xray

语音推理优化参考技巧库。当用户提问与语音推理、语音 AI 性能、实时语音系统延迟、ASR/TTS 优化相关时触发。包含 RTF、流式 pipeline、VAD、量化、模型选型等实战技巧。即使用户只是问"怎么让语音更快"、"TTS 延迟太高怎么办"、"ASR 流式怎么做"也应触发。

SIMD (Single Instruction Multiple Data) 优化技巧知识库，蒸馏自 Daniel Lemire 博客（lemire.me/blog） 的数百篇性能工程文章与研究论文。覆盖 x86 (SSE/AVX2/AVX-512) 和 ARM (NEON/SVE2) 的实战优化 模式、代码范例与性能直觉。当用户提问涉及 SIMD 向量化、性能优化、数据并行、字节解析、 JSON/文本/UTF-8/base64 加速、位图操作、整数压缩、prefix sum、字符串扫描、 类型转换加速时触发。也适用于"为什么我的循环慢"、"如何用 intrinsic 优化"、"AVX vs NEON" 等问题。只要涉及批量数据处理性能就应优先查阅本 skill。

使用 Nsight Compute 对 CUDA kernel 进行性能分析和优化的完整指南。 当用户提到 CUDA 性能分析、kernel 调优、ncu 命令、profiler 数据解读、 瓶颈诊断、SOL 指标、占用率分析、DRAM Throughput、L1/L2 Cache Throughput、 Compute Throughput、Roofline 图、Warp Stall、Memory Chart、Section Sets、 Scheduler Statistics、Warp State、Branch Divergence、Register Spilling 等话题时， 主动使用此 skill。也适用于用户粘贴 ncu 输出数据需要解读的场景。 资料来源：NVIDIA 官方文档 2026.1、Kernel Profiling Guide、NERSC Roofline 文档。

Expert-level knowledge about AI/ML knowledge distillation — a training paradigm where a student model learns from a teacher model. Use this skill whenever the user asks about knowledge distillation, teacher-student learning, model compression via distillation, soft targets, KD loss, on-policy distillation, off-policy distillation, self-distillation, multi-teacher distillation, sequence-level KD, GKD (Generalized Knowledge Distillation), OPD (On-Policy Distillation), MOPD (Multi-Teacher On-Policy Distillation), OPSD (On-Policy Self-Distillation), DistilBERT, soft labels, temperature scaling, KL divergence in distillation, or any RL–distillation hybrid method. Also trigger when asked about compressing large LLMs into smaller ones, transferring capabilities from frontier models, exposure bias in autoregressive models fixed via student rollouts, or synthetic data pipelines for model training.

GPU 术语速查手册，基于 Modal GPU Glossary（CC BY 4.0）。当用户提问涉及 GPU 硬件结构、CUDA 编程模型、GPU 性能分析、内核优化、内存带宽、屋顶线模型、 SM 占用率、Warp 分化、算术强度等概念时触发。也适用于"为什么我的 kernel 慢"、 "compute-bound 和 memory-bound 怎么区分"等实际调优问题。

Analyze a software codebase for algorithmic complexity and performance hotspots, then propose or implement safe optimizations without breaking behavior. Use when Codex is asked to scan many files, find inefficient loops, nested iteration, repeated scans, costly rendering/recomputation, N+1 queries, avoidable O(n^2) or O(n) operations, or reduce complexity such as O(n^2) to O(n log n) / O(n), while preserving tests, APIs, outputs, and maintainability.

Teach the user a new skill or concept, within this workspace.

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, or make a codebase more testable and AI-navigable.

每日自动化阅读 Feedly Today 文章、标记已读、生成中文总结报告。当用户说"打开 Feedly 看新闻"、"帮我看今天的 Feedly"、"获取 Feedly 文章"、"标记 Feedly 已读"、"生成今日阅读报告"、"总结今天的技术新闻"时使用此 skill。

Deploys TCP Trojan proxy nodes on Xray-core with certbot Let's Encrypt or self-signed EC P-256 + SHA-256 certificate fingerprint pinning, TCP Fast Open kernel tuning with BBR, nginx-compatible fallback site, gRPC user sync (not HTTP auth callback), and systemd hardening with strict filesystem isolation. Use when deploying a Trojan node on Xray, pinning a self-signed cert fingerprint, configuring TCP Fast Open, or setting up the Xray gRPC stats API. Not for Hysteria2 — see deploying-hy2-nodes.

X-ray any AI model's behavioral patterns — refusal boundaries, hallucination tendencies, reasoning style, formatting defaults. No API key needed.

Senior engineer CLI expertise for AI agents — workflows, safety guardrails, gotchas, and anti-patterns across cloud, IaC, containers, databases, dev tools, and platforms