agentsclimarketplace

Engineering

98,147 rows, by stacks then stars

  • Tao port huggingface model

    NVIDIA/skills/skills/tao-port-huggingface-model Skill

    4,064★ repo

    Integrate 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.

  • Tao run automl

    NVIDIA/skills/skills/tao-run-automl Skill

    4,064★ repo

    Run 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).

  • Tao run inference service

    NVIDIA/skills/skills/tao-run-inference-service Skill

    4,064★ repo

    Start, 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.

  • Tao run on kubernetes

    NVIDIA/skills/skills/tao-run-on-kubernetes Skill

    4,064★ repo

    Kubernetes 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.

  • Tao run on local docker

    NVIDIA/skills/skills/tao-run-on-local-docker Skill

    4,064★ repo

    Local 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".

  • Tao run platform

    NVIDIA/skills/skills/tao-run-platform Skill

    4,064★ repo

    TAO 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".

  • Tao setup nvidia gpu host

    NVIDIA/skills/skills/tao-setup-nvidia-gpu-host Skill

    4,064★ repo

    Host 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.

  • Tao train rtdetr

    NVIDIA/skills/skills/tao-train-rtdetr Skill

    4,064★ repo

    RT-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".

  • Tilegym adding cutile kernel

    NVIDIA/skills/skills/tilegym-adding-cutile-kernel Skill

    4,064★ repo

    Add 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.

  • Tilegym cutile python

    NVIDIA/skills/skills/tilegym-cutile-python Skill

    4,064★ repo

    Expert 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★ repo

    Iteratively 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.

  • Vss deploy dense captioning

    NVIDIA/skills/skills/vss-deploy-dense-captioning Skill

    4,064★ repo

    Use 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★ repo

    Use 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★ repo

    Deploy 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.

  • Vss deploy profile

    NVIDIA/skills/skills/vss-deploy-profile Skill

    4,064★ repo

    Use 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.

  • Vss deploy video embedding

    NVIDIA/skills/skills/vss-deploy-video-embedding Skill

    4,064★ repo

    Use 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.

  • Vss query analytics

    NVIDIA/skills/skills/vss-query-analytics Skill

    4,064★ repo

    Use 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.

  • Vss setup behavior analytics

    NVIDIA/skills/skills/vss-setup-behavior-analytics Skill

    4,064★ repo

    Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.

  • Vss setup video analytics api

    NVIDIA/skills/skills/vss-setup-video-analytics-api Skill

    4,064★ repo

    Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.

  • Workflow

    SamurAIGPT/Generative-Media-Skills/library/workflow Skill

    4,041★ repo

    Build, 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.

  • Agent orchestration

    parcadei/Continuous-Claude-v3/.claude/skills/agent-orchestration Skill

    3,950★ repo

    Agent Orchestration Rules

  • Agentic workflow

    parcadei/Continuous-Claude-v3/.claude/skills/agentic-workflow Skill

    3,950★ repo

    Agentic Workflow Pattern

    The same file is in 1 other repository

  • Agentica claude proxy

    parcadei/Continuous-Claude-v3/.claude/skills/agentica-claude-proxy Skill

    3,950★ repo

    Guide for integrating Agentica SDK with Claude Code CLI proxy

    The same file is in 1 other repository

  • Router first architecture

    parcadei/Continuous-Claude-v3/.claude/skills/archive/router-first-architecture Skill

    3,950★ repo

    Router-First Architecture

  • Background agent pings

    parcadei/Continuous-Claude-v3/.claude/skills/background-agent-pings Skill

    3,950★ repo

    Background Agent Pings

    The same file is in 1 other repository

  • Braintrust tracing

    parcadei/Continuous-Claude-v3/.claude/skills/braintrust-tracing Skill

    3,950★ repo

    Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

    The same file is in 1 other repository

  • Create handoff

    parcadei/Continuous-Claude-v3/.claude/skills/create_handoff Skill

    3,950★ repo

    Create handoff document for transferring work to another session

    The same file is in 1 other repository

  • Dead code

    parcadei/Continuous-Claude-v3/.claude/skills/dead-code Skill

    3,950★ repo

    Find unused functions and dead code in the codebase

    The same file is in 1 other repository

  • Debug hooks

    parcadei/Continuous-Claude-v3/.claude/skills/debug-hooks Skill

    3,950★ repo

    Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.

    The same file is in 1 other repository

  • Debug

    parcadei/Continuous-Claude-v3/.claude/skills/debug Skill

    3,950★ repo

    Debug issues by investigating logs, database state, and git history

    The same file is in 1 other repository

  • Environment triage

    parcadei/Continuous-Claude-v3/.claude/skills/environment-triage Skill

    3,950★ repo

    Environment Triage

    The same file is in 1 other repository

  • Explore

    parcadei/Continuous-Claude-v3/.claude/skills/explore Skill

    3,950★ repo

    Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)

    The same file is in 1 other repository

  • Hook developer

    parcadei/Continuous-Claude-v3/.claude/skills/hook-developer Skill

    3,950★ repo

    Complete Claude Code hooks reference - input/output schemas, registration, testing patterns

