Results for “gpi”

Use this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without host CPU mediation. Covers picking GPI vs doca-gpunetio, the doca_gpi / domain / channel object model, the GPU-side handle handoff (doca_gpu_gpi_channel*), attaching GPU memory to a GPI domain, the domain and channel attribute objects, and debugging DOCA_ERROR_* from doca_gpi_* calls. Trigger even when the user does not explicitly mention "DOCA GPI" — implicit phrasings include "my CUDA kernel needs to post RDMA directly from GPU memory", "DOCA_ERROR_* from doca_gpi_gpu_channel_get", "how do I hand a GPU handle to my CUDA kernel", "how many channels can a GPI domain hold", or "GPU kernel driving RDMA without the host CPU on the path". Refuse and route elsewhere for the doca-gpunetio Send/Receive surface, the doca-rdma queue lifecycle, DPA-side initiation (doca-rdmi), or the CUDA programming model — those belong to other skills.

The English summary is being prepared. Showing the original description.

Automate Bigpicture IO operations through Rube MCP, a connection for agent tools. The skill discovers available actions and their required inputs, checks the service connection, and runs the selected tools.

• Find tools for a Bigpicture IO task
• Run multiple supported operations in bulk
• Retrieve all pages of a tool response

Automate Bigpicture IO operations through Rube MCP, a connection for agent tools. The skill discovers available actions and their required inputs, checks the service connection, and runs the selected tools.

• Find tools for a Bigpicture IO task
• Run multiple supported operations in bulk
• Retrieve all pages of a tool response

Firmware development for the 30-pin NodeMCU ESP8266 devkit — NodeMCU DevKit V1.0 / Amica (CP2102) and LoLin NodeMCU V3 (CH340G), built on the Ai-Thinker ESP-12E or ESP-12F module (ESP8266EX, 4 MB flash), with PlatformIO and the Arduino ESP8266 core (`board = nodemcuv2`). Use when working on a NodeMCU, ESP-12E, ESP-12F or ESP8266 devkit: project setup, platformio.ini, the D0-D10 vs GPIO numbering, which pins are safe and which break the boot, GPIO15/GPIO0/GPIO2 strapping, the A0 divider and 1 V ADC, software I2C and software PWM, analogWrite range, LittleFS and flash layouts, OTA, deep sleep and the missing GPIO16-to-RST link, Wi-Fi, heap exhaustion, watchdog and Soft WDT resets, exception decoding, flashing over CP2102/CH340, or debugging why the board does not boot, prints garbage, or reboots by itself.

The English summary is being prepared. Showing the original description.

Firmware development for the 36-pin ESP32-WROOM-32 development board — the original DOIT ESP32 DevKit V1 with 18 pins per side, i.e. the 30-pin layout plus the six in-package flash pins (SD0 SD1 SD2 SD3 CMD CLK = GPIO6-11) broken out at the USB end, CH340G or CP2102 bridge, AMS1117 LDO, user LED on GPIO2, GPIO0 not on the header. Use when working on a 36-pin ESP32 devkit (ESP32-D0WDQ6 / ESP32-D0WD-V3, ESP-WROOM-32 module), or when identifying which ESP32 board size you have: project setup, platformio.ini and sdkconfig for ESP-IDF or Arduino, pin mapping and which GPIOs are safe, the flash-pin trap, strapping pins, ADC1 vs ADC2 with Wi-Fi, SPI speed and IO_MUX pins, deep sleep and RTC wake pins, flashing, BOOT/EN recovery, brownouts, or debugging why something on the board does not work.

The English summary is being prepared. Showing the original description.

Firmware development for the 38-pin ESP32-WROOM-32 development board — Espressif ESP32-DevKitC V4, Ai-Thinker NodeMCU-32S, DOIT ESP32 DevKit V1 38-pin and their CH340/CP2102 clones, 19 pins per side, with GPIO0 and the six in-package flash pins (GPIO6-11, labelled D0 D1 D2 D3 CMD CLK or SD0-SD3) broken out. Use when working on a 38-pin ESP32 devkit (ESP32-D0WDQ6 / ESP32-D0WD-V3, ESP-WROOM-32 or ESP32-WROVER module): project setup, platformio.ini and sdkconfig for ESP-IDF or Arduino, pin mapping and which GPIOs are safe, the flash-pin and IO0 traps, WROVER GPIO16/17 PSRAM conflict, strapping pins, ADC1 vs ADC2 with Wi-Fi, SPI speed and IO_MUX pins, deep sleep and RTC wake pins, flashing, BOOT/EN recovery, brownouts, or debugging why something on the board does not work.

