skill may create the portrait layer; the host artifact workflow owns typography, layout, file placement, and publication.
  • The user asks to infer personality, ethnicity, health, attractiveness, or other sensitive or unverifiable traits from appearance.
  • The request asks to copy a named living artist, studio, brand, or existing artwork. Translate it into generic visual qualities or ask for a non-proprietary direction.

Procedure

  1. Inspect only the references needed for the task. Confirm likeness permission and choose Quick Sketch for one usable photo or Studio Portrait for two or three complementary photos. Never average faces or combine poses.
  2. Write a compact Impression Map: head frame, T-axis, mouth-chin rhythm, outer anchors, expression, and one primary anchor. Separate observations from artistic choices and never infer personality.
  3. Choose the mode from the request. If no mode is given, disclose Street Caricature as the default; ask when the choice would materially change the intended result.
  4. Redesign relationships coherently. Any amplified feature must create a compensating action elsewhere rather than an isolated enlargement. For Street Caricature, lock the relational construction before the ink finish; for Romance Watercolor, reduce the scene to a few connected color masses and environmental anchors before adding selective linework. For Paper-Cut Illustration, simplify inside the preserved silhouette and keep scene contacts and occlusion. Preserve reference roles and expression unless the user requests a change.
  5. Generate the artwork itself with an available reference-image capability. For Paper-Cut Illustration, preserve the source aspect ratio and framing by default. For the other modes, default to social-feed-portrait at 4:5, targeting an exact 1080 x 1350 px export when the current surface can create and verify it. Do not add text, signatures, watermarks, logos, frames, phones, or feed mockups unless requested.
  6. Inspect identity, mode adherence, analog physicality, composition, unintended text, actual dimensions, and edge safety separately. Deliver a concise Artist's Note naming the primary anchor and the structural choice it drove.
  7. For a series or revision, use the consistency reference to separate identity, treatment, and requested changes. Change the Impression Map or one named rendering defect, restate accepted invariants, and preserve the best accepted result. Do not blindly regenerate after repeated identity drift.

Failure Boundary

  • If no accessible portrait is available, request an upload or attachment; never invent the subject or claim a local path was read.
  • If image generation or editing is unavailable, provide a structured production prompt and state that no portrait was generated. A prompt is not a finished artwork.
  • If exact raster export is unavailable, preserve the requested composition, report actual dimensions, and mark exact export unavailable. Never stretch the image or fabricate dimensions.
  • Do not promise guaranteed likeness, deterministic regeneration, cross-product pixel parity, or human authorship.
  • Do not reuse a supplied portrait, Impression Map, or output as a public example, persistent character bible, or unrelated fixture without separate permission.

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 Street Portrait Artist AI skill do?

Analyze supplied portrait references into a stable impression map, then create a kind Street Caricature, Romance Watercolor portrait, or Paper-Cut Illustration with coherent feature relationships and targeted revision. Use when a real person's recognizable visual identity should be interpreted rather than traced. Do not use for graffiti or murals, restoration, face swaps, photorealistic retouching, personality inference, or imitation of a named living artist.

Why use Street Portrait Artist on TypingMind?

Because you install it once and use it with any model. Street Portrait Artist 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 Street Portrait Artist in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kyungseo/skillstead/tree/main/skills/street-portrait-artist. 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 Street Portrait Artist?

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 Street Portrait Artist?

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

Is the Street Portrait Artist AI skill free?

Yes. It is published on GitHub by kyungseo under the LICENSE.txt license. 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 👇