Skill rating

Report product feedback about OpenResearch itself with `orx feedback`. Use when the user expresses frustration with an OpenResearch feature or bug, says a feature would be nice to have, or you hit a m

Launch and monitor experiment runs and route guidance for hf, modal, k8s/Kubernetes, ssh, slurm, ray, OpenResearch, Tinker, and local backends. Covers the fixed run contract, sizing, cancellation, and

Plan and drive the experiment tree: first-launch setup, fixed run contract, frozen nodes, stacked-bush tree shape, branch/launch/wait/promote, repair limits, notes, and turn summaries. Use before crea

Draft an academic paper or preprint as LaTeX. Create a .tex file in the project working tree, where it renders for the user and compiles to PDF. Use for a paper, preprint, manuscript, arXiv or submiss

Create standalone OpenResearch compute instances with `orx instance create`. Use when the user wants a persistent machine for manual or ad-hoc work rather than an experiment run.

Initialize a project with `orx up` and add experiment nodes with `orx create-experiment`. Use when starting a project or experiment, when the tree is empty, or when choosing a baseline, parent, or run

Locate and read persisted experiment output with `orx logs`. Invoke when inspecting run progress, debugging a run failure, or retrieving recorded configuration and measurements; use `orx-results` to i

Create independent project chats with `orx agent spawn` using the user's New Chat settings. Covers standalone opening messages, project selection, worktrees, and compute authorization. Use before crea

Read, edit, commit, and diff experiment code; coordinate shared worktrees and preserve frozen branch history. Use before branch work, when starting work alongside other sessions, comparing nodes, prep

Save reusable skills and LaTeX templates with `orx skills add` and `orx templates add`. Use when the user asks to create, import, or add a skill or template to OpenResearch for use across projects.

Interpret and summarize measured experiment results. Invoke before reporting measured results, including summarizing a completed run, comparing runs, evaluating an outcome, or recommending a next expe

Create or update interactive HTML charts for chat and static publication figures. Invoke before writing plotting code or when an existing figure needs correction; use `orx-results` for experiment inte

Explain and compare scientific or technical concepts using original research evidence. Use before answering conceptual or architectural questions, research claims, literature reviews, or related-work

Save and organize durable research outputs in the artifacts directory. Invoke when creating or reorganizing a report, exported dataset, or other deliverable; use `orx-results` for analysis and `orx-fi

Use the `orx` CLI to run local OpenResearch projects from a terminal — create experiment branches, launch and supervise compute, inspect logs and evidence, and manage the experiment tree. Read this be