    The same file is in 1 other repository

  • Llm tuning patterns

    parcadei/Continuous-Claude-v3/.claude/skills/llm-tuning-patterns Skill

    3,950★ repo

    LLM Tuning Patterns

    The same file is in 1 other repository

  • Constrained optimization

    parcadei/Continuous-Claude-v3/.claude/skills/math/optimization/constrained-optimization Skill

    3,950★ repo

    Problem-solving strategies for constrained optimization in optimization

  • Convex optimization

    parcadei/Continuous-Claude-v3/.claude/skills/math/optimization/convex-optimization Skill

    3,950★ repo

    Problem-solving strategies for convex optimization in optimization

  • Mcp chaining

    parcadei/Continuous-Claude-v3/.claude/skills/mcp-chaining Skill

    3,950★ repo

    Research-to-implement pipeline chaining 5 MCP tools with graceful degradation

    The same file is in 1 other repository

  • Mcp scripts

    parcadei/Continuous-Claude-v3/.claude/skills/mcp-scripts Skill

    3,950★ repo

    MCP Script Rules

    The same file is in 1 other repository

  • Opc architecture

    parcadei/Continuous-Claude-v3/.claude/skills/opc-architecture Skill

    3,950★ repo

    OPC Architecture Understanding

    The same file is in 1 other repository

  • Parallel agent contracts

    parcadei/Continuous-Claude-v3/.claude/skills/parallel-agent-contracts Skill

    3,950★ repo

    Parallel Agent Type Contracts

    The same file is in 1 other repository

  • Parallel agents

    parcadei/Continuous-Claude-v3/.claude/skills/parallel-agents Skill

    3,950★ repo

    Parallel Agent Orchestration

  • Plan agent

    parcadei/Continuous-Claude-v3/.claude/skills/plan-agent Skill

    3,950★ repo

    Planning agent that creates implementation plans and handoffs from conversation context

  • Refactor

    parcadei/Continuous-Claude-v3/.claude/skills/refactor Skill

    3,950★ repo

    Code refactoring workflow - analyze → plan → implement → review → validate

  • Release

    parcadei/Continuous-Claude-v3/.claude/skills/release Skill

    3,950★ repo

    Release preparation workflow - security audit → E2E tests → review → changelog → docs

  • Repo research analyst

    parcadei/Continuous-Claude-v3/.claude/skills/repo-research-analyst Skill

    3,950★ repo

    Analyze repository structure, patterns, conventions, and documentation for understanding a new codebase

    The same file is in 2 other repositories

  • Research agent

    parcadei/Continuous-Claude-v3/.claude/skills/research-agent Skill

    3,950★ repo

    Research agent for external documentation, best practices, and library APIs via MCP tools

    The same file is in 1 other repository

  • Resume handoff

    parcadei/Continuous-Claude-v3/.claude/skills/resume_handoff Skill

    3,950★ repo

    Resume work from handoff document with context analysis and validation

    The same file is in 2 other repositories

  • Router first architecture

    parcadei/Continuous-Claude-v3/.claude/skills/router-first-architecture Skill

    3,950★ repo

    Router-First Architecture

    The same file is in 1 other repository

  • Security

    parcadei/Continuous-Claude-v3/.claude/skills/security Skill

    3,950★ repo

    Security audit workflow - vulnerability scan → verification

  • Skill developer

    parcadei/Continuous-Claude-v3/.claude/skills/skill-developer Skill

    3,950★ repo

    Meta-skill for creating and managing Claude Code skills

  • Tdd migrate

    parcadei/Continuous-Claude-v3/.claude/skills/tdd-migrate Skill

    3,950★ repo

    TDD workflow for migrations - orchestrate agents, zero main context growth

    The same file is in 1 other repository

  • Tdd migration pipeline

    parcadei/Continuous-Claude-v3/.claude/skills/tdd-migration-pipeline Skill

    3,950★ repo

    Orchestrator-only workflow for migrating/rewriting codebases with full TDD and agent delegation

    The same file is in 1 other repository

  • Tdd

    parcadei/Continuous-Claude-v3/.claude/skills/tdd Skill

    3,950★ repo

    Test-driven development workflow with philosophy guide - plan → write tests → implement → validate

  • Test

    parcadei/Continuous-Claude-v3/.claude/skills/test Skill

    3,950★ repo

    Comprehensive testing workflow - unit tests ∥ integration tests → E2E tests

  • Validate agent

    parcadei/Continuous-Claude-v3/.claude/skills/validate-agent Skill

    3,950★ repo

    Validation agent that validates plan tech choices against current best practices

    The same file is in 2 other repositories

  • Workflow router

    parcadei/Continuous-Claude-v3/.claude/skills/workflow-router Skill

    3,950★ repo

    Goal-based workflow orchestration - routes tasks to specialist agents based on user goals

    The same file is in 1 other repository

  • Template MCP Server

    microsoft/mcp/com.microsoft/template-server-name MCP server

    3,866★ repo

    Template MCP server example.

  • Architecture patterns

    foryourhealth111-pixel/Vibe-Skills/bundled/skills/architecture-patterns Skill

    3,822★ repo

    Implement 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

  • Chembl database

    foryourhealth111-pixel/Vibe-Skills/bundled/skills/chembl-database Skill

    3,822★ repo

    Query 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.

  • Claude skills

    foryourhealth111-pixel/Vibe-Skills/bundled/skills/claude-skills Skill

    3,822★ repo

    Claude 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