Acg Character Settei logo

Acg Character Settei

Community
Innei
acg-character-settei

Use when generating an ACG (anime/manga) character settei sheet (キャラ設定資料) — multi-view full-body lineup, expression list, detail callouts, color palette — from a template settei image plus a single character reference image. Built on top of gemini-image-generation; this skill encodes the layout-locking + identity-locking prompt pattern that reliably produces settei-style output.

Overview

PublisherInnei
RepositorySKILL
Skill nameacg-character-settei
Stars
81
Forks
2
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Acg Character Settei 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/Innei/SKILL.git /tmp/SKILL
mkdir -p .claude/skills
cp -r /tmp/SKILL/skills/content/acg-character-settei .claude/skills/acg-character-settei
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Acg Character Settei 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 Acg Character Settei 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 Acg Character Settei 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.

ACG Character Settei Generation

Overview

Produce a horizontal anime character design sheet by feeding the model two reference images at once:

  1. Template image — supplies layout, composition, line weight, palette aesthetic, and white background.
  2. Character image — supplies identity (hair, eyes, face, outfit, expression).

The skill is a thin wrapper over gemini-image-generation. Read that skill first for client setup, retry pattern, and watermark handling.

When to Use

  • User has a settei template (any artist's character sheet) and wants to restyle a different character into the same sheet format.
  • User wants a clean three-view + expression-sheet + detail-callout layout for an OC, VTuber, or avatar character.

Skip when:

  • Only one full-body pose is needed → use plain gemini-image-generation instead.
  • The template requires legible Japanese annotations as real text (Gemini cannot render exact text reliably; treat the script labels as decorative).

Inputs

VariableMeaning
TEMPLATE_PATHPath to the settei template image (defines layout).
CHARACTER_PATHPath to the character reference image (defines identity).
OUTFIT_DESCOne-sentence outfit description, locked across all three full-body views.
OUT_PATHOutput PNG path.

Workflow

text
[1] Inspect both inputs
      -> read template to identify panels (full-body count, expression count, callouts, palette)
      -> read character to extract identity tokens (hair, eyes, blush, accessories, outfit)

[2] Compose the prompt with two locked blocks
      -> LAYOUT block: lock template's composition, line style, background, panel arrangement
      -> IDENTITY block: lock character's hair / eyes / accessories / outfit, applied to every panel

[3] Call gemini-3.1-flash-image-preview
      -> contents = [prompt, template_image, character_image]
      -> aspect_ratio = "16:9", image_size = "2K"

[4] Verify
      -> three full-body views all wear the same outfit
      -> expression row matches template count
      -> character identity matches reference (hair color, eye color, accessories)
      -> if drift, tighten the locked block that drifted and retry; do not patch the output

Prompt Pattern

Two blocks, positive instructions, ≤ ~200 words total. Long negative-list prompts trigger MALFORMED_FUNCTION_CALL.

text
Create a horizontal anime character settei sheet matching the EXACT layout,
composition, line weight, soft watercolor shading, and pure white background
of the FIRST reference image:
- left: three full-body standing views (front, side, back)
- upper right: row of small head-and-shoulder expression variations
  (gentle smile, blush, surprised, sleepy, pout, happy)
- lower right: close-up detail callouts (eye, <key outfit detail>) and small
  color-palette swatch dots
- thin pencil-style annotation lines and tiny handwritten-style note marks
  (decorative, no need to read)

The character must be the girl from the SECOND reference image:
<2–4 short identity sentences: hair, bangs, eye color, accessories, expression>.
She wears <OUTFIT_DESC>. Keep the same outfit consistent across all three
full-body views.

Art style: soft anime cel-shading with light watercolor highlights, clean
thin linework, bright airy palette, white paper background — match the first
reference's aesthetic exactly.

Rules

  • Always pass exactly two reference images: template first, character second. Order matters — the model treats the first image as the structural template.
  • Lock the outfit explicitly with Keep the same outfit consistent across all three full-body views. Without this, side and back views drift to different outfits.
  • Do not include negative lists (do NOT add ...). Use positive substitutes.
  • Treat label text as decorative. Never request specific Japanese strings; the model will produce plausible-looking marks but not real readable text.
  • Aspect ratio 16:9, size 2K matches the typical settei canvas. Use 1K for fast iteration. On Vertex (VERTEX_AI_KEY or GOOGLE_GENAI_USE_VERTEXAI=true), image_size is dropped automatically — the model uses its default resolution.
  • Identity drift fix: re-extract identity tokens from the character reference and compress to ≤ 4 sentences; do not over-describe.
  • Auth: any one of GOOGLE_AI_STUDIO_API_KEY / GEMINI_API_KEY / GOOGLE_API_KEY (AI Studio), or VERTEX_AI_KEY (Vertex Express), or GOOGLE_GENAI_USE_VERTEXAI=true + GOOGLE_CLOUD_PROJECT/LOCATION (Vertex ADC). Never read .env directly.

Script

scripts/gen_settei.py — copy, edit the four constants at the top, run with uv run. Inline uv deps declared at the top of the file.

bash
uv run skills/content/acg-character-settei/scripts/gen_settei.py

Verification

  • Open the output PNG; confirm three distinct full-body views with the SAME outfit.
  • Confirm expression row count matches template.
  • Confirm character hair color / eye color / accessory placement matches the character reference.
  • If a Gemini sparkle ✦ leaked in (from a Gemini-sourced template), add the watermark-removal clause from gemini-image-generation and retry.

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 Acg Character Settei AI skill do?

Use when generating an ACG (anime/manga) character settei sheet (キャラ設定資料) — multi-view full-body lineup, expression list, detail callouts, color palette — from a template settei image plus a single character reference image. Built on top of gemini-image-generation; this skill encodes the layout-locking + identity-locking prompt pattern that reliably produces settei-style output.

Why use Acg Character Settei on TypingMind?

Because you install it once and use it with any model. Acg Character Settei 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 Acg Character Settei in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Innei/SKILL/tree/main/skills/content/acg-character-settei. 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 Acg Character Settei?

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 Acg Character Settei?

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

Is the Acg Character Settei AI skill free?

It is published on GitHub by Innei. 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 👇