Agent Skills

CV Model Training

cv-train-stack

Review, run, validate and audit computer vision model training with checks for dataset quality, preprocessing consistency, augmentation, and deployment validati

TensorsLab Image Generation

skills

Generate and edit images (text→image, image→image, advanced edits) using TensorsLab models with automatic prompt enhancement and local output saving.

Video Expert Analyzer

video-expert-analyzer

Analyze videos, score scenes and extract best shots using an AI-powered five-dimension scoring system based on Walter Murch's editing rules. Works with Bilibili

Depth Estimation (Privacy)

deepcamera

Real-time monocular depth estimation for camera feeds with a privacy-focused depth-only mode to anonymize people while preserving scene layout.

Transformers.js ML Integration

opencode-skills-collection

Run state-of-the-art ML models for text, image, and audio directly in JavaScript/Node.js without a separate Python backend.

GraspGenX: Cross-Embodiment 6-DOF Grasping

graspgenx

Generate high-confidence 6-DOF grasps for any gripper using a cross-embodiment foundation model via ZMQ or MCP.

Generative Diffusion Model Analyzer

pjt222

Evaluates pre-trained diffusion models using quality metrics, noise schedule analysis, and latent space probing.