Saddss/cursor-skills

Saddss/cursor-skills

Skill Claude CodeCodex

A workflow for creating, revising, and checking publication-ready figures for papers, theses, and technical reports.

Saddss/cursor-skills

Skill Claude CodeCodex

Use before any creative work — adding features, modifying behavior, or extending a mature framework (vLLM, SGLang, TRT-LLM, benchmark harness). Explores intent, constraints, and design; requires user approval before code.

Saddss/cursor-skills

Skill Claude CodeCodex

Launch multiple explore subagents in parallel to investigate architecture, data models, APIs, and deployment; synthesize an onboarding document. Use when first entering an inference framework repo, benchmark harness, or unfamiliar serving stack.

Saddss/cursor-skills

Skill Claude CodeCodex

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, describes a performance regression, or debugs vLLM / SGLang /…

Saddss/cursor-skills

Skill Claude CodeCodex

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…

Saddss/cursor-skills

Skill Claude CodeCodex

Execute a written implementation plan task-by-task with verification checkpoints. Use after writing-plans when implementing multi-step features in mature frameworks; stop when blocked instead of guessing.

Saddss/cursor-skills

Skill Claude CodeCodex

Grilling session that challenges a plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against project language and documented decisions, or before major inference-stack or benchmark…

Saddss/cursor-skills

Skill Claude CodeCodex

Compact the current conversation into a handoff document for another agent to pick up. Use when ending a long session, switching agents, or handing off benchmark runs, profiling investigations, or multi-step infra work.

Saddss/cursor-skills

Skill Claude CodeCodex

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, make a codebase more testable and AI-navigable, or untangle inference engine /…

Saddss/cursor-skills

Skill Claude CodeCodex

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Saddss/cursor-skills

Skill Claude CodeCodex

OpenAI Triton (@triton.jit) kernel development for inference/training ops. NEVER use for CUDA C++, TileIR, or profiling tools (ncu, nsys). Covers fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify. Use when implementing…

Saddss/cursor-skills

Skill Claude CodeCodex

Layer-level torch profiler trace analysis: forward-pass boundaries, anchor kernels, per-layer timing clusters, Perfetto navigation. Use when llm-torch-profiler-analysis three-table summary is too coarse and you need which layers or prefill/decode forward passes dominate.

Saddss/cursor-skills

Skill Claude CodeCodex

Framework-independent LLM serving benchmark for SGLang, vLLM, TensorRT-LLM. Config-driven searchspace over launch flags under shared workload, GPU budget, and latency SLA. Use for cross-framework deployment comparison, cookbook sweeps, or finding best serve command before QPS binary search. Pairs with…

Saddss/cursor-skills

Skill Claude CodeCodex

Parse SGLang/vLLM startup logs for GPU memory decomposition (weights, KV pool, CUDA graph, overhead) and max-concurrency estimates. Use for KV cache budget, mem-fraction-static tuning, OOM triage, or explaining why concurrency is capped.

Saddss/cursor-skills

Skill Claude CodeCodex

Unified torch.profiler triage for sglang, vllm, TensorRT-LLM: kernel table, overlap-opportunity table, fuse-pattern table with prefill/decode separation. Use when analyzing trace.json(.gz), live server profiling, or fusion/kernel opportunities after perf-nsight-systems points to compute. Complements…

Saddss/cursor-skills

Skill Claude CodeCodex

Find the maximum sustainable QPS of an LLM inference service that meets a p50 e2e latency SLO using onlinereplay.py and a binary search. Use for maximum-QPS benchmarks, SLO-based performance tests, and optional serving configuration or feature tuning on local OpenAI-compatible servers.

Saddss/cursor-skills

Skill Claude CodeCodex

Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Use when onboarding onto a new project, understanding architecture, investigating cross-cutting concerns, or mapping vLLM / SGLang / TRT-LLM / FlexKV code paths.

Saddss/cursor-skills

Skill Claude CodeCodex

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…

Saddss/cursor-skills

Skill Claude CodeCodex

Performance analysis coordination workflow. Guides profiling delegation, bottleneck classification (compute / memory / launch / communication / sync), and structured report generation. Use when the user asks to analyze performance, profile a workload, check MFU / SOL, diagnose bottlenecks, understand why a vLLM /…

Saddss/cursor-skills

Skill Claude CodeCodex

Analyze host/CPU overhead in LLM inference (vLLM / SGLang / TRT-LLM serve / lmdeploy / TensorRT-LLM) from nsys traces. Phase 1 (Detection): determine whether host overhead is the bottleneck via a binary YES/NO verdict with metric evidence (GPU idle ratio, host prep exposed ratio, per-phase breakdown). Phase 2 (Root…

Saddss/cursor-skills

Skill Claude CodeCodex

Profiles and optimizes LLM inference host / CPU overhead (vLLM / SGLang / TRT-LLM serve / lmdeploy / TensorRT-LLM PyExecutor) using lineprofiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low, when perf-host-analysis has concluded "host-bound", or…

Saddss/cursor-skills

Skill Claude CodeCodex

Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp stall analysis, metric interpretation, and programmatic .ncu-rep report analysis. Use when optimizing CUDA kernels in vLLM / SGLang / TRT-LLM / custom inference…

Saddss/cursor-skills

Skill Claude CodeCodex

Nsight Systems (nsys) CLI for system-level timeline profiling. Use when the user wants to run nsys profile, analyze .nsys-rep reports, use nsys stats/analyze/recipe commands, diagnose GPU idle time from timeline traces, profile distributed training with NCCL overlap analysis, or profile an LLM inference server (vLLM /…

Saddss/cursor-skills

Skill Claude CodeCodex

Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection, prioritization criteria, and safe modification workflow. Use when applying optimizations, writing kernels, or improving vLLM / SGLang / TRT-LLM / lmdeploy performance.…