gpt-image-2
Supports image generation, masked edits, multi-image batches, streaming, partial images, and mixed text-and-image Responses flows. Works with OpenAI-compatible gateways and reads configuration from environment variables and .env files.
Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Supports image generation, masked edits, multi-image batches, streaming, partial images, and mixed text-and-image Responses flows. Works with OpenAI-compatible gateways and reads configuration from environment variables and .env files.
Uses the unified Pilio developer API for text-to-image generation and prompt-based editing. Supports restyling, product-photo transformations, and compositions based on one or more local reference images.
Covers GPT Image 2 generation and editing with emphasis on embedded text, logos, multilingual typography, and instruction precision. Includes size choices, preservation language for edits, and alternative model selection.
Covers image creation and editing with emphasis on text, logos, multilingual typography, and instruction precision. Includes fixed output sizes, preservation language for edits, and guidance on choosing alternative models.
Helps create, rewrite, classify, and improve image-generation prompts. Uses visual styles, industrial prompt templates, category and scene tags, pitfalls, and examples from the awesome-gpt-image-2 library.
Uses the GPT Image 2 edit endpoint through RunComfy. Covers multilingual text editing, layout and typography precision, preservation language, up to ten reference images, and selection of alternative editing models.
Guides the GPT Image 2 edit endpoint on RunComfy. Covers multilingual text changes, layout and typography precision, preservation instructions, and composition using up to ten reference images.
Provides RunComfy prompting and schema guidance for GPT Image 2 editing. Covers multilingual text changes, up to ten reference images, preservation of existing content, and precise layout and typography.
Enables autonomous deep research within Codex using an MCP integration.
Use only when the user asks for an Awwwards-style, GSAP-heavy, cinematic landing page with explicit motion choreography and experimental layout variance. Do not use for normal frontend tasks, dashboards, accessibility-first sites, image-only work, or concise fixes.
Guides conversion of JVM applications to native binaries with GraalVM Native Image. Covers Maven and Gradle build tools, reflection and resource issues, startup and memory optimization, and support for Spring Boot, Quarkus, and Micronaut.
Reviews a specified set of tests across multiple languages. Reports each fully qualified test name with an A–F grade, score band, and brief note, focusing on curated tests rather than whole-suite audits.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name