Loading...
Loading...
Found 1,669 Skills
Guides supply chain management—sourcing and supplier qualification, procurement and PO governance, demand forecasting and inventory policy, logistics and fulfillment (3PL, Incoterms, lead times), supplier scorecards, cost and TCO analysis, supply risk and continuity, and SCM KPI dashboards. Use when designing supply strategy, running RFQs, setting safety stock, resolving stockouts or excess inventory, improving OTIF, dual-sourcing critical parts, or building supplier business reviews—not for contract legal redlines (commercial-counsel), vendor security assessments (information-security-engineer), DC construction delivery programs (senior-data-center-capacity-delivery-manager), compute GL and invoice reconciliation (compute-accounting-manager), SaaS quote-to-order (deal-operations-administrator), or enterprise strategy cases (business-consultant).
Compile TensorRT-LLM on a SLURM cluster. Covers submitting a batch job with a container image, monitoring the job, and verifying the build. Use when the user wants to compile TRT-LLM remotely via SLURM rather than on a local compute node.
Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for AD_DUMP_GRAPHS_DIR workflows. Covers TRT-LLM paths, registry, default.yaml registration, graph validation, tests, and a review checklist — without prescribing profiling tools or throughput targets.
Compile TensorRT-LLM on a compute node inside a Docker container. Use this when already on a compute node with GPUs visible.
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-analysis. Triggers: host overhead, inter-step gap, scheduling overhead, forward step isolation, nsys iteration analysis, NVTX breakdown, request management overhead, GPU idle, host bottleneck, host prep exposed, inter-kernel gap, bubble analysis, graph coverage, eager kernel, rank imbalance, straggler detection.
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform the fixed fair SGLang/vLLM/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed framework under the same workload and SLA.
Write, push, run, publish, and manage Kaggle Benchmark tasks using the kaggle CLI and the kaggle-benchmarks Python SDK. Use when the user wants to create or push a benchmark task (optionally with attached Kaggle datasets), run benchmarks against LLM models, check task/run status, stream or fetch execution logs, download results and source notebooks, publish a task to make it public, or troubleshoot benchmark workflows.
Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers. Each area lists sub-skills in a "(dispatcher for: ...)" clause. The LLM reads one area entry and routes to the correct sub-skill. Proven via held-out A/B eval: dispatcher pattern outperforms naive pipe-table compression.
Use when building or editing any AI feature in n8n: AI Agents, Text Classifier, Information Extractor, Sentiment Analysis, Summarization Chain, Basic LLM Chain, embeddings, vector stores, single one-shot LLM calls, or AI media generation (image / audio / video) via the native LangChain provider nodes. Triggers on any `@n8n/n8n-nodes-langchain.*` node, "agent", "chat assistant", "LLM with tools", "tool calling", "fromAi", "system prompt", "memory window", "structured output", "outputParser", "function calling", "RAG", "vector store", "embeddings", "classify with AI", "extract fields with LLM", "sentiment analysis", "summarize with LLM", "single LLM call", chat triggers with files, AI image / video / audio generation, or any multi-turn or one-shot LLM behavior.
Design MCP resources to expose content for LLM consumption. Use when creating static or dynamic resources in xmcp.
PocketFlow framework for building LLM applications with graph-based abstractions, design patterns, and agentic coding workflows
AI and ML expert including PyTorch, LangChain, LLM integration, and scientific computing