robodojo_main — Claude Code prompt: what it does and install
The robodojo_main prompt for Claude Code helps verify RoboDojo actions against environment snapshots. It separates intermediate changes from evidence of a completed action.
MIT ★ 488 updated 2026-11-15
.claude/commands/robodojo_main.mdWhat robodojo_main does
The prompt helps interpret RoboDojo snapshots while a robot action is running. Snapshots appear after primitive steps; during a background high-level action, an observer can receive an older snapshot or a new primitive marked in_flight. Those views may show an intermediate state, so check the corresponding action after it finishes.
Direct results include state, feedback, and the ID of the final RGB snapshot. move, grasp, and release attach the final head view and available wrist images from participating arms; hold attaches one final head view. These RGB records contain no depth or calibration. Use view_env_state for extra or recorded views, and capture_scene for calibrated geometry. Images captured before closure, lifting, or release do not confirm the effect of that action.
What it helps with
- check whether a high-level action has finished
- distinguish an intermediate snapshot from a final result
- verify the effect of grasping, lifting, or releasing
- retrieve extra views or calibrated geometry
Example prompts for the agent
- Check whether the final snapshot confirms that the robot action finished.
- Compare the result of
graspwith images captured after the action completes. - Retrieve extra environment views and inspect the state with
view_env_state.
How to install robodojo_main
Manually: put the files in place
.claude/commands/robodojo_main.mdHow to use
Paste the text at the start of a chat or into project instructions
Questions about robodojo_main
How do I install robodojo_main in Claude Code?
Place the prompt file at .claude/commands/robodojo_main.md.
What does robodojo_main do?
It helps interpret RoboDojo snapshots and tell intermediate changes apart from the result of a completed action.
What evidence confirms a RoboDojo action's result?
Check a snapshot corresponding to the completed action. Evidence from before closure, lifting, or release does not confirm that action's effect.
Source text
robodojo_main.md · MIT
RoboDojo publishes snapshots after completed primitive steps. During a background high-level action, an observer may see an earlier snapshot or a newly completed primitive marked in_flight. These can show intermediate changes; verify the corresponding completed action before relying on its final effect. Direct results contain state, feedback and the final RGB snapshot_id. move/grasp/release attach the final head image and participating arms' wrist images when available; hold attaches one final head image. These RGB records have no depth or calibration. actor_act attaches its latest snapshot's views. Use view_env_state for additional or recorded views and capture_scene when calibrated geometry is needed. Evidence from before closure, lift or release does not verify that action's effect.
© Open-RUA · MIT · Open-RUA/uni-robot-agent