More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Maxilun embodied systems

    1

    Physical software engineering orchestrator and simulation harness for embedded firmware, robotics kinematics, communication buses, and FMEA safety triage.

    $19

    /mo

    Subscription · cancel anytime

    Secure checkout via Stripe

    • Always the latest version
    • Delivered live to your agent via MCP
    • Cancel anytime, access ends at period end
    Security scanned
    Maxilun embodied systems

    Maxilun embodied systems

    Example session with this skill installed

    /embodied full --board esp32 --task "Calculate A/B partitions and RAM budget for an AMR rover with an 800KB TinyML model"

    • Read your context and instructions
    • Compiled the maxilun embodied systems
    • Generated the data export

    I have completed the multi-stage hardware and firmware analysis for the Autonomous Mobile Robot (AMR) rover on the ESP32 platform.

    Embedded Architecture & Resource Budget

    1. Memory Budgeting (HardwareArch)

    ComponentAllocatedLimitStatus
    Flash (App A)1.4 MB4.0 MB[CONFIRMED]
    Flash (App B)1.4 MB4.0 MB[CONFIRMED]
    SRAM (Static)180 KB520 KB[INFERRED]
    TinyML Arena800 KB2048 KB (PSRAM)[CONFIRMED]

    2. OTA Partition Table (Firmware)

    
    # ESP-IDF Partition Table
    # Name,   Type, SubType, Offset,  Size, Flags
    nvs,      data, nvs,     ,        0x4000,
    otadata,  data, ota,     ,        0x2000,
    phy_init, data, phy,     ,        0x1000,
    ota_0,    app,  ota_0,   ,        1400K,
    ota_1,    app,  ota_1,   ,        1400K,
    storage,  data, spiffs,  ,        1000K,
    

    3. FMEA Triage (Triage)

    • Hazard: OTA Failure during write. RPN: 24 (S:4, O:2, D:3).
    • Mitigation: Dual-boot A/B rollback with monotonic eFuse anti-rollback [REQUIRED].
    • Hazard: TinyML Heap Exhaustion. RPN: 40 (S:5, O:4, D:2).
    • Mitigation: Static allocation of Tensor Arena in PSRAM with WDT monitoring.

    Next steps

    • Export the partitions.csv to your ESP-IDF project root.
    • Run embodied.py tune to define PID gains for the rover traction control.
    • Verify the SHA-256 signing keys for the Stage 5 Fleet manifest.

    partitions.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

    $19/mo

    Subscription · always the latest version

    • Secure checkout via Stripe
    • Cancel anytime
    • Delivered live via MCP

    About this skill

    Shipping physical software requires managing hardware constraints that traditional dev tools ignore. This skill provides an engineering orchestrator and simulation harness for embedded firmware, robotics, and IoT systems, ensuring your code respects physical boundaries like memory ceilings, bus bandwidth, and safety protocols.

    What it does

    • FMEA Safety Triage computes risk priority numbers and ISO 26262 ASIL hazard matrices for edge systems.
    • Resource Budgeting validates Flash and SRAM headroom across MCU profiles and budgets TinyML Tensor Arena capacity.
    • Firmware Architecture generates ESP-IDF A/B partition tables and calculates FreeRTOS RMS stack allocations.
    • Kinematics Simulation models motion for differential drive, Mecanum, and planar arms with trapezoidal velocity profiling.
    • Control Tuning implements closed-loop PID controllers using Ziegler-Nichols auto-remediation and exports static C headers.
    • Fleet Security signs OTA manifests with SHA-256/ECDSA and enforces monotonic eFuse anti-rollback bounds.

    How it works

    1. Triage the physical threat model to establish safety mitigations and ASIL ratings.
    2. Analyze hardware constraints using GCC linker maps or target board manifests to verify memory and thermal limits.
    3. Simulate control logic and kinematics to validate motion profiles before generating C firmware headers.
    4. Verify the integrated design against the initial safety requirements to produce an institutional audit report.

    Frameworks & tools

    Targeting embedded environments including ESP-IDF, FreeRTOS, and bare-metal C/C++. Integrates with GCC linker maps, PlatformIO, and TinyML workflows.

    Why this beats prompting it yourself

    Generic LLMs lack the physical grounding to catch ISR race conditions or flash wear-out risks. This skill uses a multi-agent DAG to enforce strict hardware boundaries and safety envelopes that standard prompts overlook.

    Use cases

    • Drafting FMEA worksheets for ISO 26262 compliance in automotive robotics.
    • Optimizing ESP32 partition tables for secure A/B OTA updates.
    • Tuning PID constants for high-precision motor control systems.
    • Budgeting SRAM for edge AI models on constrained microcontrollers.

    Known limitations

    Does not design physical PCB layouts or electrical schematics. Analysis is based on models and simulation, not physical hardware certification or formal medical safety proof.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Cannot design PCB layouts or electrical schematics. Results are simulations and analysis, not formal safety certifications or hardware-in-the-loop proofs.

    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 buying a skill.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 11 days ago

    Software
    PythonNode.jsGit

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed11 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a specialized engineering co-pilot that manages hardware-specific constraints like SRAM budgeting, FMEA safety triage, and PID tuning—critical physical factors that standard LLMs often overlook or miscalculate.

    The skill is compatible with any AI agent platform that supports structured file inputs and complex reasoning, and it outputs production-ready formats including static C headers, ESP-IDF partition tables, and GCC linker map analysis.

    While it does not generate PCB layouts, it provides the logic-layer 'connective tissue' such as kinematics modeling, memory allocation for TinyML, and security protocols for OTA firmware updates.

    You receive the complete multi-agent orchestration logic, standardized templates for ISO 26262 compliance reports, and the simulation harness for testing motion profiles and control loops.

    Yes, the skill is specifically designed to analyze target board manifests and linker maps to ensure your firmware and TinyML models respect strict Flash and SRAM headroom limits.

    New in Agents & Orchestration