为 Python+CUDA 应用（如 NVDEC）提供 SOLID CUDA 13 / GPU 流水线护栏：在边界处使用具体类型、小模块、显式设备/资源生命周期，无静默 Any 泄漏。适用于编辑 CUDA 13、PyNvCodec、GPU 解码/推理代码时。
该技能为使用 CUDA 13 进行 GPU 编程的开发者提供一套强制性的编码规范与最佳实践，尤其适用于涉及 PyNvCodec、GPU 解码与推理的 Python+CUDA 应用。其核心目标是通过在公共 API 边界处强制使用具体类型替代 `Any`，减少类型泄漏；通过将 SDK 对象封装在窄适配器后面，降低对第三方库的直接依赖；并通过清晰的命名（如 `surface`、`decoder`、`stream`）和文档化设备所有权，使资源生命周期管理变得明确。该技能还强调可靠性，要求将流重连和解码器重置作为一等路径处理，使用显式错误而非静默吞异常的方式报告 CUDA 初始化失败，并保持 CPU 编排层薄而轻。最终，该技能帮助开发者构建更可靠、更易于维护的 GPU 管道代码。
npx skills add https://github.com/Nutz95/CursorCodingSkills/tree/HEAD/skills/solid-cuda-13Installed? Explore more 编程与开发 skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Anysurface、decoder、stream）Any 而没有类型包装计划This repo contains 3 individual skills — each has its own dedicated page.
>- SOLID Batch (.bat/.cmd) guardrails: thin wrappers around PowerShell/Python, setlocal, explicit errorlevel checks, no secrets. Use when editing Windows launchers or portable package entrypoints.
>- SOLID C++ / ESP32 firmware guardrails: file/class size, no nested classes, strict DI at composition roots, no UNIT_TEST / test ifdefs in production headers (and avoid them in .cpp), no hardcoded secrets, one type per public header, public API /// comments, dual-core radio pinning (PRO_CPU 0 / APP_CPU 1), FreeRTOS-safe patterns. Use when editing ESP-IDF, Arduino-ESP32, PlatformIO firmware, or ESP-NOW / BLE / Wi-Fi tasks.
>- SOLID Docker/Compose guardrails: small Dockerfiles, non-root when practical, no secrets in images, pinned base tags, clear multi-stage builds. Use when editing Dockerfile or compose files.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.