J Poses logo

J Poses

Community
ShinChven
j-poses

A library of alluring Japanese style photography poses.

Overview

PublisherShinChven
Repositorynano-banana-skills
Skill namej-poses
Stars
73
Forks
10
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the J Poses 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/ShinChven/nano-banana-skills/tree/main/skills/j-poses
  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/ShinChven/nano-banana-skills.git /tmp/nano-banana-skills
mkdir -p .claude/skills
cp -r /tmp/nano-banana-skills/skills/j-poses .claude/skills/j-poses
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable J Poses 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 J Poses 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 J Poses 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.

J Poses

A collection of refined and alluring poses inspired by Japanese photography styles. These poses focus on silhouette, line, and mood without specifying character appearance or environment.

Pose Library

  • Sultry Seated Lean: Seated on a low chair, legs crossed elegantly. One arm rests on the top leg, while the upper body leans slightly forward toward the lens, creating a sense of intimacy.
  • The Over-the-Shoulder Glance: Standing with the back to the camera, head turned to look directly into the lens. One hand rests lightly on the hip, emphasizing the curve of the back.
  • Reclining Sofa Pose: Lying on a sofa on one side, propped up by an elbow. The other hand rests on the hip or thigh, with legs slightly staggered for depth.
  • Graceful Tatami Kneel: Kneeling with hips resting on heels. The back is arched slightly, and hands are placed softly on the lap or used to gently brush hair away from the face.
  • Window-side Contemplation: Leaning against a window sill with one hip. One arm is raised, hand touching the window frame, while looking out with a soft, dreamy expression.
  • Side-Saddle Floor Sit: Sitting on the floor with both legs tucked to one side. One hand supports the weight behind the body, while the other rests on the knee, creating a long, flowing line.
  • Arching Stand: Standing tall with hands clasped behind the back. The chest is pushed forward slightly and the back is arched, creating a sophisticated and confident silhouette.
  • Soft Approach: Captured mid-stride walking toward the camera. The gaze is lowered slightly with a subtle smile, and one hand is gracefully adjusting a sleeve or accessory.
  • Table-side Intimacy: Sitting at a cafe table, chin resting softly on the palm of one hand. The other arm lies across the table, drawing the viewer into the personal space.
  • Languid Supine View: Lying flat on the back on a soft surface. The head is tilted back slightly toward the camera, with arms stretched loosely above the head, emphasizing a relaxed and alluring form.
  • The S-Curve Arch: Kneeling on a soft surface, torso twisted slightly toward the camera, one hand pulling back hair while the other rests on her thigh, emphasizing the waist and hip line.
  • The Leaning Intimacy: Standing with a slight forward lean, hands gently pulling at the neckline or collar of the outfit, shoulders shrugged to accentuate the collarbones and cleavage.
  • The Seated Recline: Sitting sideways with legs tucked, one arm supporting her weight behind her while the other hand trails up her leg or rests on her waist, creating a dynamic diagonal line.
  • The Over-the-Shoulder Tease: Back to the camera with a deep arch in the lower back, looking back with an intense gaze, hands resting on the small of the back or gently tugging at the hem of the garment.
  • The Soft Embrace: Standing or kneeling, arms crossed under the bust to push up and accentuate curves, fingers lightly grazing the skin of the upper arms or shoulders.
  • The Asymmetrical Femoral-Cross: Seated upright with legs crossed (right over left). Torso rotated slightly left, left hand resting on the thigh, and right hand touching the collarbone. Head tilted slightly, gazing directly forward.
  • The Affectionate Tuck: Subject sitting, pulling knees to chest and hugging their thighs, gazing affectionately at the viewer.

Frequently asked questions

What does the J Poses AI skill do?

A library of alluring Japanese style photography poses.

Why use J Poses on TypingMind?

Because you install it once and use it with any model. J Poses 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 J Poses in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ShinChven/nano-banana-skills/tree/main/skills/j-poses. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use J Poses?

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 J Poses?

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

Is the J Poses AI skill free?

Yes. It is published on GitHub by ShinChven under the MIT 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 👇