Mastermind
A skill that creates tasks with context
Search and filter the whole catalogue. Results update as you type.
309 prompts
A skill that creates tasks with context
Useful for taking a single input image and transforming it to 9 different focal length shots that you can then upscale to use for start + end frame video generations. Yo…
OpenAI's experimental skill Codex AI Coding Assistant. Source: https://github.com/openai/skills
A high-fidelity image prompt designed to create a dramatic, low-angle urban portrait. This scene captures a subject in dark streetwear (hoodie and cap) sitting in a nigh…
Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.
Agente que simula Sam Altman — CEO da OpenAI, ex-presidente da Y Combinator, arquiteto da era AGI.
Build a low-latency, Iron Man-inspired tactical voice assistant (F.R.I.D.A.Y.) using Pipecat, Gemini, and OpenAI.
Get reliable JSON, enums, and typed objects from LLMs using response_format, tool_use, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA…
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. De…
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs…
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (…
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or…
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT…
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, t…
Daily digest of AI releases from Anthropic, Meta, Vercel Labs, OpenAI and Google GitHub repos, the Claude Cowork changelog, the claude.dev blog and Hacker News, deduplic…
4.1 voidBeast_GPT41Enhanced 1.0 : a advanced autonomous developer agent, designed for elite full-stack development with enhanced multi-mode capabilities. This latest evo…
Beast Mode 2.0: A powerful autonomous agent tuned specifically for GPT-5 that can solve complex problems by using tools, conducting research, and iterating until the pro…
Highlight augments the legibility of a written composition. Nonetheless, ChatGPT defaults to exhibit Markdown syntax, obliging one to manually select the highlighted seg…
Kindly generate a system message promptly, to allow ChatGPT to sustain playing a certain role in the ongoing session. Contributed by @jamie-cao.
ChatGPT comes with trpg settings. The effect of Chinese prompt words is better, and this word needs further adjustment. Contributed by @gandli.
When making voice recordings, it is often customary to say verbal and intonational words, which can then be converted into written language using ChatGPT to optimise the…
A detailed prompt for generating a realistic studio portrait of a woman in red fashion attire using Nano Banana Pro (GPT Image 2), focusing on lighting, pose, and textur…
A comparison of ChatGPT Image 2, Grok Imagine, and Gemini Nano Banana 2 using a detailed swimsuit portrait prompt.