The English summary is being prepared. Showing the original description.

Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the `gpunetio_ib_write_lat` client + server pair under `doca/tools/gpunetio_ib_write_lat/`, checking GPU-NIC pairing, reading the half-iter / full-iter / CUDA-side usec columns, characterizing median / p99 / jitter for a real-time control loop, picking GPUNetIO vs GPI vs CPU-initiated `perftest`, or weighing the latency-vs-batching trade-off. Trigger even without 'GPUNetIO' or 'ib_write_lat': 'GPU kernel RDMA latency benchmark', 'how fast can a CUDA kernel post a WRITE', 'p99 RDMA latency on H100 + ConnectX', 'kernel-launched WR tail latency', or 'compare GPU-init vs CPU-init perftest'. Route elsewhere for bandwidth runs (doca-gpunetio-ib-write-bw), the GPI surface (doca-gpi), library debugging (doca-gpunetio), or DOCA install.

The English summary is being prepared. Showing the original description.

Use when evaluating stocks through Duan Yongping's benfen (本分) value investing lens: good business, right price, long hold, understand what you own, and stay within your circle of competence.

The English summary is being prepared. Showing the original description.

Ingests unstructured and semi-structured documents into Neo4j as a knowledge graph. Use when chunking PDFs, HTML, plain text, or Markdown; extracting entities and relationships from text with an LLM (SimpleKGPipeline, neo4j-graphrag); loading JSON via apoc.load.json; building Document→Chunk→Entity graph structures; or connecting LangChain/LlamaIndex document loaders to Neo4j. Covers neo4j-graphrag SimpleKGPipeline, LLM Graph Builder web UI, entity resolution, chunking strategies, and graph schema design for RAG pipelines. Does NOT handle structured CSV/relational import — use neo4j-import-skill. Does NOT handle GraphRAG retrieval after ingestion — use neo4j-graphrag-skill. Does NOT handle vector index creation — use neo4j-vector-search-skill.

The English summary is being prepared. Showing the original description.

Use when configuring GPIO modes, alternate functions, pull resistors, or EXTI interrupts on STM32/nRF/ESP32-class MCUs. Not for register access rules: use mmio-and-bit-manipulation.

The English summary is being prepared. Showing the original description.

Firmware development for the ESP32-C3 0.42" OLED board (ESP32-C3FH4, QFN32) — the ABRobot / 01Space "ESP32-C3-0.42LCD" mini board and its clones, sold as "ESP32-C3 SuperMini with OLED" and "ESP32 C3 OLED development board". Covers its 72x40 SSD1306 OLED on I2C, the single I2C bus, blue LED on GPIO8, BOOT button on GPIO9, USB Serial/JTAG console, ADC1, Wi-Fi/BLE, and the ESP-IDF + PlatformIO setup around them. Use when working on this board or a bare ESP32-C3: project setup, platformio.ini and sdkconfig, pin mapping and strapping pins, getting the 0.42-inch display to show something other than snow, U8g2 offsets, adding a second I2C device, flashing over USB-C, or debugging why something on the board does not work.

The English summary is being prepared. Showing the original description.

Firmware development for the 30-pin ESP32-WROOM-32 development board — the DOIT ESP32 DevKit V1 / ESP32 CH340 Type-C / NodeMCU-ESP32 30-pin form factor, 15 pins per side, CH340G or CP2102 USB-UART bridge, AMS1117 LDO, user LED on GPIO2. Use when working on a 30-pin ESP32 devkit (ESP32-D0WDQ6 / ESP32-D0WD-V3, ESP-WROOM-32 module): project setup, platformio.ini and sdkconfig for ESP-IDF or Arduino, pin mapping and which GPIOs are safe, strapping pins, ADC1 vs ADC2 with Wi-Fi, SPI speed and IO_MUX pins, I2C, deep sleep and RTC wake pins, flashing over the CH340 bridge, BOOT/EN recovery, brownouts, or debugging why something on the board does not work.

The English summary is being prepared. Showing the original description.

Automate Bigpicture IO tasks via Rube MCP (Composio). Always search tools first for current schemas.

The English summary is being prepared. Showing the original description.

Develop firmware and drivers for ARM Cortex-M microcontrollers, including Teensy, STM32, nRF52, and SAMD. Get complete modules with initialization and usage examples, plus guidance on interrupts, memory handling, data transfers, performance, and fault diagnosis.

