pose-datajoint

Name: pose-datajoint
Availability: InStock
Author: peabody124

Query biomechanics DataJoint tables for video/session counts and pose reconstructions.

3|Updated Dec 25, 2025

Search Tags:#query #biomechanics #reconstruction #monocular #MMC #datajoint #pose-estimation

Ready to run

npx skills add https://github.com/peabody124/reproducible_agent_environment --skill pose-datajoint

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pose-datajoint
Source: https://github.com/peabody124/reproducible_agent_environment/tree/main/skills/pose-datajoint
Command: npx skills add https://github.com/peabody124/reproducible_agent_environment --skill pose-datajoint

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a Python-oriented reference to query biomechanics DataJoint tables to count videos and sessions, filter by video_project or participant_id/subject_id, and fetch keypoints or kinematic reconstructions across both Multi-Camera (MMC) and Monocular (PBL) pipelines.

Core Features & Use Cases

Query and filter biomechanics datasets across MMC and monocular pipelines using standard DataJoint keys.
Fetch outputs such as timestamps, qpos, joints, sites, and reconstruction data for analysis or visualization.
Use Case: A researcher counts all MMC videos in a project and retrieves the corresponding kinematic reconstructions for downstream analysis.

Quick Start

Run sample queries to count MMC videos for a project and fetch the first trial's qpos, or query monocular sessions for a specific subject.

Frequently Asked Questions about pose-datajoint

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I query biomechanics DataJoint tables to count videos and sessions?▼

To query biomechanics DataJoint tables, use this Skill to filter datasets by video_project, participant_id, or subject_id and retrieve video/session counts across both MMC and monocular pipelines.

What do I need to fetch pose estimation keypoints from a monocular pipeline?▼

Fetching pose estimation keypoints from a monocular pipeline requires DataJoint and domain-specific models like monocular_dj and pose_pipeline to be installed and accessible in your Python environment.

Can I retrieve kinematic reconstructions for multi-camera MMC trials using DataJoint?▼

Yes, you can retrieve kinematic reconstructions for multi-camera MMC trials by querying DataJoint tables to fetch outputs like qpos, joints, sites, and timestamps for downstream analysis.

Does this biomechanics query approach work for both multi-camera and monocular data?▼

This biomechanics query approach works for both Multi-Camera (MMC) and Monocular (PBL) pipelines, supporting standard DataJoint keys to filter and fetch pose reconstruction data across both workflows.

What are the limitations of querying pose reconstruction data with DataJoint?▼

A key limitation is the strict environment requirement: DataJoint and specific models like multi_camera_dj, monocular_dj, and KinematicReconstruction must be pre-installed and accessible in Python to execute pose reconstruction queries successfully.