Engineering
98,147 rows, by stacks then stars
NVIDIA/skills/skills/tao-port-huggingface-model Skill
4,064★ repoIntegrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use when the user asks to "integrate a HuggingFace model into TAO", "add an HF model to TAO Toolkit", "wire a HuggingFace ViT/DETR/ SegFormer into tao-pytorch", "build a TAO trainer + deploy pipeline for an HF CV model", or pastes a HuggingFace model URL/ID and wants it turned into a TAO model. Covers the full 7-phase loop: prerequisites check, HuggingFace inspection and validation, codebase exploration, tao-core configuration and native trainer implementation, ONNX export plus TensorRT deploy integration, packaging and L0 testing, container-based end-to-end validation, and (conditional) accuracy/latency tuning. Supports classification, object detection, semantic / instance / panoptic segmentation, zero-shot detection, and depth estimation.
NVIDIA/skills/skills/tao-run-automl Skill
4,064★ repoRun AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, automl, automl_settings, AutoMLRunner, tao_automl, bayesian search, hyperband, ASHA, LLM-guided search, autoresearch, or wants to tune training hyperparameters for any TAO network. Platform-agnostic — runs on any SDK (Brev, SLURM, Kubernetes, Docker).
NVIDIA/skills/skills/tao-run-inference-service Skill
4,064★ repoStart, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill. Handles container image resolution, job-payload JSON construction, and the service registry. Use when the user wants to run inference on a TAO model checkpoint using a microservice container, deploy a TAO inference endpoint, or stop a running inference container.
NVIDIA/skills/skills/tao-run-on-kubernetes Skill
4,064★ repoKubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use when running on EKS / GKE / AKS / on-prem clusters with the NVIDIA GPU Operator installed, or when integrating TAO into an existing k8s-native ML platform.
NVIDIA/skills/skills/tao-run-on-local-docker Skill
4,064★ repoLocal or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use when running TAO jobs on the current machine, a directly attached Docker host, or a remote GPU box exposed through DOCKER_HOST. Trigger phrases include "run locally", "local Docker", "remote Docker", "use my GPU", "run on my machine", "host Docker daemon".
NVIDIA/skills/skills/tao-run-platform Skill
4,064★ repoTAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM, local Docker, Kubernetes). Use when the user wants to run TAO jobs through the SDK, get job tracking, S3 I/O wrapping, multi-node distributed training, or platform-specific features that docker-run can't provide. Trigger phrases include "use the TAO SDK", "call tao_sdk", "AutoMLRunner", "ActionWorkflow", "Job handles", "S3 I/O wrapping", "TAO platform run".
NVIDIA/skills/skills/tao-setup-nvidia-gpu-host Skill
4,064★ repoHost setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.0, and NVIDIA Container Toolkit 1.19.0 for Docker/local-Docker and Kubernetes GPU worker hosts. The `--check-only` path works on any Linux distribution; `--install` automates debian-family (Ubuntu/Debian/Pop!_OS/Mint/Zorin/Raspbian), rhel-family (Fedora/RHEL/Rocky/AlmaLinux), and suse-family (openSUSE/SLES) hosts, and prints actionable manual-install steps for everything else. Use when the user asks to "set up an NVIDIA GPU host", "check TAO Docker GPU runtime", or prepare a Kubernetes GPU worker for TAO.
NVIDIA/skills/skills/tao-train-rtdetr Skill
4,064★ repoRT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO RT-DETR model. Trigger phrases include "train RT-DETR", "real-time DETR", "low-latency object detection", "RT-DETR distillation / quantization".
NVIDIA/skills/skills/tilegym-adding-cutile-kernel Skill
4,064★ repoAdd a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.
NVIDIA/skills/skills/tilegym-cutile-python Skill
4,064★ repoExpert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.
Tilegym improve cutile kernel perf
NVIDIA/skills/skills/tilegym-improve-cutile-kernel-perf Skill
4,064★ repoIteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
NVIDIA/skills/skills/vss-deploy-dense-captioning Skill
4,064★ repoUse this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.
Vss deploy detection tracking 2d
NVIDIA/skills/skills/vss-deploy-detection-tracking-2d Skill
4,064★ repoUse this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill.
Vss deploy detection tracking 3d
NVIDIA/skills/skills/vss-deploy-detection-tracking-3d Skill
4,064★ repoDeploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video files, and RTSP streams, and chains to `vss-generate-video-calibration` when calibration is missing. Use `vss-deploy-profile` for the full warehouse blueprint and `vss-deploy-detection-tracking-2d` for single-camera 2D detection.
NVIDIA/skills/skills/vss-deploy-profile Skill
4,064★ repoUse to select, configure, deploy, verify, debug, or tear down a VSS profile (base, search, lvs, warehouse, edge). Not for standalone microservices — use the vss-deploy-* skill.
NVIDIA/skills/skills/vss-deploy-video-embedding Skill
4,064★ repoUse this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage prerequisites, the `/v1` REST API (file uploads, text and video embeddings, live RTSP streams, health and metrics), Redis/Kafka/OTel integration, common failure modes, and teardown.
NVIDIA/skills/skills/vss-query-analytics Skill
4,064★ repoUse this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range narrative reports.
