tidybot-services/tidybot-universe/tidybot-run-robot-task
Claude Code and agent skill by tidybot-services/tidybot-universe
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install tidybot-services/tidybot-universe/tidybot-run-robot-taskSKILL.md
Run Robot Task
When the user asks you to do something on the robot, follow this order strictly. Do not skip to writing raw SDK code.
Step 1: Check Existing Skills
- Check
dev/folder for local in-progress skills that match the task - Fetch the skill catalog:
GET http://<ROBOT_IP>:8080/skills/catalog(or check your memory for known skills) - If a matching skill exists, use it — do not reinvent
Step 2: Chain If Possible
If no single skill matches but multiple existing skills can be combined:
- Break the task into sub-steps mapped to existing skills
- Execute them in sequence, passing context between steps
- Chaining tested skills beats untested new code
Step 3: Build New Only as Last Resort
If no existing skill covers the task:
- Read the SDK guide first:
GET http://<ROBOT_IP>:8080/docs/guide/html - Check the
active-servicesskill for available backends - Follow the
tidybot-skill-devskill to build, test, and save todev/(usetb-prefix for robot skills)
Execution Checklist
Before running any code on the robot:
- [ ] Acquire a lease (
POST /lease/acquire) - [ ] Read the SDK guide if writing new code (every session, no exceptions)
- [ ] Use
print()for status — poll/code/statusfor output - [ ] Check recorded frames after execution to verify results
- [ ] Release lease or let it expire when done
Debugging Failures
When execution fails or hangs:
- Check `/code/status` — includes stderr with tracebacks
- Check `~/tidybot_uni/logs/` — persistent logs for everything:
agent_server.log— server runtime (connections, bridge errors, lifecycle)code_execution.log— stdout/stderr from all executionscode_executions/— per-execution saved scripts + output
- Do NOT redirect server output to
/tmp/— the built-in logs already capture everything
Key References
- Robot connection: see
robot-connectionskill - Hardware specs: see
robot-hardwareskill - SDK methods: see
robot-sdk-refskill - Building new skills: see
tidybot-skill-devskill - Available services: see
active-servicesskill
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskill-agent-setup/openclaw/workspace/skills/tidybot-run-robot-task/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/tidybot-services/tidybot-universe/tidybot-run-robot-task)