Loading
Clone a prompt that shipped someone else's project. Your keys, any model, ranked by real usage.
Drop in Anthropic, OpenAI, Google, xAI, or DeepSeek keys. Encrypted at rest. Never touches your browser.
Every listing shows real run counts, the dev who shipped it, and the project it came from. Usage-weighted ranking, no upvote games.
Clone a repository pack in one click. Stream from any provider. Chain prompts into workflows when one isn't enough.
These are new — no run data yet. Be the first to take one for a spin.
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build new Arcade error adapters from scratch using public Arcade TDK patterns. Use when adding provider integrations, mapping SDK exceptions, or extending HTTP/GraphQL/auth adapter behavior.
The distinguishing concern for servers is lifecycle: an agent needs to start the server in the background, verify it's up, interact with it, then cleanly shut it down. A foreground npm start that blocks the shell is useless to an agent.
/stuck — diagnose frozen/slow Claude Code sessions
<descriptionContain information about the user — one detail per file. Over many sessions these accumulate into a picture of who the user is and how to collaborate with them. Each memory captures one thing: their role, a goal, a responsibility, an area of knowledge, or a preference. For example, you should collaborate with a senior software engineer differently than a student wh
7. Agent Memory Instructions: If the user mentions "memory", "remember", "learn", "persist", or similar concepts, OR if the agent would benefit from building up knowledge across conversations (e.g., code reviewers learning patterns, architects learning codebase structure, etc.), include domain-specific memory update instructions in the systemPrompt.
Staff engineers, solo devs, and indie-hacker founders authoring prompts they use in their own work. No AI-generated library filler.
The library layer costs nothing — browse everything, publish, and run unlimited on your own key. Subscriptions live on the Flows workspace, one door over.
Discover & store every prompt, flow, pack, and research source. Unlimited BYOK runs, full analytics, developer API, creator revenue share. No card, ever.
Run guided flows step-by-step, generate custom ones, and publish your own to earn from every run. Free on your Oort BYOK key. See plans →
The whole library is free and open — bring your own key and run any prompt on any model. No subscription on Oort.