Skip to content
Skills Library
Design & UX · Tool integration

generate-image

/generate-image

Generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt.

Repository
skills ↗
Licence
Apache-2.0
Last repository change
24.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
5
Scripts
1
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 24.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What to check before installing
  • 1 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: scripts/generate-image.sh

What it does and when to use it

Generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt.

Original author description

Generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt.

How it works

  1. Before you start
  2. Quick start
  3. Workflow
  4. Output location
  5. Options
  6. Deliverable naming
  7. Requirements
Original SKILL.md headings · 75 lines, 450 words
SKILL.md preview
---
name: generate-image
description: Generate images with OpenAI GPT Image 2 via the Codex CLI, billed through the user's ChatGPT Plus subscription (no OpenAI API key, no per-image API cost). Use when the user asks to create, generate, or make an image, picture, illustration, icon, hero graphic, or concept art from a text prompt.
---

# 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 user. For changes, iterate in small
   single-variable steps and restate the invariants (see PROMPTING.md).

## Output location

When `--out` is not given, the script resolves the folder automatically:

| Condition | Target folder |
|-----------|---------------|
| `./public/` exists (web/app initiative) | `./public/images/` |
| otherwise | `./assets/images/` (created if missing) |

This establishes a consistent `assets/images/` convention across projects while
respecting web projects, where images must live under `public/` to be served.

## Options

| Flag | Effect |
|------|--------|
| `--out <dir>` | Write into this directory instead of the resolved default |
| `--out <file>.png` | Write to this exact file path |
| `--name <basename>` | Use this basename instead of slugifying the prompt |

Existing files are never overwritten: the script appends `-2`, `-3`, ... instead.

## Deliverable naming

These outputs are work assets, so they get short functional names by default.
If an image is a stakeholder **deliverable**, pass an explicit
`--name` following the file-naming rule, e.g.
`--name "20260612_Hero Banner_v1"`.

## Requirements

- `codex` CLI installed (`brew install --cask codex`)
- Logged in with a ChatGPT account: `codex login` (Plus or higher; image
  generation is not available on Free)

The script checks both and fails with a clear message if either is missing.
Files in this package (5)
  • DERIVATION.json 4 KB
  • LICENSE 11 KB
  • PROMPTING.md 3 KB
  • SKILL.md 3 KB
  • scripts/generate-image.sh 3 KB

Versions

RepositoryScoreLicence
This page · getedgehq/skills100Apache-2.0
foryourhealth111-pixel/Vibe-Skills100Apache-2.0
github/awesome-copilot100MIT
synthetic-sciences/openscience100Apache-2.0
comfy-org/comfy-skills100MIT
mikepsinn/disease-eradication-plan100CC-BY-4.0
laurigates/claude-plugins100MIT
bdambrosio/Cognitive_workbench100MIT
cluesmith/codev100Apache-2.0

Database snapshot: 13.11.2026 · package version e95318d5aab5 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 1 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95gpt-image-2
    Generate or edit a raster image with OpenAI's gpt-image-2 through the Codex CLI, billed to the ChatGPT subscription rather than an API key. Use whenever the user asks for a photo, illustration, mockup, texture, marketing visual, or an edit to an existing image file, including…
  • 100codex-image
    Generate or edit raster images (photos, illustrations, mockups, hero images, product shots, bitmap icons, transparent cutouts) with OpenAI GPT Image 2 by triggering the local Codex CLI, billed to the user's ChatGPT subscription — no API key needed. Use when the user says…
  • 100codex-image
    Generate images using OpenAI's Codex backend API with gpt-image-2 tool. Use when the user asks to generate images via Codex, ChatGPT image generation, or gpt-image-2. Triggers on "codex image", "codex generate", "gpt-image", "chatgpt generate image". Token is auto-fetched from…
  • 100gpt-image-skill
    Generate or edit images using OpenAI GPT Image API (gpt-image-2, gpt-image-1, etc). Use ONLY when the user explicitly names OpenAI or GPT as the provider: "gpt image", "openai image", "generate image with openai", "用 openai 画图", "用 GPT 生成图片". For generic image requests without a…
  • 100generating-images
    Generate or edit images using the OpenAI Image API (gpt-image-2). Use when the user asks to generate, create, draw, render, illustrate, mock up, or edit an image, icon, logo, mockup, illustration, OG image, blog hero, marketing asset, or similar visual. Also use when the user…
  • 100codex-imagegen
    Generate or edit raster images (photos, illustrations, mockups, logos, product shots, game/UI assets, textures, infographics) using Codex's built-in image_gen tool — driven headlessly through `codex exec`. Billed via the user's ChatGPT/Codex login, so it needs NO OpenAI API key.…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.