How do I install the Tidybot Robot Connection skill?

Run npx skillmds@latest add tomevault-io/tidybot-robot-connection in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tidybot Robot Connection safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tidybot Robot Connection?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tidybot Robot Connection free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Tidybot Robot Connection?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tidybot Robot Connection by tomevault-io

Name: Tidybot Robot Connection
Author: tomevault-io

Tidybot Robot Connection

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. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Robot Connection

Robot IP: <ROBOT_IP>
API Key: <API_KEY>
Base URL: http://<ROBOT_IP>:8080

Key Endpoints

Endpoint	Method	Purpose
`/code/execute`	POST	Run Python code on the robot
`/code/status?stdout_offset=N&stderr_offset=N`	GET	Poll execution output
`/code/recordings/{execution_id}`	GET	Execution recording metadata
`/code/recordings/{execution_id}/frames/{filename}`	GET	Retrieve recorded camera frame (JPEG)
`/code/sdk/`	GET	SDK reference (browsable)
`/code/sdk/markdown`	GET	SDK reference as markdown
`/docs/guide/html`	GET	Getting-started guide
`/cameras/{id}/frame`	GET	Live camera frame (use sparingly)

Logs

All logs are in ~/tidybot_uni/logs/:

File	Content
`agent_server.log`	Agent server runtime log (connections, errors, lifecycle)
`code_execution.log`	Stdout/stderr from all code executions
`code_executions/`	Per-execution Python files + output (timestamped)

Logs rotate daily (e.g. agent_server.log.2026-03-05). Always check these first when debugging errors — don't redirect server output to /tmp/.

Notes

web_fetch blocks private IPs. Use curl -L via shell for robot endpoints.
Prefer print() + polling /code/status over live camera polling.
Recorded frames save automatically at 0.5 Hz during execution — use those instead of live polls.

Source: TidyBot-Services/Tidybot-Universe — distributed by TomeVault.

---name: tidybot-robot-connectiondescription: 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. Use when this capability is needed.---# Robot Connection- **Robot IP:** `<ROBOT_IP>`- **API Key:** `<API_KEY>`- **Base URL:** `http://<ROBOT_IP>:8080`## Key Endpoints| Endpoint | Method | Purpose ||----------|--------|---------|| `/code/execute` | POST | Run Python code on the robot || `/code/status?stdout_offset=N&stderr_offset=N` | GET | Poll execution output || `/code/recordings/{execution_id}` | GET | Execution recording metadata || `/code/recordings/{execution_id}/frames/{filename}` | GET | Retrieve recorded camera frame (JPEG) || `/code/sdk/` | GET | SDK reference (browsable) || `/code/sdk/markdown` | GET | SDK reference as markdown || `/docs/guide/html` | GET | Getting-started guide || `/cameras/{id}/frame` | GET | Live camera frame (use sparingly) |## LogsAll logs are in `~/tidybot_uni/logs/`:| File | Content ||------|---------|| `agent_server.log` | Agent server runtime log (connections, errors, lifecycle) || `code_execution.log` | Stdout/stderr from all code executions || `code_executions/` | Per-execution Python files + output (timestamped) |Logs rotate daily (e.g. `agent_server.log.2026-03-05`). **Always check these first when debugging errors** — don't redirect server output to `/tmp/`.## Notes- `web_fetch` blocks private IPs. Use `curl -L` via shell for robot endpoints.- Prefer `print()` + polling `/code/status` over live camera polling.- Recorded frames save automatically at 0.5 Hz during execution — use those instead of live polls.---> Source: [TidyBot-Services/Tidybot-Universe](https://github.com/TidyBot-Services/Tidybot-Universe) — distributed by [TomeVault](https://tomevault.io).

Frequently asked questions