NVIDIA/TileGym/cutile-autotuning A Agent Skill Active
Use when adding, modifying, optimizing, or debugging CuTile autotuning code.
Browse SKILL.md-based agent skills for Claude Code, Codex, Cursor, Gemini CLI and more.
Use when adding, modifying, optimizing, or debugging CuTile autotuning code.
Expert cuTile programming assistant.
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning.
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' in...
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI).
Install cuOpt for Python, C, or as a server (pip, conda, Docker) — system requirements, install commands, and verification.
LP, MILP, and QP (beta) with cuOpt — C API only.
LP, MILP, and QP (beta) with cuOpt — CLI only (MPS files, cuopt_cli).
Solve Linear Programming (LP), Mixed-Integer Linear Programming (MILP), and Quadratic Programming (QP, beta) with the Python API.
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only.
cuOpt REST server — start server, endpoints, Python/curl client examples.
cuOpt REST server — what it does and how requests flow.
Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server).
Numerical optimization (LP, MILP, QP) — concepts, problem-text parsing, and formulation patterns.
Vehicle routing (VRP, TSP, PDP) — problem types and data requirements.
After solving a non-trivial problem, detect generalizable learnings and propose skill updates so future interactions benefit automatically.
NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API.
Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engi...
Deploy Nemotron Voice Agent on Workstation (x86), Jetson Thor, or Cloud NIMs.
"NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage.
Manage and monitor VSS alerts after the alerts profile is deployed.
Deploy, debug, or tear down any VSS profile using a compose-centric workflow — config (dry-run) with env overrides, review resolved compose, then compose up.
Produce video analysis reports by discovering the deployed VSS agent, querying POST /generate for a timestamped captioned summary of the clip, then formatting the agent reply as th...
Use this skill when working with the RTVI VLM or RT-VLM microservice API on VSS 3.1.
Query video analytics data and metrics from Elastic search via the VA-MCP server (port 9901).
Search video archives using natural language — find events, objects, actions, and people across recorded video using fusion search (Cosmos Embed1 semantic search + CV attribute sea...
Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly.
Call the vss agent to run video understanding on video to answer a text question.
Query VIOS REST APIs: sensor list, recording timelines, video clip extraction, snapshot capture, add/delete sensors and streams
Generate video summary reports using the VSS video_search_frag extension with Long Video Summarization (LVS), Enterprise RAG knowledge retrieval, and human-in-the-loop parameter co...
A skills governed plug-and-play harness for staged, test-driven skill orchestration
69 marketing skills across SEO/GEO, influencer, paid ads, and email on one shared contract, with 5 benchmark-driven auditor gates (CORE-EEAT, CITE, C³, ROAS, SEND) and keyless data connectors
Prompt for clarification on ambiguous requirements
Deep architectural context via ultra-granular code analysis
Smart contract security toolkit with vulnerability scanners for 6 blockchains
Search and extract data from Burp Suite project files
Diagnose and fix Claude in Chrome MCP extension connectivity issues
Detect compiler-induced timing side-channels in crypto code
Index and search culture documentation
Security-focused diff review with git history analysis
DWARF debugging format expertise
Identify state-changing entry points in smart contracts
Scan Android APKs for Firebase misconfigurations and security vulnerabilities
Detect insecure default configurations like hardcoded secrets, default credentials, and weak crypto
Modern Python tooling with uv, ruff, ty, and pytest best practices
Property-based testing for multiple languages and smart contracts
Create and refine Semgrep rules for vulnerability detection
Port existing Semgrep rules to new target languages with test-driven validation