Image Generator

Name: Image Generator
Author: avivsinai

avivsinai/telclaude

1 installs
6 repo stars
Updated August 3, 2026
avivsinai/telclaude

image-generator is a Claude Code skill that generates images from text prompts via the GPT Image 1.5 API using the telclaude generate-image CLI.

About

This skill generates images from text prompts by calling the GPT Image 1.5 API through the telclaude generate-image CLI command. A developer uses it inside a telclaude Telegram agent when a user asks to create, draw, or make an image. It exposes size and quality flags and relies on the CLI to manage the API key and rate limits.

Generates images via the GPT Image 1.5 API using the telclaude CLI
Supports size (square/landscape/portrait) and quality (low/medium/high) options
CLI handles API key retrieval from keychain, rate limiting, and error handling

Image Generator by the numbers

1 all-time installs (skills.sh)
Ranked #1,200 of 1,335 Generative Media skills by installs in the Skillselion catalog
Data as of Aug 4, 2026 (Skillselion catalog sync)

At a glance

image-generator capabilities & compatibility

Requires an OpenAI API key; cost scales with GPT Image 1.5 usage.

Capabilities: image generation · text to speech · video frames
Works with: openai
Use cases: image generation
Pricing: Bring your own API key

From the docs

What image-generator says it does

Generate images using GPT Image 1.5 when users request visual content.

SKILL.md

This handles API key retrieval from keychain, rate limiting, and proper error handling.

SKILL.md

npx skills add https://github.com/avivsinai/telclaude --skill image-generator

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/avivsinai/telclaude/image-generator.svg)](https://skillselion.com/skills/avivsinai/telclaude/image-generator)

Installs	1
repo stars	★ 6
Last updated	August 3, 2026
Repository	avivsinai/telclaude ↗

What it does

Generate an image from a text prompt when a Telegram user asks to create or illustrate visual content.

Who is it for?

Adding on-demand image creation to a telclaude Telegram agent.

Skip if: Editing existing images or running without the telclaude CLI and an OpenAI key.

When should I use this skill?

A user asks to create, generate, draw, or make an image or illustration.

What you get

Outputs a generated image file path from a text prompt.

By the numbers

3 quality levels (low, medium, high)
4 size options including auto

Files

SKILL.mdMarkdownGitHub ↗

Image Generation Skill

Generate images using GPT Image 1.5 when users request visual content.

When to Use

Use this skill when users:

Ask to "create", "generate", "draw", or "make" an image
Request illustrations, artwork, diagrams, or visual content
Want to visualize concepts, ideas, or descriptions

How to Generate Images

Use the telclaude generate-image CLI command. This handles API key retrieval from keychain, rate limiting, and proper error handling.

# Basic usage - generates image and outputs file path
telclaude generate-image "YOUR_PROMPT_HERE"

# With size option (default: 1024x1024)
telclaude generate-image "YOUR_PROMPT" --size 1536x1024

# With quality option (default: medium)
telclaude generate-image "YOUR_PROMPT" --quality high

Options:

--size: "auto", "1024x1024" (square), "1536x1024" (landscape), "1024x1536" (portrait). Default: 1024x1024
--quality: "low" (fast/cheap), "medium" (balanced), "high" (best quality)

Example

To generate a landscape sunset image:

telclaude generate-image "A serene mountain landscape at sunset with a lake reflection" --size 1536x1024 --quality high

The command outputs:

Generated image saved to: /path/to/generated-image.png
Size: 1234.5 KB
Model: gpt-image-1.5

Response Format

After running the command, include the full file path in your response. The telclaude relay automatically detects paths to generated media and sends the file to the user via Telegram.

Example response:

I've generated your image and saved it to:
/media/outbox/generated/1234567890-abc123.png

[The relay will automatically send the image to you]

Important:

Always include the full path from the command output in your response
The relay detects paths under TELCLAUDE_MEDIA_OUTBOX_DIR (default .telclaude-media in native mode; /media/outbox in Docker) and sends them automatically
No additional commands are needed - just include the path

Best Practices

1. Be Descriptive: Include details about style, mood, colors, composition 2. Specify Style: Mention if you want photorealistic, illustration, cartoon, etc. 3. Avoid Prohibited Content: No copyrighted characters, real people, or inappropriate content 4. Use Quality Wisely: "low" for drafts, "high" for final images