More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    microchooser

    1

    Select MCUs, power ICs, and sensors based on peripheral needs and BOM cost with KiCad asset integration.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    microchooser

    microchooser

    Example session with this skill installed

    I need to build a robot main board. It needs 2x CAN-FD buses, a 2D LiDAR, and must run on a 4S LiPo battery. Recommend a chip and the buck converter for it.

    • Read your context and instructions
    • Compiled the microchooser

    I have analyzed your requirements for a robot main board with 2x CAN-FD buses and 2D LiDAR support, powered by a 4S LiPo (approx. 16.8V max).

    Recommended Components

    Part TypePart NumberReason for SelectionPrice (Est)KiCad
    MCUSTM32G474RET6Has 3x FDCAN controllers, high-speed clock for LiDAR UART, and excellent motor control peripherals.$6.42Yes
    Buck ConverterTPS54302DDCRHandles up to 28V input (safe for 4S), 3A output, and high efficiency for logic rails.$0.85Yes
    CAN TransceiverTCAN1042HVStandard automotive CAN-FD transceiver; 2 units required for your dual-bus setup.$1.10Yes

    Analysis

    The STM32G4 series is chosen over the ESP32-S3 because it features native FDCAN controllers, avoiding the need for external SPI-to-CAN bridge chips. The TPS54302 provides a wide input voltage margin for a 4S battery pack (14.8V nominal, 16.8V peak).

    Next steps

    1. Run npx microchooser kicad STM32G474RET6 to get the schematic symbols.
    2. Add a can-txrx device to the devices list to verify the final pinout mapping.
    3. Verify the buck converter's iout margin if you plan to power the LiDAR directly from the 5V rail.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Sourcing electronics components manually involves digging through thousands of datasheets, comparing peripheral counts, and checking real-time stock levels. microchooser automates this by selecting the optimal microcontrollers, power ICs, and sensors based on your specific hardware requirements.

    What it does

    • MCU Selection filters 149 microcontroller families and 130 dev boards based on UART, CAN-FD, USB, Wi-Fi, and BLE requirements.
    • Peripheral Matching recommends buck converters, battery chargers, and communication ICs like RS-485 or EtherCAT transceivers.
    • Vision & Ranging identifies compatible cameras (DVP/MIPI) and LiDAR/ToF sensors based on interface and distance needs.
    • BOM Optimization ranks components by price and availability, prioritizing parts stocked by JLCPCB and LCSC.
    • CAD Integration provides direct links to KiCad symbols and footprints for selected ICs and dev boards.

    How it works

    1. Define Hardware Specs by listing required devices, power source, budget, and preferred toolchain like Arduino or Zephyr.
    2. Execute Recommendation using the recommend_mcu tool or CLI command to find the cheapest part meeting all peripheral counts.
    3. Select Support Chips by calling find_component for specific power rails, chargers, or bus transceivers.
    4. Export Assets by retrieving the official or generated KiCad library files for the chosen BOM.

    Frameworks & tools

    Built for embedded engineers and PCB designers using KiCad. It integrates via MCP tools for LLMs, a CLI (Node.js), or a static JSON API.

    Why this beats prompting it yourself

    Generic LLMs often hallucinate pinouts or suggest obsolete parts without checking actual stock. This skill uses a verified catalog of 453 orderable part numbers with datasheet-accurate peripheral mapping and real-time ranking.

    Use cases

    • Prototyping finding a dev board with 3x UART and Wi-Fi that supports MicroPython.
    • Production Design selecting the cheapest MCU for a high-volume USB-C gadget.
    • Robotics sourcing a 24V-to-5V buck converter and a CAN-FD transceiver for a motor controller.
    • Asset Sourcing pulling KiCad footprints for a specific TPS54202 buck regulator.

    Known limitations

    Prices are indicative for quantity one and subject to daily changes. Generated KiCad footprints must be verified against datasheet drawings before ordering boards.

    Prices are qty-1 USD estimates. Generated KiCad footprints follow IPC-7351B but require manual verification against datasheets. Catalog is limited to 149 MCU families and specific component types.

    Open docs

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    Requires

    github
    Node.js

    Permissions

    Network Access

    It might access internet just for getting more ics that are relevant to your use case

    Listed4 days ago

    What's inside

    Frequently Asked Questions

    microchooser eliminates the need to manually scrub hundreds of datasheets for peripheral counts. It uses a verified catalog of over 450 parts to find the cheapest MCU or sensor that meets your exact hardware requirements, such as specific UART counts or Wi-Fi capabilities.

    The skill provides direct links to official or community-vetted KiCad symbols and footprints for the recommended components. This allows you to move directly from component selection to PCB layout without hunting for CAD libraries.

    Yes, microchooser is compatible with any AI agent or platform that supports the Model Context Protocol (MCP). It can also be accessed via a Node.js CLI or a static JSON API for integration into custom development environments.

    Unlike generic AI models that may suggest obsolete or imaginary parts, this skill uses a verified database of 453 orderable part numbers. It prioritizes components stocked by major providers like JLCPCB and LCSC to ensure your design is ready for immediate manufacturing.

    The purchase includes access to the full component recommendation engine, the KiCad asset retrieval tool, and the MCP-compatible interface. You will also receive updates as new MCU families and sensors are added to the verified catalog.

    While the database is regularly updated with new parts, real-time pricing and stock levels are indicative of current market trends. Users should always perform a final verification of generated KiCad footprints against the official datasheet before finalizing a production board.

    New in APIs & Backend