Browse skills

Generate custom OpenAI skills from natural language descriptions, streamlining integration and automating complex workflows.

Generates creative text formats like poems, code, scripts, musical pieces, email, letters, etc., based on a single prompt – useful for diverse content creation needs.

Workiq Copilot assists legal professionals by summarizing documents and extracting key information for faster research & analysis.

This skill provides a streamlined CLI quickstart for Copilot, accelerating your workflow and enabling faster command execution.

Boost Prompt enhances prompts with relevant context & instructions, improving AI response quality and accuracy for better results.

Generates images from textual descriptions, offering a creative way to visualize ideas and concepts instantly.

This skill generates human-like text responses from audio input, enabling voice-based interactions and content creation.

Verifies code changes suggested by OpenAI's models against existing tests and project requirements.

Access a vast library of pre-built datasets for machine learning projects, accelerating development and experimentation.

Ralph GPU accelerates complex computations by leveraging powerful GPUs, boosting performance for demanding tasks and data processing.

Official vercel-labs skill for software development workflows.

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, co

Automatically detects and flags potential vulnerabilities in AI model code using Trail of Bits' expertise and OpenAI integration.

Build custom ChatGPT-powered apps quickly and easily – perfect for automating tasks & creating unique user experiences without coding expertise.

Official openai skill for OpenAI — helps with software development workflows.

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridg

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for vi

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after exp

Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-leve

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger on

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI\u2019s video API using the bundled CLI (`scripts/sora.py`), including requests like \u201cgenerate AI

Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.