Trouvez la capacité idéale pour votre agent.
List installed skills, search the skill registry, install new skills, and manage workspace extensions. Use when the user asks to find, install, list, or configure skills, or mentions skill registry, extensions, or workspace capabilities.
Search and discover academic papers from arXiv and web sources using arxiv_to_prompt and web search. Use when the user asks to find research papers, search arXiv, look up scientific literature, do a literature review, or needs academic references.
Conduct thorough academic peer reviews with structured feedback using load_pdf and arxiv_to_prompt. Use when the user asks to review a paper, provide manuscript feedback, critique research, or write a referee report.
Load, analyze, and visualize datasets using pandas with AG Grid display. Use when the user asks to analyze CSV data, explore a dataframe, create charts, filter tabular data, or display spreadsheet-like results.
Verify proofs, check theorem correctness, and solve satisfiability problems using Lean 4, Coq, and Z3 SMT solver. Use when the user asks to prove theorems, verify mathematical proofs, check logical satisfiability, or work with proof assistants.
Construct and verify mathematical proofs using LaTeX typesetting and computational verification via jupyter_execute. Use when the user asks to prove a theorem, verify a mathematical argument, construct a formal proof, or check proof correctness computationally.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
Install cuOpt for Python — pip, conda, Docker, verification. Use when the user is installing or verifying the Python API. Standalone; no common skill.
Guide for setup arXiv paper search MCP server using Docker MCP
Write integration tests using TestContainers for .NET with xUnit. Covers infrastructure testing with real databases, message queues, and caches in Docker containers instead of mocks.
Cloud GPU processing via RunPod serverless. Use when setting up RunPod endpoints, deploying Docker images, managing GPU resources, troubleshooting endpoint issues, or understanding costs. Covers all 5 toolkit images (qwen-edit, realesrgan, propainter, sadtalker, qwen3-tts).
Explain and validate local setup paths for this repo with Docker and without Docker. Use when developers need exact prerequisites, startup commands, health checks, and troubleshooting steps.
Explain and validate local setup paths for this repository with Docker and without Docker. Use when developers need exact prerequisites, startup commands, health checks, and troubleshooting.
Build MCP servers in Python with FastMCP. Workflow: define tools and resources, build server, test locally, deploy to FastMCP Cloud or Docker. Use when creating MCP servers, exposing tools/resources/prompts to LLMs, building Claude integrations, or troubleshooting FastMCP module-level server, storage, lifespan, middleware, OAuth, or deployment errors.
Install and configure NVIDIA NemoClaw (sandboxed OpenClaw agent platform) on Linux. Handles cloudflared tunnels, Docker cgroup fixes, OpenShell, sandbox creation, remote access via Cloudflare Tunnel, and known bug workarounds. Triggers: "install nemoclaw", "setup nemoclaw", "nvidia nemoclaw", "openclaw setup", "nemoclaw on spark", "nemoclaw on dgx".
Deploy Langfuse with your application across different platforms. Use when deploying Langfuse to Vercel, AWS, GCP, or Docker, or integrating Langfuse into your deployment pipeline. Trigger with phrases like "deploy langfuse", "langfuse Vercel", "langfuse AWS", "langfuse Docker", "langfuse production deploy".
Deploy Documenso integrations across different platforms and environments. Use when deploying to cloud platforms, containerizing applications, or setting up infrastructure for Documenso integrations. Trigger with phrases like "deploy documenso", "documenso docker", "documenso kubernetes", "documenso cloud deployment".
Generate intelligent GitHub release notes with AI-powered analysis. Use this skill when you need to create a release, the user mentions release creation, or asks to publish a new version. Automatically analyzes commits since the last release, identifies key changes, acknowledges contributors, and includes Docker image references for both Docker Hub and Aliyun ACR.
