Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Install with the open skills CLI (global, non-interactive — available in every Claude Code session):
npx skills add LeoYeAI/openclaw-master-skills --skill "openai-image-gen" -g -a claude-code -yOr manually — clone and copy the skill directory (SKILL.md + companion files):
git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills /tmp/openclaw-master-skills && cp -r /tmp/openclaw-master-skills/skills/openai-image-gen ~/.claude/skills/openai-image-gen-leoyeaiThis skill is a directory: SKILL.md is the entry point; the files below ship with it.
---
name: openai-image-gen
description: Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
---
# OpenAI Image Gen
Generate a handful of “random but structured” prompts and render them via OpenAI Images API.
## Setup
- Needs env: `OPENAI_API_KEY`
## Run
From any directory (outputs to `~/Projects/tmp/...` when present; else `./tmp/...`):
```bash
python3 ~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py
open ~/Projects/tmp/openai-image-gen-*/index.html
```
Useful flags:
```bash
python3 ~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py --count 16 --model gpt-image-1.5
python3 ~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
python3 ~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
```
## Output
- `*.png` images
- `prompts.json` (prompt ↔ file mapping)
- `index.html` (thumbnail gallery)
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues only.
Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. hermes-agent@agentmail.to).