ericblue/my-claude/generate-images

Claude Code and agent skill by ericblue/my-claude

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Generate one or more images from a text prompt using OpenAI's Images API (model gpt-image-1.5). Use when the user asks to “generate images”, “create an image”, “make a thumbnail”, or similar; especially when they provide a prompt plus options like count/size/quality/output directory.

Install

npx vskill@latest install ericblue/my-claude/generate-images

SKILL.md

Generate Images (gpt-image-1.5)

Generate images via the OpenAI Images API using a deterministic helper script.

Prerequisites

  • OPENAI_API_KEY environment variable must be set
  • jq must be available (used to parse API JSON)

Usage

  • /generate-images a sunset over the ocean — generate 1 image
  • /generate-images 3 cats wearing hats — generate 3 images (shorthand count)
  • /generate-images --count 5 --size 1536x1024 a mountain landscape — full options

Arguments

The argument string is available as $ARGUMENTS.

Flags (all optional)
  • --count N (default 1) — number of images (1–10)
  • --size WxH (default 1024x1024) — one of: 1024x1024, 1536x1024, 1024x1536
  • --quality Q (default high) — low, medium, high
  • --output DIR (default ./) — directory to save images
  • --prefix NAME (default image) — filenames like {prefix}-1.png, {prefix}-2.png, ...
  • --format FMT (default png) — png or jpg

Flags can appear in any order and may be mixed with prompt tokens.

Shorthand count

If the prompt starts with a bare number + space (e.g. 3 cats wearing hats), treat the number as the count only if no --count flag is present.

Everything else is the prompt

After extracting flags and optional leading count, join the remaining text as the prompt.

Procedure

Prefer running the bundled script (it handles parsing, file naming, progress, and errors):

bash
bash /Users/ericblue/clawd/skills/public/generate-images/scripts/generate-images.sh

The script reads $ARGUMENTS (or you can pass a single argument string as $1).

Notes

  • Each API call generates one image; multiple images are generated sequentially.
  • Cost varies by quality and size (rough estimates per 1024×1024 image): low ~$0.04, medium ~$0.07, high ~$0.19. Larger sizes are ~1.5×.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ericblue/my-claude/generate-images/badge)](https://verified-skill.com/skills/ericblue/my-claude/generate-images)

Something wrong with this skill or its page? Tell us.