Codex Imagegen

Generate images such as featured images, illustrations, diagrams, thumbnails, and blog visuals with the Codex CLI built-in $imagegen skill, save them into the current project, and safely clean this run's generated-images cache. Use when the user asks to generate, create, or make an image, picture, illustration, featured image, thumbnail, visual asset, image variants, AI artwork, or explicitly asks to use Codex image generation. Do not use for screenshots, charts rendered from data, ASCII diagrams, or editing existing images.

23 stars 4 forksImages, Video & Audio Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add nathanonn/agent-skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add nathanonn/agent-skills --skill codex-imagegen
Manual install
git clone --depth 1 https://github.com/nathanonn/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/plugins/codex-imagegen/skills/codex-imagegen ~/.claude/skills/codex-imagegen

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Codex Imagegen

Generate images with Codex's built-in `$imagegen` skill, land them in the
project, and keep `$CODEX_HOME/generated_images/` from silently growing. The
bundled script uses the Codex CLI directly and applies machine, workspace,
project, environment, and per-run configuration without shipping a fixed model.

## Prerequisites

The **Codex CLI is required**. The Claude Code codex plugin alone is not a
runtime for this skill.

```bash
npm i -g @openai/codex
codex login
```

Authentication is OpenAI/ChatGPT-account backed. If the CLI is absent, the
script exits with code 3 and prints these steps.

## Project folder and destination

The project marker and configuration folder is:

```text
<project>/.codex-imagegen/
├── config.toml
├── output/
└── refs/
```

`config.toml` is optional, `output/` is the default image destination, and
`refs/` is reserved for future style references. A bare `.codex-imagegen/`
directory is still a project marker.

Destination precedence is:

1. `--dest DIR`.
2. Merged `[imagegen] dest`, resolved relative to the project folder that
   holds the `.codex-imagegen/` directory.
3. `.codex-imagegen/output/` below the deepest marker found by walking upward.
4. `$PWD/.codex-imagegen/output/`.

The walk is anchored on the normalized `--dest` directory when supplied and on
`$PWD` otherwise. It visits ancestors up to `$HOME`, or up to the filesystem
root when the anchor lives outside `$HOME`. The script creates the destination
Read the full skill on GitHub

Details

Skill name
codex-imagegen
Path
plugins/codex-imagegen/skills/codex-imagegen/SKILL.md
License
MIT
Repo updated
11 November 2026

FAQ

What does the Codex Imagegen skill do?

Generate images such as featured images, illustrations, diagrams, thumbnails, and blog visuals with the Codex CLI built-in $imagegen skill, save them into the current project, and safely clean this run's generated-images cache. Use when the user asks to generate, create, or make an image, picture, illustration, featured image, thumbnail, visual asset, image variants, AI artwork, or explicitly asks to use Codex image generation. Do not use for screenshots, charts rendered from data, ASCII diagrams, or editing existing images.

How do I install the Codex Imagegen skill?

Claude Code plugin: /plugin marketplace add nathanonn/agent-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Codex Imagegen popular?

It lives in nathanonn/agent-skills, which has 23 GitHub stars and 4 forks.

Related skills

Ask First

23

nathanonn/agent-skills

Ask clarifying questions before executing tasks. Use this skill whenever the user says "ask me questions first", "clarify before doing", "ask before you start", invokes /ask-first, or wants Claude to gather requirements through Q&A before taking action. Also trigger when the user provides a task prefixed with "ask:" or says things like "I need help figuring out how to..." or "help me think through...". This skill ensures nothing is assumed — Claude asks until 95% confident, then executes.

Productivity & Notes

CLI Spec to Goal

23

nathanonn/agent-skills

Convert a Node.js CLI tool specification (even a vague one) into a Codex /goal-ready bundle — GOAL.md, VERIFY.md, PROGRESS.md inside goals/<slug>/ — with AI-agent-friendly patterns (--json, stdout/stderr separation, exit codes, structured errors, TTY detection, --dry-run) baked into every goal. Asks clarifying questions in focused batches (each with options + recommendation + reasoning), reaches 95% confidence, optionally scaffolds a missing CLI project (bin/, src/, package.json, AGENTS.md, CLAUDE.md behavioral snippet), and emits a tailored /goal command. Handles both new CLIs and adding comm

Software Development

Design System to Skill

23

nathanonn/agent-skills

Convert an extract-design-system output bundle (a .design_systems/<domain>-YYYYMMDD/ folder with DESIGN.md, AGENTS.md, COMPONENTS.md and DTCG tokens) into a self-contained, auto-triggering per-brand Claude Code agent skill that later agents use to build pages native to that brand. Use whenever the user has run extract-design-system or points at a .design_systems/ bundle and wants to reuse it — "turn this design system into a skill", "make a skill from the extracted design system", "convert .design_systems/<x> into an agent skill", "package this bundle as a skill", "generate a <brand> design-sy

Frontend & Design

Podcast From Research

9

Easternguy/podcast-from-research

Research-to-podcast pipeline for learning new topics: 20-angle full-coverage research (with blind-spot discovery) → steered NotebookLM audio overview → MP3 delivered to you, with everything ingested into a local GBrain knowledge base for permanent recall. When the user says "create a podcast on X", this handles it end-to-end. Installs its own dependencies (notebooklm-py, GBrain) if missing.

Images, Video & Audio

Video to Claude

10

rohunvora/video-to-claude

Analyze videos with Gemini and get build instructions for Claude. Supports YouTube URLs, GIFs, screen recordings, and local video files. Use when user shares a video/GIF and wants to understand how to build it, clone a UI, reverse engineer a product, or extract tutorial steps. Triggers on "watch this video", "clone this", "reverse engineer", "how do I build this", "analyze this demo".

Images, Video & Audio

Human Voice

10

ttilabs11-byte/human-voice-skill

Write anything (blog posts, articles, emails, chat replies, LinkedIn posts, summaries, release notes, feedback, apologies, bios, explainers) so it reads like one sharp, warm person and never like AI slop. Point first, specifics over adjectives, wit only where it is earned, and an ending that does work. Use whenever the user asks to write, draft, rewrite, punch up, humanise or "make this not sound like AI", or when Claude itself is writing prose a person will read.

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.