🎯
Skills
Loading...
Showing 30 of 146054 results
A skill for creating zero-dependency, animation-rich HTML presentations that run entirely in the browser, with support for PowerPoint conversion, visual style exploration, viewport-safe layouts, and keyboard/touch/wheel navigation.
Trains BEVFusion multi-sensor fusion models through NVIDIA TAO Toolkit, combining camera and LiDAR data for 3D object detection in autonomous driving and robotics applications.
Trains OCDNet text detection models with NVIDIA TAO Toolkit, fine-tuning pretrained models to accurately detect and localize text regions in natural scene images for OCR pipelines.
Trains SegFormer transformer-based semantic segmentation models using NVIDIA TAO Toolkit, combining efficient hierarchical encoders with lightweight decoders for fast and accurate segmentation on custom data.
Day 2 MCP and Context Sync skill from AI Native Camp, a 7-day intensive Claude Code bootcamp. Teaches the Model Context Protocol (MCP), plugin system, subagents, and guides users to build their own Context Sync skill.
`/hub:eval` — rank all AgentHub agent results for a session using metric mode (run an eval command in each agent's worktree with `scripts/result_ranker.py --session ... --eval-cmd ... --metric ... --direction ...`), LLM judge mode (compare `git diff {base_branch}...{agent_branch}` plus each agent's `.agenthub/board/results/agent-{i}-result.md` on correctness / simplicity / quality), or hybrid (metric first, LLM tie-break within 10%). Updates session state via `session_manager.py --update ... --state evaluating` and points to `/hub:merge` for the winner.
A skill from the Everything Claude Code performance system that provides workflow definitions, domain knowledge, and agent capabilities for AI coding tools including Claude Code, Codex, Cursor, and others.
Salesforce development skills for Claude Code covering Lightning Web Components with PICKLES architecture, wire service patterns, Apex integration, and Jest testing.
A skill for training, evaluating, and deploying RT-DETR (Real-Time Detection Transformer) models for 2D object detection, with support for distillation, quantization, and AutoML-enabled training workflows.
Helps write copy that adheres to Sentry's brand voice, tone, and stylistic guidelines, ensuring consistent and on-brand communication.
A notebooklm skill from Developer Kit, providing full-stack development tools and skills for Claude Code.
Trains Deformable DETR object detection models with NVIDIA TAO Toolkit, leveraging deformable attention mechanisms for efficient end-to-end detection that can be exported for production deployment.
Trains OneFormer universal image segmentation models with NVIDIA TAO Toolkit, using a single model architecture for panoptic, semantic, and instance segmentation guided by task-conditioned queries.
Routes Visual ChangeNet sample data within NVIDIA TAO Toolkit's change detection pipeline, directing training samples to appropriate processing stages for visual change analysis workflows.
Trains Fast Foundation Stereo depth estimation models via NVIDIA TAO Toolkit, optimizing pretrained stereo vision models with custom data for real-time depth perception in edge deployments.
An official NVIDIA-verified skill that guides training foundation stereo vision models using NVIDIA TAO Toolkit, covering dataset preparation, training configuration, and model evaluation workflows.
Day 1 test skill from AI Native Camp, a 7-day intensive Claude Code bootcamp for non-developers. Teaches Claude Code basics through hands-on exercises with guided setup and skill installation.
Part of the Sanity Agent Toolkit, providing AI agents with best practices for Portable Text serialization in Sanity CMS development. Includes MCP server access, agent skills, and integration guides for Cursor, Claude Code, and other editors.
Trains Sparse4D temporal 3D object detection models using NVIDIA TAO Toolkit, processing multi-camera video sequences for accurate 3D detection in autonomous driving scenarios.
Produces thorough, cited research reports by searching multiple web sources using Firecrawl and Exa MCP tools, with multi-angle query planning, source cross-referencing, and structured report generation with inline citations.
Guides podcast strategy, production, distribution, marketing, and SEO in a market of 3M+ active shows and 500M+ global listeners, where discoverability (~32% search, ~28% apps, ~24% social) is the main bottleneck. Distinguishes format (interview/solo/co-hosted/narrative), niche, and goals, and hands off show-note writing to article-content.
A marimo skill that converts Streamlit apps to marimo notebooks, mapping Streamlit widgets to marimo UI equivalents. Covers execution model differences, state management, and caching pattern migration.
Skill from Anthropic's Knowledge Work Plugins that guides building applications with Zoom's Meeting SDK for embedding video meeting experiences in custom applications.
A Claude Code skill providing the latest OWASP security best practices (2025-2026) including Top 10:2025, ASVS 5.0, and Agentic AI Security (ASI01-ASI10), with secure code patterns and language-specific quirks for 20+ programming languages.
A Claude plugin that provides specialized guidance for building Zoom Phone integrations, bundling skills, connectors, and sub-agents to help developers create telephony features using Zoom platform APIs.
A spring boot project creator skill from Developer Kit, providing full-stack development tools and skills for Claude Code.