All use cases

AI Research Skills, hosted. Nothing to install.

Machine-learning research writing done properly: related work with verified references and publication-quality figures. On AgentSky it runs in a long-lived session around the agent you choose: say what you need and the paper section and figure comes back in the conversation.

AI Research Skills has to be cloned, installed and configured on a machine before it does any work, and its results live wherever that machine is.

BuildClaude Code + Claude Sonnet 5

Choose something else when

Run it locally when the work needs your own GPUs for experiments.

AI Research Skills

Review option pricing before running.

Runs started with multiple options stay blind until you vote.

How it works

  1. Step 1

    It runs the real project

    The session clones AI Research Skills at a pinned commit and runs its own workflow and scripts, not an imitation of its output.

  2. Step 2

    Your agent is its model

    The agent you choose drives AI Research Skills directly, so there is no provider key to set up.

  3. Step 3

    It stays set up

    The session is long-lived: the install, your files and earlier results stay between visits, so the next request starts where the last one ended.

What AgentSky runs

  • AI Research Skills installed in a hosted session
  • The agent you choose as its model
  • A session that keeps your work between visits

Powered by AI Research Skills

AI Research Skills is an open-source project (Orchestra-Research/AI-Research-SKILLs, MIT). AgentSky hosts it at a pinned commit; its results come from the project itself.

A description of the hosted integration, not a claim about the quality of its results.

AI Research Skills on GitHub