Bundle a Tidybot skill and its dependencies into a single executable Python script for robot submission. Use when (1) submitting a multi-dependency skill to the robot, (2) preparing code for the /code/execute API, (3) resolving deps.txt dependency chains into one file.
Start, stop, restart, and health-check the MuJoCo sim server and agent server. Use when (1) launching the sim for skill development or testing, (2) restarting after a crash, (3) checking if the sim is running, (4) shutting down cleanly.
Audit all Tidybot repos for uncommitted/unpushed changes, diff workspace skills and personality files against the Tidybot-Universe setup repo, and summarize. Use when (1) the user says "push tidybot" or "commit tidybot", (2) reviewing what's changed before pushing, (3) syncing workspace files to the public repo.
Robot connection credentials and API endpoints — IP address, API key, base URL, and all key REST endpoints. Use when (1) making API calls to the robot, (2) executing code on the robot via /code/execute, (3) debugging connection issues or timeouts, (4) needing the robot IP or API key mid-session, (5) polling execution status or retrieving recorded frames, or (6) fetching SDK docs or the getting-started guide.
Execute a physical task on the robot (pick up, place, move, look at, etc.). Use when the user asks you to do something with/on the robot — any manipulation, navigation, or perception task. Triggers on requests like "pick up the banana," "put that on the plate," "go to the table," "what do you see," etc.
External services catalog — model endpoints, vision APIs, grasping backends, and Python client SDKs available to robot skills. Use when (1) a skill needs an external model or API, (2) checking what backend services are available, (3) debugging service timeouts or connection failures, (4) requesting a new service that doesn't exist yet, (5) downloading or using a service's Python client SDK.
Build, test, and iterate robot skills for Tidybot. Use when (1) asked to make a new robot skill, (2) prototyping or iterating on skill code, (3) running or recording skill trials, (4) tracking success/failure stats, (5) deciding whether to chain existing skills or build new, (6) debugging skill execution, (7) needing a backend API, model, or service that doesn't exist yet.
Publish a tested robot skill to the tidybot-skills org. Use when the user approves publishing a skill from the dev/ folder.