A complete Python wrapper around OpenAI's image generation and editing endpoints, including the newer Responses API flows. It handles text-to-image, masked edits, multi-image batches, streaming with partial previews, and mixed text plus image inputs. The pre-flight validation catches unsupported model combinations before you waste tokens, and everything is configurable through environment variables or CLI flags. If you're doing anything beyond a single image generation, especially if you need streaming or want to chain edits with conversation context, this gives you the full surface area in one script. The dry-run flag and response saving are nice touches for debugging payloads before you send them.
npx -y skills add gargantuax/openskills --skill gpt-image-2 --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
prisma/skills
firebase/agent-skills
Dexploarer/hyper-forge
itsmostafa/aws-agent-skills
prisma/skills