More screenshots

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    🛡️ Model Resilience Linter

    2

    The skill scans your codebase—supporting Python, JavaScript, and TypeScript—to detect patterns that signal poor reliability.

    $12

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned
    🛡️ Model Resilience Linter

    🛡️ Model Resilience Linter

    Example session with this skill installed

    Check my backend directory to see if we have any single provider risks or missing failovers.

    • Read your context and instructions
    • Compiled the model resilience linter

    Model Resilience Audit Results

    MRL001: Single-provider lock-in

    • services/gpt_client.ts:L42: Direct dependency on OpenAI without fallback provider detected.

    MRL003: No timeout configured

    • utils/llm_query.py:L12: API call lacks an explicit timeout setting.

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

    What you get

    Identify hardcoded LLM endpoints that lack secondary fallbacks.Detect missing timeouts and retry logic in AI service calls.Review repository for model provider lock-in and single points of failure.Ensure graceful degradation defaults are present for failed AI queries.

    About this skill

    Audit Your LLM Infrastructure for Single-Point-of-Failure Risk

    In the rapidly shifting landscape of AI providers, relying on a single model or endpoint is a significant architectural risk. The Model Resilience Linter is a specialized static analysis tool designed for developers to identify brittle LLM integrations before a provider outage or API deprecation brings down your application.

    What it does

    The skill scans your codebase—supporting Python, JavaScript, and TypeScript—to detect patterns that signal poor reliability. It specifically looks for:

    • Single-Provider Lock-in: Code that lacks a secondary fallback or failover logic.
    • Configuration Gaps: Missing timeouts, hardcoded base URLs, and lack of exponential backoff.
    • Graceful Degradation: Missing default states or "degraded-mode" handlers for when AI services are entirely unavailable.

    Why use this skill?

    Manually auditing a large repository for reliability anti-patterns is time-consuming and prone to human error. This skill automates the detection of infrastructure debt using a specialized rule set (MRL001-MRL006). Unlike general linters, it understands the specific failure modes of LLM calls, providing high-signal feedback and remediation references to help you build a provider-agnostic, resilient AI stack.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 3 months ago

    • Passed all security checks, Safe to install

    Listed3 months ago

    Frequently Asked Questions