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…
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…
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…
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 /…
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.…
Skill Claude CodeCodex
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec), and data load time. (2) Standalone kernel/op — write CUDA event timing code with warmup, per-iteration statistics, and anti-pattern avoidance. Also covers NVTX…
Skill Claude CodeCodex
Benchmark an ingress-layer hot/cold pool separation scheme for LLM serving against a unified cache-aware baseline, and (optionally) reproduce it on real Kubernetes via kind. Use when the user asks to "测冷热分离"/"ingress split benchmark"/"分离 vs 统一哪个 QPS 高"/"扫冷热配比"/"pp separation"/"验证 ingress-nginx 冷热分流"/"在 kind 上跑真 vLLM…
Skill Claude CodeCodex
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
Skill Claude CodeCodex
Build throwaway prototypes to validate a design before production code. Terminal state-machine for routing/cache/overload logic, or UI variants on one route. Use when prototyping, sanity-checking a state model, exploring routing policies, or saying "prototype this" / "let me play with it".
Skill Claude CodeCodex
Two-axis branch review — Standards (CONTRIBUTING.md, CONTEXT, ADRs) and Spec (issue/PRD/plan). Runs parallel sub-agents on git diff. Use before PR, when reviewing a branch, or after implementing routing/benchmark/harness changes.
Skill Claude CodeCodex
Research-before-coding workflow. Search the repo, framework APIs, libraries, and existing patterns before writing custom code. Use when adding a feature to a mature framework (vLLM, SGLang, TRT-LLM, benchmark harness), before creating a utility/helper, or when the user asks to "add X functionality".
Skill Claude CodeCodex
Scaffold docs/agents/ in a target repo — issue tracker (GitHub/GitLab/local), triage labels, domain doc layout. Run once per repo before to-issues, review, or other skills that read docs/agents/issue-tracker.md.
Skill Claude CodeCodex
Simplify and refine recently changed code for clarity, reuse, and efficiency while preserving behavior. Use before opening a PR, after implementing a feature in a mature framework, or when asked to clean up a branch diff.
Skill Claude CodeCodex
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, asks for test-first development, or writes tests for benchmark harnesses, profiling scripts, or inference automation.
Skill Claude CodeCodex
Break a plan, spec, or PRD into independently-grabbable GitHub issues using tracer-bullet vertical slices. Use when converting a plan into issues, splitting a benchmark study / routing feature / multi-PR infra work into tickets, or preparing AFK-agent-ready tasks.
Skill Claude CodeCodex
Before claiming work is complete, fixed, or passing — run verification commands and cite evidence. Use before commit/PR, after implementing features or benchmark fixes, when saying tests pass or bug is fixed.
Skill Claude CodeCodex
Write bite-sized implementation plans from an approved spec. Use after brainstorming or grill-with-docs, before touching code on multi-step features in mature codebases (vLLM, SGLang, inference harness, serving stack patches).