• Build an SPI driver for an external sensor
• Design interrupt-driven UART reception
• Review DMA transfers and cache consistency

Assess a company’s management through public statements, delivered commitments, crisis decisions, and use of company funds. Produce evidence-based scores for integrity, strategy, capital allocation, and governance, alongside a verdict on long-term trust.

• Check whether executives delivered on past commitments
• Review acquisitions, buybacks, dividends, and new ventures
• Assess ownership, compensation, and related-party dealings

Develop microcontroller firmware for STM32 or ESP32, including peripheral drivers and FreeRTOS tasks. The skill guides interrupt handling, memory and power optimization, and checks that time-sensitive operations meet their deadlines.

• Implementing peripheral control on STM32 or ESP32
• Designing periodic tasks and synchronization with FreeRTOS
• Reducing firmware memory use and power consumption

Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time voice-agent pipeline, including speech (ASR/TTS) customization and cloud or local deployment. Not for offline/batch speech-to-text, text-only chat or RAG, or generic Docker or CUDA work unrelated to a voice agent.

The English summary is being prepared. Showing the original description.

Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use /digital-health-clinical-asr-eval).

The English summary is being prepared. Showing the original description.

Use when the user wants to use Arduino sensors or peripherals from MATLAB that are not directly supported by the MATLAB Support Package for Arduino Hardware. Triggers on requests to create, wrap, or expose a custom Arduino library to MATLAB. Also triggers on indirect questions like "How do I read humidity in MATLAB?" or "How do I display text on an LCD from MATLAB?" where the answer requires a custom Arduino add-on library. Covers: custom addon creation, third-party Arduino library integration, LibraryBase class, C++ header files, DependentLibraries, arduinoioaddons namespace, I2C/SPI/GPIO peripheral wrappers.

The English summary is being prepared. Showing the original description.

MaxQuant + Perseus proteomics pipeline: run MaxQuant for LFQ and SILAC; parse proteinGroups.txt in Python; filter contaminants/decoys; log2 + median-normalize; impute MNAR; t-test with FDR; volcano plot; GO/pathway enrichment. Use Proteome Discoverer for Thermo-native processing; FragPipe/MSFragger for GPU-accelerated DB search.

The English summary is being prepared. Showing the original description.

ESPHome device configuration, firmware, and IoT product development. Covers ESP32, ESP32-S3, ESP32-C3, ESP32-C6, ESP32-H2, ESP32-P4, ESP8266, RP2040, RP2350, nRF52, LibreTiny, Shelly, Sonoff, Tuya, BLE proxy, Matter firmware, Thread, Zigbee, GPIO, sensor YAML, LVGL displays, LED strips, voice assistant hardware, device flashing, Arduino conversion, alarm_control_panel, lock, valve, media_player, microphone, speaker, audio DAC, event entities, datetime entities, Z-Wave proxy, MIPI DSI displays, and DLMS smart meters. Also covers designing new ESPHome-based products: hardware selection, component sourcing, PCB design (KiCad), enclosures, 3D printing, CE/FCC certification, BOM optimization, and manufacturing from prototype to production scale.

The English summary is being prepared. Showing the original description.

Embedded firmware development for microcontrollers including memory-mapped I/O, GPIO, interrupts, timers, UART/SPI/I2C serial protocols, PWM generation, ADC sampling, interrupt-driven versus polled architectures, RTOS fundamentals, and the bring-up sequence from power-on reset through first printf. Covers AVR/Arduino, ARM Cortex-M, and ESP32 patterns. Use when writing, porting, debugging, or reviewing firmware that directly manipulates hardware peripherals.

The English summary is being prepared. Showing the original description.

Hardware interfacing and peripheral management for Zephyr RTOS. Covers the sensor subsystem (channels, triggers, fetch/get), pin control (Pinctrl) and multiplexing, GPIO management using Devicetree specs, and SoC-level hardware configurations. Trigger when adding new hardware components, configuring pinmux, or developing sensor-based applications.

The English summary is being prepared. Showing the original description.

当用户面临方向性决策纠结时使用——先判断方向对不对，再考虑怎么做好。典型触发：用户说"我在纠结要不要做XX""做了很久但效果不好""方向对不对""值不值得坚持""是方向问题还是执行问题"。 核心框架："做对的事情"（方向判断，道）vs "把事情做对"（执行效率，术），二者不可颠倒。 不适用于：纯执行层面的问题（已经有了正确方向，只需要方法）、日常小事。

The English summary is being prepared. Showing the original description.