AI & LLM Engineering · Linux · For developers

Builds ONNX Runtime from source with its build scripts, explaining the update, build and test phases, key flags and where the build output lands.

microsoft/onnxruntime

Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.

stas00/the-art-of-debugging

ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring…

yoloshii/ClawMem

Inspects and tunes the shared-vs-dedicated memory split on AMD Ryzen APUs with unified memory (UMA) so larger LLMs and image-gen models fit on the iGPU, or so reserved GPU memory is returned to the…

amd/skills

This skill should be used when the user wants to set up, install, deploy, bootstrap, or "spin up" the Build-an-Agent workshop (a.k.a.

brevdev/workshop-build-an-agent

把一段中文（或任意 Whisper 支持语言）的会议/面试录音用本地 Whisper large-v3 转成文本，再清洗成带说话人标签、修过 ASR 错字、分好章节的 markdown 文档（可选再转成 docx）。跨平台（macOS Apple Silicon 用 mlx-whisper，Windows/Linux/Intel Mac 用…

xiaopengde/murmur

Google Coral Edge TPU — real-time object detection natively (macOS / Linux)

SharpAI/DeepCamera

把本地长视频/音频转写成文字稿 + 可选字幕，纯本地（不上传云端），用 sherpa-onnx X-ASR Zipformer transducer 模型（int8 量化、中英双语、自动标点）。已在 macOS Apple Silicon（int8 + AMX，~100× 实时）、Linux ARM64（CPU，~32× 实时）与 Windows（PowerShell…

ysyecust/lecture-to-notes

Shows how to build and run ONNX Runtime WebGPU provider tests on Linux with no GPU, using the Mesa lavapipe software Vulkan adapter, and where that approach falls short.

microsoft/onnxruntime

Step-by-step playbook for migrating a pytorch/pytorch .github/workflows/.yml from EC2 to OSDC (ARC) runners — covers both dial-up and 100% opt-in patterns, with the inputs that must be plumbed…

pytorch/test-infra

A template skill demonstrating the PAI SKILL.md format. An agent skill from nirholas/PAI.

nirholas/PAI

Run and operate SubZeroClaw — the ~550-line C agentic daemon (skill.md + LLM + shell + loop).

genlayerlabs/subzeroclaw

Summarize a document at a requested length. An agent skill from nirholas/PAI.

nirholas/PAI

Build, debug, extend, localize, or publish the automated tutorial videos — the workbench that drives the real Linux app under Xvfb (virtual mic, live Voxtral transcription, task-agent proposals)…

matthiasn/lotti

A step-by-step workflow for pointing the OpenAI Codex CLI at an OmniRoute gateway on Linux, macOS or Windows, plus settings that keep multi-hour sessions alive.

diegosouzapw/OmniRoute

Index of all PAI skills.

nirholas/PAI

Pin (or re-pin) the Linux manywheel builder docker images used by the nightly/release binary build workflows in pytorch/pytorch to a fixed .ci/docker build.

pytorch/test-infra

Install Triton + SageAttention to accelerate ComfyUI (the sageattn attentionmode and inductor torch.compile used by WanVideoWrapper / many video graphs).

artokun/comfyui-mcp

XMake build configuration, options, commands, and patterns for LuisaCompute.

LuisaGroup/LuisaCompute

Builds Agent2Agent (A2A) servers and clients, the open protocol (originally from Google, now under the Linux Foundation) that lets AI agents from different frameworks call each other.

TerminalSkills/skills

Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.

NVIDIA/skills

GenieAPIService technical documentation retrieval. An agent skill from qualcomm/qai-appbuilder.

qualcomm/qai-appbuilder

A skill your agent uses to lock/cap Jetson CPU/GPU/EMC clocks, toggle EMC/CPU DVFS, or change cpufreq governors by editing BPMP DTB and nvpower.sh pre-flash.

NVIDIA/skills

A skill your agent uses to promote overlay files and built artifacts into the staged BSP image.

NVIDIA/skills

Serve a Hugging Face model with SGLang on a Linux machine with an NVIDIA or AMD GPU, configured from the model's SGLang cookbook page — or, when it has none, from the model's own files — and join it…

autonomous-ai/openharness

Serve a Hugging Face model with vLLM on a Linux machine with an NVIDIA or AMD GPU, configured from the model's official vLLM recipe — or, when it has none, from the model's own files — and join it…

autonomous-ai/openharness

QAI AppBuilder technical documentation retrieval. An agent skill from qualcomm/qai-appbuilder.

qualcomm/qai-appbuilder

Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment.

NVIDIA/skills

Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, publicsources, x-tools, guides) for the active target.

NVIDIA/skills

A skill your agent uses when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a LinuxforTegra root on the host PC.

NVIDIA/skills

Set up the BSP source workspace: LinuxforTegra overlay tracker, bspsources, Crosstool-NG toolchain.

NVIDIA/skills

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs.

jeremylongshore/tons-of-skills-marketplace

Extract Jetson Linux + sample-rootfs tarballs and run applybinaries.sh for the active target, then record bspimage in the profile.

NVIDIA/skills

能完成昇腾NPU驱动和固件安装部署，实现安装包正则匹配提取、按需添加可执行权限、Python+Shell双重包校验、系统依赖先验后装、适配CentOS/RHEL/Ubuntu/Debian系统，适用于昇腾NPU驱动和固件安装部署。

ascend-ai-coding/awesome-ascend-skills

AI 模型文件逆向与静态分析：ONNX/PyTorch/Safetensors/TFLite 格式解析、 网络结构还原、权重提取、文件级水印分析（权重 pattern/metadata/tensor hash/embedding 异常）。

dslsdzc/rev-skills

Guidance for Microsoft Defender for Endpoint (MDE) — enterprise endpoint security with next-gen AV, EDR, attack surface reduction (ASR), Defender Vulnerability Management, automated investigation…

vinayaklatthe/microsoft-security-skills