generate-imagelisted
Install: claude install-skill getedgehq/skills
# Generate Image
Creates images via OpenAI GPT Image 2. Auth runs through the Codex CLI logged in
with a ChatGPT account, so generation is covered by the user's Plus subscription.
There is no OpenAI API key and no separate per-image API billing.
## Before you start
This Skill does not talk to OpenAI directly. It shells out to the **Codex CLI**,
and that CLI has to already be installed on this machine and already signed in
to a ChatGPT account with an active Plus subscription. Check with `codex --version`
and run `codex login` if it is not signed in. There is no API key to paste, and
no separate per-image charge; the images are billed to that subscription.
Without a signed-in Codex CLI nothing here works, and the script fails at the
first call rather than producing a file.
## Quick start
```bash
# from this Skill's own directory, wherever your agent installed it
./scripts/generate-image.sh "a shiba inu wearing sunglasses, studio photo"
```
Saves to the resolved output folder (see below) as a slugified PNG, e.g.
`assets/images/a-shiba-inu-wearing-sunglasses-studio-photo.png`.
## Workflow
1. Turn the user's request into a strong English prompt. **Follow the build
order and levers in [PROMPTING.md](PROMPTING.md)** (scene → subject → details
→ invariants → use). Refine vague requests before calling; do not pass a bare
one-liner when the asset matters.
2. Run the script with the prompt. Optionally pass `--out` and `--name`.
3. Report the saved path back to the use