Skills

from mckruz/comfyui-expert

An open-source, modern ChatGPT/LLM UI framework with speech synthesis, multi-modal support, and extensible plugin system for deploying private chat applications.

Optimizes vague prompts into precise, structured specifications using EARS methodology, transforming natural language requirements into actionable, testable descriptions.

Deploys NVIDIA TAO Toolkit workflows on Kubernetes clusters, enabling scalable distributed training and optimization of vision AI models across container-orchestrated GPU infrastructure.

A Claude Code plugin marketplace with 22 skills and 27 plugins for 3D/WebGL, animation, and modern web development, covering Three.js, GSAP, React Three Fiber, Babylon.js, Framer Motion, and more.

from heygen-com/skills

Memory optimization skill from claude-brewcode, a Claude Code plugin collection. Provides memory optimization capabilities for development workflows with Claude Code.

Creates and experiments with real-time GLSL shaders for visual effects, procedural graphics, and generative art

Performs root cause analysis on Visual ChangeNet results within NVIDIA TAO Toolkit, diagnosing detection performance and identifying failure patterns in visual change detection workflows.

Generates image grounding data using NVIDIA TAO Toolkit, creating region-text pair annotations that link visual regions to language descriptions for training grounded vision-language models.

A claude-blog sub-skill that writes, translates, localizes, and emits hreflang tags for blog content in multiple languages with a single command, including cultural deep-adaptation per locale and SEO-optimized translation with format preservation.

Agent skills for Dart and Flutter development covering Drift database, adaptive UI, animations, app architecture, internationalization, navigation, networking, and testing based on official documentation.

A comprehensive developer toolkit providing Claude Code skills and plugins for software development workflows, code quality, and productivity.

Analyzes performance gaps in Visual ChangeNet models within NVIDIA TAO Toolkit, evaluating change detection accuracy and identifying areas where the model needs improvement on specific data distributions.

Executes the AutoML-powered DEFT (Deep Efficient Fine-Tuning) pipeline in NVIDIA TAO Toolkit, combining automated hyperparameter search with efficient fine-tuning for optimized vision model training.

Trains Grounding DINO open-set object detection models with NVIDIA TAO Toolkit, enabling text-prompted detection where models locate objects described in natural language using custom training data.

from botpress/skills

Designs comprehensive domain error handling strategies with categorization, recovery mechanisms, and contextual error management for different audiences.

Runs the DEFT AOI (Automated Optical Inspection) pipeline in NVIDIA TAO Toolkit, automating defect detection workflows for manufacturing quality control using fine-tuned vision AI models.

Trains optical inspection models using NVIDIA TAO Toolkit for manufacturing defect detection, fine-tuning pretrained vision models to identify anomalies and quality issues in production environments.

Trains pose classification models using NVIDIA TAO Toolkit to categorize body poses in images and video, building on pretrained pose estimation models for fitness tracking, ergonomics, and safety applications.

Performs cultural deep-adaptation of blog content for specific locales, going beyond translation to adjust examples, references, idioms, and cultural context for the target audience within the claude-blog skill suite.

Train or fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment.

from yuan1z0825/nature-skills

Executes NVIDIA TAO Toolkit workflows on the NVIDIA AI Platform, providing managed infrastructure for fine-tuning and optimizing 100+ pretrained vision AI models at scale.

Trains re-identification (ReID) models through NVIDIA TAO Toolkit, fine-tuning pretrained models to recognize and track individuals across different camera views for surveillance and retail analytics.

An official NVIDIA-verified agent skill that teaches AI agents how to optimally use NVIDIA software including CUDA-X libraries, AI Blueprints, and platform tools, installable via the skills CLI.

Audits multilingual blog content for completeness, hreflang correctness, translation parity, and freshness across locales. Part of the claude-blog skill suite that supports full-lifecycle blog management with dual optimization for Google rankings and AI citation platforms.

A branding skill from Marketing Skills, a collection of AI-powered marketing skills for content creation, SEO, social media, and campaign management.

Trains OCRNet semantic segmentation models with NVIDIA TAO Toolkit, fine-tuning pretrained models for pixel-level scene understanding with custom data and exporting optimized models for deployment.