From dora-skills
Provides pre-built Dora hub nodes for robotic and AI tasks including camera capture, object detection (YOLO), segmentation (SAM2), depth estimation, visualization (Rerun), and speech-to-text (Distil-Whisper).
How this skill is triggered — by the user, by Claude, or both
Slash command
/dora-skills:hub-nodesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> Pre-built nodes for common robotic and AI tasks
Pre-built nodes for common robotic and AI tasks
| Package | Command | Description |
|---|---|---|
| opencv-video-capture | pip install opencv-video-capture | Webcam/video capture |
| dora-pyrealsense | pip install dora-pyrealsense | Intel RealSense |
| dora-pyorbbecksdk | pip install dora-pyorbbecksdk | Orbbeck cameras |
opencv-video-capture
- id: camera
build: pip install opencv-video-capture
path: opencv-video-capture
inputs:
tick: dora/timer/millis/33
outputs:
- image
env:
CAPTURE_PATH: "0" # 0 for webcam, or path to video
IMAGE_WIDTH: "640"
IMAGE_HEIGHT: "480"
| Package | Command | Description |
|---|---|---|
| dora-yolo | pip install dora-yolo | YOLO v8 detection |
| dora-mediapipe | pip install dora-mediapipe | MediaPipe detection |
dora-yolo
- id: yolo
build: pip install dora-yolo
path: dora-yolo
inputs:
image: camera/image
outputs:
- bbox
env:
MODEL: yolov8n.pt # yolov8n/s/m/l/x.pt
DEVICE: cuda # cuda or cpu
| Package | Command | Description |
|---|---|---|
| dora-sam2 | pip install dora-sam2 | Segment Anything 2 |
dora-sam2
- id: sam
build: pip install dora-sam2
path: dora-sam2
inputs:
image: camera/image
bbox: yolo/bbox # Optional: guided segmentation
outputs:
- mask
| Package | Command | Description |
|---|---|---|
| dora-vggt | pip install dora-vggt | Depth estimation |
| dora-cotracker | pip install dora-cotracker | Point tracking |
dora-vggt
- id: depth
build: pip install dora-vggt
path: dora-vggt
inputs:
image: camera/image
outputs:
- depth
- points3d
| Package | Command | Description |
|---|---|---|
| dora-rerun | pip install dora-rerun | Rerun visualization |
dora-rerun
- id: plot
build: pip install dora-rerun
path: dora-rerun
inputs:
image: camera/image
boxes2d: yolo/bbox
# Optional inputs:
# depth: depth/depth
# points3d: depth/points3d
# mask: sam/mask
| Package | Command | Description |
|---|---|---|
| dora-distil-whisper | pip install dora-distil-whisper | Distil-Whisper STT |
| dora-funasr | pip install dora-funasr | FunASR (Chinese STT) |
dora-distil-whisper
- id: stt
build: pip install dora-distil-whisper
path: dora-distil-whisper
inputs:
audio: microphone/audio
outputs:
- text
env:
MODEL: base # tiny, base, small, medium, large
LANGUAGE: en
| Package | Command | Description |
|---|---|---|
| dora-kokoro-tts | pip install dora-kokoro-tts | Kokoro TTS |
| dora-outtetts | pip install dora-outtetts | OuteTTS |
| dora-parler | pip install dora-parler | Parler TTS |
dora-kokoro-tts
- id: tts
build: pip install dora-kokoro-tts
path: dora-kokoro-tts
inputs:
text: llm/response
outputs:
- audio
env:
VOICE: af_bella
| Package | Command | Description |
|---|---|---|
| dora-vad | pip install dora-vad | Voice activity detection |
dora-vad
- id: vad
build: pip install dora-vad
path: dora-vad
inputs:
audio: microphone/audio
outputs:
- speech_audio
- is_speaking
| Package | Command | Description |
|---|---|---|
| dora-microphone | pip install dora-microphone | Microphone input |
