skills.rest
melandlabs
melandlabsOFFICIAL
Explore all skills by this author →
𝕏@AlloomiAIGitHub

openloomi-lifestyle-image

Detects user intent to generate lifestyle images and returns a structured JSON decision.

1.0k|46|Updated Apr 10, 2026
Search Tags:#image generation#intent classification#JSON output#reference image#chat routing#OpenLoomi#lifestyle image
One-click install
npx skills add https://github.com/melandlabs/openloomi --skill openloomi-lifestyle-image
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: openloomi-lifestyle-image
Source: https://github.com/melandlabs/openloomi/tree/main/skills/openloomi-lifestyle-image
Command: npx skills add https://github.com/melandlabs/openloomi --skill openloomi-lifestyle-image

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Chat applications need to distinguish genuine image generation requests from ordinary image questions, prompt-writing help, or negated requests. This Skill classifies whether a user message asks OpenLoomi to generate a lifestyle image, so the host app only triggers its image generation flow when appropriate.

Core Features & Use Cases

  • Intent Classification: Returns a boolean matched decision with a high, medium, or low confidence level for lifestyle image generation requests.
  • Reference Image Detection: Sets hasReferenceImage when an uploaded image is intended as a style, subject, or persona reference for generation.
  • Structured Output Contract: Produces a strict JSON object with matched, confidence, reason, hasReferenceImage, and an optional refinedPrompt.
  • Use Case: A user says "Use this photo as a style reference and create a lifestyle portrait." The Skill returns matched: true with hasReferenceImage: true, while a message like "What character is in this image?" returns matched: false.

Quick Start

Ask the assistant to decide whether the message "Generate a lifestyle image for my LinkedIn profile based on my interests" is a lifestyle image generation request and return the JSON decision.

Frequently Asked Questions about openloomi-lifestyle-image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect image generation intent in chat messages?▼

Use this intent classification skill to evaluate the user message against generation verbs like generate, create, draw, or render combined with lifestyle image subjects. It returns a JSON decision with matched, confidence, and reason fields.

How to distinguish image generation requests from image understanding questions?▼

Requests to analyze, describe, OCR, or identify an uploaded image return matched: false, while requests to create or generate a lifestyle visual return matched: true. Uploading an image alone never triggers a positive match.

Does this skill generate images itself?▼

No, it only judges intent and prepares a decision signal for the host app. Image generation provider calls are handled separately by OpenLoomi's existing lifestyle image flow.

What output format does the lifestyle image intent decision use?▼

It returns JSON with matched (boolean), confidence (high, medium, or low), reason (snake_case string), hasReferenceImage (boolean), and an optional refinedPrompt summarizing the generation intent.

When should the confidence level be medium instead of high?▼

Use medium when lifestyle generation is plausible but underspecified, such as vague requests lacking a clear subject or purpose. Reserve high for explicit requests to generate an image now, and low with matched: false for ordinary chat.

Related Skills

Explore More Product & Management Skills→
liuyu520liuyu520
2

webui-attachment-upload

Encode WebUI attachments as base64 and deliver them via WebSocket to Claude Code CLI.

Community
Advanced
jordanurbsjordanurbs
1

venice-video-model-routing

Route Venice AI video generation models and reference strategies for character consistency.

Community
Advanced
theLightArchitecttheLightArchitect

CORSO

Orchestrate CORSO operations for personality, build cycles, memory enrichment, and security scanning.

Community
Advanced
spamschspamsch
29

image_generation

Generate images from text descriptions using native image generation models.

Community
Intermediate