Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    ML Serving Architecture Selector

    1

    Choose and justify batch, real-time, streaming, edge, managed, Kubernetes, or serverless model serving with an evidence-tagged ADR.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ML Serving Architecture Selector

    ML Serving Architecture Selector

    Example session with this skill installed

    We need to serve a 2GB LLM for internal document Q&A. We have 500 users, p99 latency needs to be under 2s, and our team has zero Kubernetes experience. Batch or real-time?

    • Read your context and instructions
    • Compiled the ml serving architecture

    ARTIFACT: ML-SERVING-ADR
    DECISION: Managed real-time endpoint; avoid self-hosted Kubernetes.

    BINDING CONSTRAINTS

    • [Verified] p99 latency under 2 seconds eliminates batch for the interactive path.
    • [Verified] Zero Kubernetes experience eliminates self-hosted Kubernetes.
      COST: requests/day × compute-seconds × current unit price; CALIBRATE request rate and vendor price.
      STEELMAN: A 2GB model may create cold-start or memory constraints that require direct measurement.
      REVISIT: Re-open the choice when measured concurrency, latency, cost, or team capacity crosses an approved threshold.

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

    About this skill

    Choose a serving pattern your team can actually operate

    ML serving decisions are often made from technology preference instead of workload constraints. This skill turns latency, throughput, freshness, cost shape, team capacity, rollout needs, and compliance requirements into a structured architecture decision.

    What it produces

    • A binding-constraint register tagged Verified, Inferred, or Assumed
    • An elimination pass for structurally unsuitable patterns
    • A six-axis comparison matrix for the surviving options
    • Cost formulas using supplied values and CALIBRATE markers where values are missing
    • An ML-SERVING-ADR with the decision, strongest counterarguments, and revisit triggers

    Patterns covered

    Batch, real-time, streaming, edge, managed platforms, Kubernetes-based serving, and serverless inference. The skill compares architecture patterns; it does not deploy or configure any platform.

    Best for

    • Teams deciding whether online inference is actually necessary
    • Architects comparing managed serving with self-operated infrastructure
    • ML teams documenting why an option was eliminated
    • Reviewers who need explicit trade-offs and conditions that reopen the decision

    Boundaries

    It does not query live prices, benchmark latency, provision infrastructure, prove compliance, or guarantee cost or performance. Provider-specific claims must be verified against current authoritative documentation.

    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.

    Produces a decision artifact from supplied constraints; it does not deploy infrastructure, query live vendor pricing, benchmark latency, or guarantee cost or performance. Missing workload or team data is labeled Assumed or CALIBRATE. Runtime routing was not executed during package validation.

    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

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill helps teams avoid expensive infrastructure mistakes by objectively analyzing workload constraints like latency and cost to select the most sustainable serving pattern, from batch to edge.

    You will receive a structured ML-SERVING-ADR (Architecture Decision Record), a constraint register, a six-axis comparison matrix, and customizable cost formulas to justify your choice.

    No, this skill is focused on strategic architecture and trade-off analysis; it does not generate deployment scripts or interface with cloud provider APIs to provision resources.

    This skill is designed to run on any major LLM-based agent platform that supports text-based inputs and structured document generation.

    The skill includes 'CALIBRATE' markers in its cost formulas, allowing you to plug in your team's specific vendor pricing or internal labor rates for accurate forecasting.

    Updates are delivered through the marketplace platform and include refined architectural patterns as new serving technologies and industry best practices emerge.

    New in Agents & Orchestration