| dora-pyaudio | pip install dora-pyaudio | Audio playback |
| Package | Command | Description |
|---|---|---|
| dora-qwen | pip install dora-qwen | Qwen text models |
| dora-llama-cpp-python | pip install dora-llama-cpp-python | Llama.cpp models |
| dora-mistral-rs | pip install dora-mistral-rs | Mistral models |
dora-qwen
- id: llm
build: pip install dora-qwen
path: dora-qwen
inputs:
text: stt/text
outputs:
- response
env:
MODEL: Qwen/Qwen2.5-7B
| Package | Command | Description |
|---|---|---|
| dora-qwen2-5-vl | pip install dora-qwen2-5-vl | Qwen2.5-VL |
| dora-internvl | pip install dora-internvl | InternVL |
dora-qwen2-5-vl
- id: vlm
build: pip install dora-qwen2-5-vl
path: dora-qwen2-5-vl
inputs:
image: camera/image
prompt: user/question
outputs:
- response
env:
MODEL: Qwen/Qwen2.5-VL-7B
| Package | Command | Description |
|---|---|---|
| dora-rustypot | pip install dora-rustypot | Dynamixel servos |
dora-rustypot
- id: arm
build: pip install dora-rustypot
path: dora-rustypot
inputs:
command: planner/joints
outputs:
- state
env:
SERIAL_PORT: /dev/ttyUSB0
BAUD_RATE: "1000000"
| Package | Command | Description |
|---|---|---|
| dora-pytorch-kinematics | pip install dora-pytorch-kinematics | FK/IK |
dora-pytorch-kinematics
- id: kinematics
build: pip install dora-pytorch-kinematics
path: dora-pytorch-kinematics
inputs:
target_pose: planner/target
outputs:
- joint_targets
env:
URDF_PATH: robot.urdf
| Package | Install | Description |
|---|---|---|
| dora-ros2-bridge | Rust crate (build from dora repo) | ROS2 integration |
Note: dora-ros2-bridge is a Rust library in the main dora repository, not a pip package. See the ROS2 bridge examples.
| Package | Install | Description |
|---|---|---|
| dora-lerobot | From dora-lerobot repo | LeRobot dataset tools |
Note: dora-lerobot is from a separate repository:
git clone https://github.com/dora-rs/dora-lerobot cd dora-lerobot && pip install -e dora_lerobot
Recording
# Install from dora-lerobot repo first
- id: recorder
path: dora-lerobot-recorder
inputs:
image: camera/image
state: arm/state
action: teleop/command
env:
DATASET_NAME: my_dataset
Replay
# Install from dora-lerobot repo first
- id: replay
path: dora-lerobot-replay
inputs:
tick: dora/timer/millis/33
outputs:
- image
- state
- action
env:
DATASET_NAME: my_dataset
nodes:
# Camera
- id: camera
build: pip install opencv-video-capture
path: opencv-video-capture
inputs:
tick: dora/timer/millis/100
outputs:
- image
# VLM for image understanding
- id: vlm
build: pip install dora-qwen2-5-vl
path: dora-qwen2-5-vl
inputs:
image: camera/image
prompt: stt/text
outputs:
- response
# Microphone
- id: microphone
build: pip install dora-microphone
path: dora-microphone
inputs:
tick: dora/timer/millis/100
outputs:
- audio
# Speech to text
- id: stt
build: pip install dora-distil-whisper
path: dora-distil-whisper
inputs:
audio: microphone/audio
outputs:
- text
# Text to speech
- id: tts
build: pip install dora-kokoro-tts
path: dora-kokoro-tts
inputs:
text: vlm/response
outputs:
- audio
# Speaker
- id: speaker
build: pip install dora-pyaudio
path: dora-pyaudio
inputs:
audio: tts/audio
# Visualization
- id: plot
build: pip install dora-rerun
path: dora-rerun
inputs:
image: camera/image
npx claudepluginhub zhanghandong/dora-skills --plugin dora-skillsProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.