agentleFS
D-RoboticsD-Robotics/rdk-device-skills/skills/rdk-llm-deployment/SKILL.md

rdk-llm-deployment

Skill4 starsChanged 2 months agoLicence not identifiedView on GitHub

Run on-device LLM / VLM chat and the voice stack (ASR→LLM→TTS, plus the xiaozhi 小智 assistant) on D-Robotics RDK boards. Covers hobot_llamacpp GGUF LLM/VLM on X5/S100, the S600 oellm_runtime / D-Robotics_LLM_S600 SDK path, the legacy hobot_llm on X3, and sensevoice_ros2 + hobot_tts. Use whenever the user wants a chatbot / 看图问答 / 语音助手 on the board, asks which LLM/VLM a board can run, or hits a board↔stack mismatch (e.g. trying hobot_llamacpp on S600). 触发词:端侧大模型、在板上跑 LLM、llama.cpp BPU、GGUF、hobot_llamacpp、InternVL、SmolVLM、Qwen3、VLM 看图问答、语音助手、小智、xiaozhi、语音识别、ASR、sensevoice、语音合成、TTS、hobot_tts、hobot_llm、oellm、S600 跑大模型。Routing — robot ACTION policies (VLA / Pi0 / LeRobot) → rdk-embodied-lerobot; ready-made vision detection/classification/segmentation + CLIP perception models → rdk-model-zoo; "can THIS board even run an LLM" sizing/expectation only → rdk-ecosystem; ROS2 env setup → rdk-tros-setup.

  • Deletes or force-pushes
  • Installs packages

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.