cpo chief engineer playbook

    1

    Chief engineer playbook for silicon photonics, CPO architecture selection, link budgets, and NPI design reviews.

    $10

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    cpo chief engineer playbook

    Example session with this skill installed

    **Analyze the link budget for a CPO engine:** 0 dBm TX, 3 dB modulator loss, 1 dB waveguide loss, 1.5 dB coupling loss, and 0.6 dB connector loss. Target sensitivity is -8 dBm.

    • Read your context and instructions
    • Compiled the cpo chief engineer

    I have calculated the link budget based on your parameters. The current configuration provides a margin of 1.9 dB against the -8 dBm target sensitivity. ## Link Budget Analysis | Parameter | Value | Unit | Notes | | :--- | :--- | :--- | :--- | | TX Launch Power | 0.0 | dBm | Input | | Modulator Insertion Loss | -3.0 | dB | | | Waveguide Loss | -1.0 | dB | | | Coupling Loss (FAU) | -1.5 | dB | | | Connector Loss | -0.6 | dB | | | **Total Channel Loss** | **-6.1** | **dB** | Calculated | | **Received Power (PRX)** | **-6.1** | **dBm** | Calculated | | Receiver Sensitivity Target | -8.0 | dBm | Input | | **Link Margin** | **1.9** | **dB** | Result | **Calculation Logic:** `Margin = TX_Power - Mod_IL - WG_Loss - Cpl_Loss - Conn_Loss - Sensitivity` `1.9 = 0 - 3.0 - 1.0 - 1.5 - 0.6 - (-8.0)` **Risk Assessment:** 1. **Coupling Variation**: A 1.9 dB margin is tight for high-volume manufacturing. FAU alignment shifts >0.5 dB could trigger BER issues. 2. **Thermal Drift**: If the laser wavelength drifts without TEC compensation, additional mismatch loss may exceed the 1.9 dB buffer. **Next steps** - Run `cpo_calc.py yield` to determine how this margin affects EIC/PIC binning requirements. - Check `01-architecture-and-link-budget.md` for TDECQ penalty adjustments. - Review connector reliability specs in `06-reliability-and-qualification.md`.

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

    About this skill

    Navigating the fragmented technical requirements of Co-Packaged Optics (CPO) and silicon photonics programs often leads to misaligned link budgets, thermal crosstalk failures, or yield-model collapses during NPI. This skill provides a structured knowledge base and calculation engine for chief engineers managing 800G to 6.4T optical engine development.

    What it does

    • Architectural Trade-offs evaluates CPO versus LPO and traditional pluggable optics across power, density, and latency.
    • Link Budget Analysis calculates TDECQ, BER, and sensitivity margins using industry-standard frameworks.
    • Packaging Engineering provides guidance on EIC/PIC stacking, hybrid bonding, CoWoS, and fiber array (FAU) coupling.
    • Thermal and Signal Integrity tracks thermal crosstalk, wavelength drift, and liquid cooling requirements.
    • Yield and Reliability Modeling computes KGD/KGE metrics, FIT/AFR rates, and qualification requirements per GR-468.

    How it works

    1. Classification identifies if the query relates to architecture definition, design review, failure analysis, or supply chain.
    2. Quantization runs specific scripts for link budgets, power-per-bit (pJ/bit), yield cascades, or TCO comparison.
    3. Template Application generates structured outputs using industry-standard formats like 8D reports, design review checklists, or risk registers.

    Frameworks & tools

    Silicon photonics design rules, IEEE 802.3/OIF standards, and Python-based calculation scripts for optical link and reliability modeling.

    Why this beats prompting it yourself

    Generic LLMs struggle with the interdependencies between optical loss, thermal drift, and packaging yield. This skill forces a multi-domain check across eight specialized reference modules to ensure engineering assumptions remain physically consistent.

    Use cases

    • Compare CPO vs LPO power efficiency for 1.6T switch deployments.
    • Debug link budget closure issues involving TDECQ and modulator insertion loss.
    • Develop a design review checklist for wafer-level optical testing.
    • Model the TCO and yield impact of shifting from COUPE to TGV glass substrates.

    Known limitations

    Does not perform full electromagnetic or thermal simulations. Users must provide local specific parameters for custom PDKs or proprietary vendor processes.

    Requires specific input parameters for accurate script execution. Does not replace FEA/EM simulation tools. Coverage is focused on 800G+ architectures.

    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 13 days ago

    Permissions

    Terminal / Shell
    Read Files
    Listed13 days ago

    What's inside

    Frequently Asked Questions

    This skill serves as a technical co-pilot for hardware leads, bridging the gap between optical link budgeting, thermal constraints, and NPI yield modeling to prevent costly design failures in 800G+ programs.

    The playbook includes a comprehensive knowledge base, a calculation engine for link and power metrics, and standardized templates for design reviews and 8D failure analysis reports.

    While it provides deep architectural and standard IEEE/OIF insights, users should provide their own specific Process Design Kit (PDK) data for the most accurate custom modeling.

    This skill is designed for use within enterprise AI agent environments; simply import the playbook into your workspace to begin running link budget and architectural trade-off scripts.

    Unlike generic models, this skill uses a multi-domain check system to ensure that optical loss, thermal drift, and packaging yield assumptions remain physically consistent and technically feasible.

    New in Agents & Orchestration