Skip to main content
prompt GP ChatGPT

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

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/robodojo_main.md
Open on GitHub

What 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 grasp with 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.md

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

Similar prompts

Prompts catalog →
rebase-latest-main dyoshikawa rebase-latest-main — a skill that walks the agent through fetching origin/main, rebasing the current branch and resolving conflicts. Handy when your branch has drifted behind main. CX Codex +1 ★ 1,636repo stars pull-main dyoshikawa pull-main is a Claude Code skill that switches to main and fetches its latest changes. It runs when asked to update or sync the branch with the remote. CX Codex +1 ★ 1,636repo stars vstack-main Hao AI Lab vstack-main — a subagent for Claude Code coordinates Verification Stack stages and checks their evidence independently. It accepts a stage only after reviewing its artifacts and results. CX Codex ★ 89repo stars cache-miss.sequence tt-a1i cache-miss.sequence drives the Archify skill to build a sequence diagram for a dashboard request that misses cache in Redis and falls through to PostgreSQL. CX Codex GP ChatGPT ★ 98,599repo stars web-runtime.architecture tt-a1i web-runtime.architecture — a prompt for generating a production web architecture JSON diagram using Archify and saving it directly to benchmark-candidate.json. CX Codex GP ChatGPT ★ 98,599repo stars product-analytics.dataflow tt-a1i This prompt guides Archify through a product analytics data-flow diagram, from web and mobile events to dashboards and a model, with a distinct path for consent-gated identity data. CX Codex GP ChatGPT ★ 98,599repo stars agent-tool-call.workflow tt-a1i agent-tool-call.workflow — a prompt for building a workflow diagram where an AI agent calls tools with human approval gates. CX Codex GP ChatGPT ★ 98,599repo stars agent-run.lifecycle tt-a1i agent-run.lifecycle instructs an agent to build a structured lifecycle diagram for an agent run using the Archify workflow. CX Codex GP ChatGPT ★ 98,599repo stars

From the same set41

The whole set →
resource_global-serial The resource_global-serial Claude Code prompt sequences tool calls that share one exclusive resource. It batches calls whose outcomes are already determined and separates steps that need feedback. GP ChatGPT ★ 488repo stars resource_per-resource The resource_per-resource prompt for Claude Code and ChatGPT assigns tool calls to declared resource domains. It orders physical-world calls while allowing independent snapshot perception to overlap. GP ChatGPT ★ 488repo stars return_immediate The return_immediate Claude Code prompt sets how an agent handles tool calls: each result arrives before planning continues. It groups independent calls and pauses when the next decision needs fresh feedback. GP ChatGPT ★ 488repo stars storage_access storage_access is a Claude Code prompt that limits an agent’s access to stored resources. It defines allowed paths for robot references, observations, and session work. GP ChatGPT ★ 488repo stars tool_calling The tool_calling prompt for Claude Code and ChatGPT sets rules for using structured tools. It guides the agent to select a declared tool by its description and parameter schema. GP ChatGPT ★ 488repo stars batch The batch prompt for Claude Code groups independent reads and perception queries in one model response. Physical actions stay ordered, with a pause where their result needs checking. GP ChatGPT ★ 488repo stars hybrid The hybrid Claude Code prompt coordinates a humanoid as one actor. It combines upper-body targets with walking velocity while native control handles the legs and waist. GP ChatGPT ★ 488repo stars hybrid The hybrid prompt for Claude Code reports RoboDojo task progress with evidence-backed subgoals. A reviewer checks action-model proposals before execution. GP ChatGPT ★ 488repo stars

Project sponsors

Companies that keep this analytics open