skills.rest
aiyinluya
aiyinluyaCOMMUNITY
Explore all skills by this author →
GitHub

sn-image-base

Generate images, recognize visuals, and optimize text via multiple LLM backends.

2|Updated May 19, 2026
Search Tags:#image generation#vlm#vision recognition#openai compatible#llm text optimization#api key config
One-click install
npx skills add https://github.com/aiyinluya/SenseNova-Skills-Studio --skill sn-image-base-aiyinluya
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sn-image-base
Source: https://github.com/aiyinluya/SenseNova-Skills-Studio/tree/main/skills/sn-image-base
Command: npx skills add https://github.com/aiyinluya/SenseNova-Skills-Studio --skill sn-image-base-aiyinluya

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill removes the complexity of wiring up image generation, image recognition (VLM), and text optimization (LLM) across different model providers, returning clean results ready for upper-layer skills.

Core Features & Use Cases

  • Image generation (sn-image-generate): turns a prompt into an image by calling a text-to-image backend (supports SenseNova, Nano Banana, and OpenAI-compatible image endpoints).
  • Image recognition (sn-image-recognize): analyzes one or more images with a vision-capable model using OpenAI-compatible or Anthropic Messages-compatible chat protocols.
  • Text optimization (sn-text-optimize): rewrites/optimizes text using an LLM with the same shared chat runtime approach.
  • Provider-agnostic configuration: uses environment variables with prioritized fallbacks, so you can override keys, base URLs, models, and interface types without changing code.

Quick Start

Ask your agent to run sn-image-generate with a prompt to produce an image, for example: "Generate a product banner image for a new skincare launch and return the saved image path."

Frequently Asked Questions about sn-image-base

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

FAQPage Schema
How do I generate images from text prompts using an OpenAI-compatible API?▼

Generating images from text prompts involves calling a text-to-image backend via an OpenAI-compatible endpoint. This skill executes that process by routing your prompt through configured providers like SenseNova or Nano Banana to return a saved image file path.

Can I use vision recognition models to analyze and caption multiple images?▼

Vision recognition models can analyze and caption multiple images using OpenAI-compatible or Anthropic Messages-compatible chat protocols. This skill passes your input images to a vision-capable model to perform structured VLM analysis and return descriptive text.

How do I configure environment variables to switch between different LLM providers?▼

Configuring environment variables to switch LLM providers requires setting prioritized fallbacks for API keys, base URLs, models, and interface types. This skill reads those environment variables to override provider configurations without altering the underlying code.

Does this tool support text optimization for office workflows?▼

Text optimization for office workflows is supported through LLM-based text rewriting. This skill uses a shared chat runtime to process your input text, optimize the phrasing, and return the refined content ready for document integration.

What's the best way to run image generation and text optimization in a unified runtime?▼

The best way to run image generation and text optimization in a unified runtime is through a shared chat execution layer. This skill utilizes a unified runner execution to handle both visual and text tasks across multiple provider endpoints.

Why do I need a YAML-declared skill entry for deterministic CLI usage?▼

A YAML-declared skill entry is needed for deterministic CLI usage to ensure structured tool interfaces and validated execution. This skill requires this declaration to manage environment-variable fallbacks and execute commands predictably across different model providers.

Related Skills

Explore More Design & Creative Skills→
0xHoneyJar0xHoneyJar
1

loa-credentials

Manage API credentials across environment variables, encrypted stores, and dotenv files.

Official
Intermediate
smilebank7smilebank7
2

Extract Materials

Extract text, tables, and equations from PDFs, PPTX, DOCX, and images into Markdown.

Community
Intermediate
mu-zi-leemu-zi-lee
13

muzilee-gemini-image-skills

Automate Gemini web chat and image generation via a local Python daemon and Tampermonkey worker.

Community
Intermediate
shiqkuangsanshiqkuangsan
17

tooyoung:nano-banana-builder

Create Next.js apps for text-to-image generation and iterative editing with Gemini APIs.

Community
Advanced