# Openloomi Lifestyle Image

Identify whether a user is asking OpenLoomi to generate a lifestyle image, portrait...

- Repository: https://github.com/melandlabs/openloomi (1038 stars)
- Category: AI and agents
- License: Apache-2.0
- Last updated: 2026-09-24
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add melandlabs/openloomi --skill openloomi-lifestyle-image -g -a claude-code -y`
Codex: `npx skills add melandlabs/openloomi --skill openloomi-lifestyle-image -g -a codex -y`
Cursor: `npx skills add melandlabs/openloomi --skill openloomi-lifestyle-image -g -a cursor -y`
Gemini CLI: `npx skills add melandlabs/openloomi --skill openloomi-lifestyle-image -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add melandlabs/openloomi`

## Description

Identify whether a user is asking OpenLoomi to generate a lifestyle image, portrait, personal visual, or lifestyle scene. Use this skill for chat messages that may request image generation for a user's lifestyle, identity, persona, personal brand, social profile, memories, interests, or real-life scene; distinguish true generation intent from ordinary image understanding, prompt-writing, editing, or negated requests.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# OpenLoomi Lifestyle Image

## Purpose

Decide whether the user is asking to generate a lifestyle image through OpenLoomi's existing lifestyle image flow. This skill only judges intent and prepares a decision signal for the host app. Do not call image generation providers from this skill.

## Decision

Return a lifestyle image generation decision only when the user clearly wants OpenLoomi to create or generate a lifestyle-oriented image.

Use `matched: true` when the request asks to generate, create, make, draw, design, render, or produce a lifestyle image, personal visual, avatar-like lifestyle scene, personal brand image, social profile visual, or life-scene image based on the user's profile, memory, interests, chat context, or uploaded reference image.

Use `matched: false` when the user is only asking to:

- Analyze, identify, describe, OCR, classify, or understand an uploaded image.
- Write or improve a prompt without asking to generate the image now.
- Edit an existing image without asking for lifestyle generation.
- Discuss image generation conceptually.
- Say not to generate an image, or says image generation is unnecessary.
- Ask an unrelated design, document, code, or chat question.

## Reference Images

Set `hasReferenceImage: true` when the current user message includes an uploaded image that appears intended as style, subject, persona, or visual reference for generation.

Do not set `matched: true` only because an image was uploaded. If the user asks what the image shows, who the character is, or asks for image understanding, return `matched: false`.

If the user uploads a reference image and also asks to generate a lifestyle image from or inspired by it, return `matched: true` and `hasReferenceImage: true`.

## Output Contract

When the host requests a structured decision, return only JSON with this shape:

The rest: https://github.com/melandlabs/openloomi/blob/HEAD/skills/openloomi-lifestyle-image/SKILL.md