rdk-device
rdk-device is an Embedded, IoT & robotics skill for AI agents, published by D-Robotics in the moss repository on GitHub. Skillspace rates rdk-device C (73/100) and it passed the safety scan; the rating is based on static analysis only.
End-to-end deployment of a user's OWN model on RDK boards — quantize .pt/.onnx into .bin (X3/X5/Ultra) or .hbm (S100/S100P/S600) through the BPU toolchain — plus first-boot/network setup, camera bringup, and on-board inference debugging. Use whenever the user is deploying a self-trained model, reports slow inference (1-2 FPS, "pt 拷上去很慢"), is doing first boot / 开箱 / 入门, or debugging a camera or 推理 pipeline. 触发词:部署模型、YOLO 转换、hb_mapper、hb_compile、量化、.bin/.hbm、pt 直接跑很慢、BPU 推理、首次开箱、新手上手、摄像头无画面、v4l2。Routing — ready-made precompiled models → rdk-model-zoo; inference as a ROS node / stereo depth / lidar → rdk-ros; embodied ACT/VLA/Pi0 BPU compile → rdk-embodied-lerobot; pure error-code lookup → rdk-board-knowledge.
- Grade
- C
- Quality
- 73 / 100
- Safety
- Passed
- GitHub stars
- 73
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 94 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.