imagegenlisted

# Image Generation Skill (gpt-image-2 via Codex CLI) Generates or edits images for the current project (for example website assets, game assets, UI mockups, product mockups, wireframes, logo design, photorealistic images, or infographics) using `gpt-image-2`. ## Top-level mode This skill has exactly one execution mode: the bundled bash wrapper `scripts/gen.sh`, which shells out to the local `codex` CLI. - The Codex CLI must be installed and logged in (`codex login`) with a ChatGPT plan that includes Image 2. - The skill never reads `OPENAI_API_KEY`. Authentication and billing piggyback on the user's existing ChatGPT subscription. - All image generation and editing routes through `gen.sh`. Do not hand-roll one-off SDK runners or call `codex exec` directly from chat. - Never modify `scripts/gen.sh`, `scripts/extract_image.py`, or `scripts/remove_chroma_key.py`. If something is missing, ask the user before doing anything else. - For transparent-background requests, use `gen.sh --transparent`. Do not strip backgrounds with ad-hoc post-processing scripts when the chroma-key pipeline would do it more reliably. If `codex` is not installed or not logged in, stop and tell the user. Do not silently fall back to a different image route, an HTML mockup, or a screenshot workflow. ## When to use - Generate a new image (concept art, product shot, cover, website hero). - Generate a new image using one or more reference images for style, composition, mood, or subject guidance. - Edit a