horizonrobotics/holoagent/robot-service
Claude Code and agent skill by horizonrobotics/holoagent
- community
Checking that the SKILL.md file is still in the repository.
Canonical skill for OpenClaw robot service interfaces, covering robot_bridge on each robot and multi_robot_ctl on the control center. **Use this skill when:** - The user wants to trigger robot actions through HTTP services - The user asks about robot_bridge or multi_robot_ctl - The task involves remote navigation, arm control, or semantic navigation - The task requires multi-robot fan-out control - The user needs the official external control surface instead of internal FIFO details
Install
npx vskill@latest install horizonrobotics/holoagent/robot-serviceSKILL.md
Robot Service
This skill documents the canonical external control surface for OpenClaw robots.
Architecture
Layer 1: robot_bridge on each robot
Default robot-side HTTP server:
- host:
0.0.0.0 - port:
8000
Supported mappings:
- Navigation signal
POST /api/navigation/{name}- ROS topic:
chat_signal_pub
- Relative navigation
POST /api/relative_nav- ROS topic:
/relative_nav - JSON body:
{"cmd": "forward,left,degrees"}
- Semantic navigation
POST /api/semantic_nav- ROS topic:
/chat_loc_pub - JSON body:
{"cmd": "floor,room,object"}
- Arm skill
POST /api/arm/{skill}- ROS topic:
arm_signal_pub
- Stop navigation
POST /api/navigation/stop- ROS topic:
chat_signal_pub
Health check:
GET /health
Layer 2: multi_robot_ctl on the master machine
Default control-center port:
8080
Supported fan-out endpoints:
POST /trigger/one_point_1POST /trigger/one_point_2POST /trigger/one_point_3POST /trigger/one_point_4POST /trigger/multi_point_1POST /trigger/multi_point_2POST /trigger/stop
Optional query parameter:
robot_id=<id>robot_id=all
Workflow
- Identify whether the request should go to a single robot bridge or the multi-robot control layer.
- Confirm the target endpoint, robot scope, and payload format before sending the request.
- Prefer documented HTTP endpoints and only fall back to ROS topics when appropriate for the integration.
- Execute one service request at a time and inspect the returned status.
- Report the endpoint, payload, and result clearly for downstream workflow tracking.
Safety Rules
- If the target robot is ambiguous, ask which robot should execute.
- If the command is unsafe or unclear, do not trigger the service.
- If unsure, stop and clarify.
Examples
See:
README.mdassets/service_examples.sh
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingagentic_robot/agentOS/holoagent_skills/skills/robot-service/SKILL.md
Popularity
- Repository stars
- 324
- Repository forks
- 23
- 7-day trend score
- 29
Stars and forks are for the whole GitHub repository, not this skill alone. 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/horizonrobotics/holoagent/robot-service)