NVIDIA/skills/skills/vss-setup-behavior-analytics Skill
4,064★ repoUse to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
NVIDIA/skills/skills/vss-setup-video-analytics-api Skill
4,064★ repoUse to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
SamurAIGPT/Generative-Media-Skills/library/workflow Skill
4,041★ repoBuild, run, and visualize multi-step AI generation workflows. The AI architect translates natural language descriptions into connected node graphs — chain image generation, video creation, enhancement, and editing into automated pipelines.
parcadei/Continuous-Claude-v3/.claude/skills/agent-orchestration Skill
3,950★ repoAgent Orchestration Rules
parcadei/Continuous-Claude-v3/.claude/skills/agentic-workflow Skill
3,950★ repoAgentic Workflow Pattern
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/agentica-claude-proxy Skill
3,950★ repoGuide for integrating Agentica SDK with Claude Code CLI proxy
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/archive/router-first-architecture Skill
3,950★ repoRouter-First Architecture
parcadei/Continuous-Claude-v3/.claude/skills/background-agent-pings Skill
3,950★ repoBackground Agent Pings
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/braintrust-tracing Skill
3,950★ repoBraintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/create_handoff Skill
3,950★ repoCreate handoff document for transferring work to another session
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/dead-code Skill
3,950★ repoFind unused functions and dead code in the codebase
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/debug-hooks Skill
3,950★ repoSystematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/debug Skill
3,950★ repoDebug issues by investigating logs, database state, and git history
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/environment-triage Skill
3,950★ repoEnvironment Triage
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/explore Skill
3,950★ repoMeta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/hook-developer Skill
3,950★ repoComplete Claude Code hooks reference - input/output schemas, registration, testing patterns
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/llm-tuning-patterns Skill
3,950★ repoLLM Tuning Patterns
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/math/optimization/constrained-optimization Skill
3,950★ repoProblem-solving strategies for constrained optimization in optimization
parcadei/Continuous-Claude-v3/.claude/skills/math/optimization/convex-optimization Skill
3,950★ repoProblem-solving strategies for convex optimization in optimization
parcadei/Continuous-Claude-v3/.claude/skills/mcp-chaining Skill
3,950★ repoResearch-to-implement pipeline chaining 5 MCP tools with graceful degradation
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/mcp-scripts Skill
3,950★ repoMCP Script Rules
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/opc-architecture Skill
3,950★ repoOPC Architecture Understanding
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/parallel-agent-contracts Skill
3,950★ repoParallel Agent Type Contracts
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/parallel-agents Skill
3,950★ repoParallel Agent Orchestration
parcadei/Continuous-Claude-v3/.claude/skills/plan-agent Skill
3,950★ repoPlanning agent that creates implementation plans and handoffs from conversation context
parcadei/Continuous-Claude-v3/.claude/skills/refactor Skill
3,950★ repoCode refactoring workflow - analyze → plan → implement → review → validate
parcadei/Continuous-Claude-v3/.claude/skills/release Skill
3,950★ repoRelease preparation workflow - security audit → E2E tests → review → changelog → docs
parcadei/Continuous-Claude-v3/.claude/skills/repo-research-analyst Skill
3,950★ repoAnalyze repository structure, patterns, conventions, and documentation for understanding a new codebase
The same file is in 2 other repositories
parcadei/Continuous-Claude-v3/.claude/skills/research-agent Skill
3,950★ repoResearch agent for external documentation, best practices, and library APIs via MCP tools
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/resume_handoff Skill
3,950★ repoResume work from handoff document with context analysis and validation
The same file is in 2 other repositories
parcadei/Continuous-Claude-v3/.claude/skills/router-first-architecture Skill
3,950★ repoRouter-First Architecture
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/security Skill
3,950★ repoSecurity audit workflow - vulnerability scan → verification
parcadei/Continuous-Claude-v3/.claude/skills/skill-developer Skill
3,950★ repoMeta-skill for creating and managing Claude Code skills
parcadei/Continuous-Claude-v3/.claude/skills/tdd-migrate Skill
3,950★ repoTDD workflow for migrations - orchestrate agents, zero main context growth
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/tdd-migration-pipeline Skill
3,950★ repoOrchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation
The same file is in 1 other repository
parcadei/Continuous-Claude-v3/.claude/skills/tdd Skill
3,950★ repoTest-driven development workflow with philosophy guide - plan → write tests → implement → validate
parcadei/Continuous-Claude-v3/.claude/skills/test Skill
3,950★ repoComprehensive testing workflow - unit tests ∥ integration tests → E2E tests
parcadei/Continuous-Claude-v3/.claude/skills/validate-agent Skill
3,950★ repoValidation agent that validates plan tech choices against current best practices
The same file is in 2 other repositories
parcadei/Continuous-Claude-v3/.claude/skills/workflow-router Skill
3,950★ repoGoal-based workflow orchestration - routes tasks to specialist agents based on user goals
The same file is in 1 other repository
microsoft/mcp/com.microsoft/template-server-name MCP server
3,866★ repoTemplate MCP server example.
foryourhealth111-pixel/Vibe-Skills/bundled/skills/architecture-patterns Skill
3,822★ repoImplement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.
The same file is in 4 other repositories
foryourhealth111-pixel/Vibe-Skills/bundled/skills/chembl-database Skill
3,822★ repoQuery ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.
foryourhealth111-pixel/Vibe-Skills/bundled/skills/claude-skills Skill
3,822★ repoClaude Skills meta-skill: extract domain material (docs/APIs/code/specs) into a reusable Skill (SKILL.md + references/scripts/assets), and refactor existing Skills for clarity, activation reliability, and quality gates.
The same file is in 3 other repositories