Loading…
Toolbay now connects to Claude. Set it up once, then list what you have built by asking.
Get my keyGet my keyAI TOOLS · BY TYPE AND USE-CASE
Agents, skills, prompts, workflows, MCP servers, and datasets — each crossed with the work you actually do. Every listing is a file you download and run in your own stack, licensed per copy. Where nothing is listed yet, we say so and you can post a request instead.
An AI agent is a program that uses a language model to work toward a goal on its own: it plans, calls tools (browsers, APIs, files), checks its results, and keeps going until the job is done — instead of answering one prompt and stopping.
An AI skill is a packaged capability you install into an AI assistant — a folder of instructions, scripts, and references that teaches a tool like Claude Code or Cursor to do one job well (deploys, audits, document work) with a single command.
An AI prompt is a written, tested instruction set for a language model — usually a system prompt plus templates and examples — that reliably produces a specific kind of output instead of generic first-try text.
An AI workflow is a multi-step automation — usually an importable graph for a tool like n8n, Make, or ComfyUI — that chains triggers, AI calls, and actions so a whole process runs end-to-end without you touching each step.
An MCP server is a connector built on the Model Context Protocol — the open standard AI assistants use to reach outside tools. Running one gives your assistant real abilities (query a database, read a CRM, control a browser) through a standard interface instead of one-off integrations.
An AI dataset is structured data prepared for machine use — training examples, evaluation sets, embeddings-ready corpora, or clean reference tables — so you can fine-tune, benchmark, or ground a model without weeks of collection and cleanup.
Get launch updates
No spam. Unsubscribe anytime.
Make a free account to keep what you download, post requests, and hear when new tools list.
Free to join · no card · no subscription