“performance”

Subagent "performance-analyzer" from nrwl/nx: Use this agent during PR review to analyze the runtime performance of a PR's changes along two axes - (1)…

Subagent "perf-profiling-specialist" from NVIDIA/TensorRT-LLM: Expert in GPU performance profiling for TRT-LLM workloads with nvidia-smi, Nsight Systems (nsys…

Subagent "perf-test-sync" from NVIDIA/TensorRT-LLM: Use this agent when the user needs to synchronize performance test cases between development (dev) and QA…

Subagent "qa-testing-feature" from streamlit/streamlit: Performs QA testing on the feature implemented in the current branch.

Subagent "code-reviewer" from anthropics/claude-cookbooks: Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter…

Subagent "frontend-developer" from davila7/claude-code-templates: Frontend development specialist for React applications and responsive design.

Subagent "code-reviewer" from borghei/Claude-Skills: Reviews code for quality, security, performance, and best practices.

Subagent "qa-engineer" from borghei/Claude-Skills: Performs quality assurance analysis on code including test coverage assessment, test generation, bug…

Subagent "security-auditor" from borghei/Claude-Skills: Performs comprehensive security audits on code and configuration.

Subagent "reviewing-local-changes" from streamlit/streamlit: Review the current branch's changes for code quality, test coverage, security, best practices…

Subagent "handsontable-reviewer" from handsontable/handsontable: Comprehensive code review agent combining quality, architecture, performance/a11y, and test…

Subagent "systematic-debugger" from PostHog/posthog: Use this agent when you need to diagnose and fix bugs, errors, or unexpected behavior in code.

Subagent "design-reviewer" from MemTensor/MemOS: Design-review sub-agent.

Subagent "kernel-cute-specialist" from NVIDIA/TensorRT-LLM: Expert in writing optimized GPU kernels using CuTe DSL for NVIDIA GPUs (Ampere through Blackwell).

Subagent "perf-torch-cuda-graph-specialist" from NVIDIA/TensorRT-LLM: Expert in CUDA Graph capture, replay, and optimization for PyTorch.

Subagent "kernel-triton-specialist" from NVIDIA/TensorRT-LLM: Expert in writing optimized Triton kernels for PyTorch operators.