Explore

Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI. Do NOT use for UPHY lane allocation or ODMDATA edits.

in the skill textfrom the user when the sensor is custom. 4. **Kernel-DT overlay** — cpp-expand the in-tree DTSI, extract its `fragment@N` body, append into the

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices.

in the skill textuse these first) 1. **Prebuilt containers (GHCR)** — NVIDIA-AI-IOT packages : `llama_cpp`, `ollama`, `live-vlm-webui`, older-Orin `vllm`, and related images built for Jetson

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Visualize, query, and stream to train on multimodal robotics data.

Skill·Apache-2.0·★ 12k·No key

Embedded C/C++ AI engineering plugin — firmware skills (FreeRTOS, Keil, HardFault, state machines) + 1% Rule / Plan Verification Gate discipline | 嵌入式 C/C++ 工程 AI 插件:固件技能与 agent 纪律。 For Claude Code, C

in the skill textmdk-build` | UV4 CLI、ARM Compiler 5/6、.map 分析、合并打包、构建诊断 | | `c-cpp-dev` | C/C++ 代码生成、风格、内存布局、重构 | | `state-machine-design` | 状态模型、重试、超时、转换门控

Skill·MIT·★ 19·No key

On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

in the skill textperformance):** - llama.cpp (`llama-server`) — for dedicated GPU inference. Without it, `node-llama-cpp` runs models in-process (auto-downloads on first use). GPU servers give better

Skill·MIT·★ 210·No key

Claude Code plugin: extract scene-change frames + audio transcript from any video so Claude can 'watch' it.

in the skill textvideo-context-marketplace /video-context:setup ``` `/video-context:setup` installs ffmpeg, yt-dlp, whisper-cpp, and the whisper model. Skip it if you want — `extract.sh` auto-installs the

Skill·MIT·★ 3·Few stars·No key

Production-ready Claude Code skills for Unreal Engine 5, llama.cpp, and OpenCode CLI integration. Built by maystudios.

in the skill textCodex, Gemini, or local models for implementation, review, and debugging | | ** llama-cpp ** | Complete llama.cpp guide — C API, GGUF, quantization, GPU backends, HTTP server, grammar constraints, UE5

Skill·MIT·★ 25·No key

A Claude skill that turns Claude into your personal financial planner — built specifically for Canadians. Interviews, budgets, action plans, interactive dashboards, and ongoing coaching.

in the skill textdashboard** with charts for net worth, debt payoff, retirement projections, RESP tracking, CPP comparison, investment growth comparison, and more - **Investment education** — popular Canadian ETFs, GICs, and

Skill·MIT·★ 63·No key

Claude Code plugin marketplace — Rust, ESP32 C++, Python backend, SwiftUI, dead code detection

in the skill textexpert` | 0 | SwiftUI-specific state, lifecycle, platform, accessibility, and architecture judgment | | ** esp32-cpp ** | `esp32-expert` | 0 | ESP32 hardware, FreeRTOS, memory, peripheral, and field-failure judgment | | ** backend

Skill·MIT·★ 11·No key

A curated collection of reusable agent skills for design, research, browser automation, and developer tooling.

Skill·Link only·★ 13

C++ Template Repository with Conan2 and Premake5 (Windows, Linux and MacOS)

Skill·Link only·★ 23

Claude Code skill that turns any website URL into a 30s cinematic marketing video — drone tour, voice off, word-synced subtitles, square/vertical/horizontal. HTML + Python + FFmpeg.

Skill·MIT·★ 3·Few stars·No key

Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.

in the skill textdir: `install-cu - /`. ## Step 4: Run Tests Run the following tests * EXAMPLE_CPP_HELLO_WORLD_TEST * EXAMPLE_PYTHON_HELLO_WORLD_TEST * EXAMPLE_CPP_TENSOR_INTEROP_TEST

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

in the skill textand explicitly mention the GGUF / 4-bit tradeoff when it selects `llama-cpp`. - For SGLang prompts, run with `--runtime sglang` and quote `--mem-fraction-static`, `--max

Official·Skill·Apache-2.0·★ 3.6k in collection·No key

Turn a video — or an animated GIF, APNG, or WebP — into a timeline of still frames so an LLM can "watch" it as a series of images.

in the skill textthe result back on the same payload: | Provider | Install / key | CLI | | :------- | :------------ | :-- | | `whisper-cpp` (default when on PATH) | `brew install whisper-cpp` (macOS) · `scoop install whisper-cpp

Skill·MIT·★ 68·No key

Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON

in the skill texteffort | Requires Calibre `ebook-convert` | | Audio (`.mp3`, `.wav`, etc.) | optional | Local `whisper-cpp` or `whisper`, optional OpenRouter fallback | | Video (`.mp4`, `.mov`, etc.) | optional | Requires `ffmpeg` plus

Skill·MIT·★ 49·No key

Claude Code skill: summarize videos, audio & podcasts with local cached transcription

in the skill textwhisper` | `large-v3-turbo` | | whisper.cpp | CPU, no Python deps | `brew install whisper-cpp` + set `AUDIO_TLDR_WHISPER_CPP_MODEL` | (your model file) | | openai-whisper | Original CLI

Skill·MIT·★ 39·No key

Cross-file drift checker. Keeps code, configs, and docs in sync deterministically. Supports 35+ languages.

in the skill textthe repository root: ```toml ignore = ['**/generated/**'] disable = ['check-ai'] [extensions] ino = 'cpp' ``` The config file can also declare blocks instead of comment tags: around a key

Skill·MIT·★ 29·No key