Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Dependency Upgrade Navigator

    1

    A major upgrade fails for one reason: the changelog is generic and your codebase is specific.

    $7

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Dependency Upgrade Navigator

    Example session with this skill installed

    plan the upgrade from React 18 to 19 for this projectplan the upgrade from React 18 to 19 for this project

    • Read your context and instructions
    • Compiled the dependency upgrade navigator

    React 18.3.1 → 19.0.0 (major). Breaking changes that affect YOUR code:
    🔴 src/index.tsx:12 — ReactDOM.render removed; migrate to createRoot.
    🔴 src/types.ts:40 — implicit children in FC removed; add children?: ReactNode.
    🟡 Default: stricter act() warnings may surface test issues.

    Ordered plan

    1. npx codemod react/19/replace-reactdom-render
    2. Manually fix the FC children types (3 files).
    3. npm i react@19 react-dom@19 (coordinated).
    4. Verify: npm test. Rollback: restore package-lock.json + git checkout.

    Note: run the test suite as the real gate — the changelog may not list every behavior change.the breaking changes that affect your code (file:line), ordered steps with commands, available codemods, and a verify/rollback plan.

    restore package-lock.json

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

    About this skill

    A major upgrade fails for one reason: the changelog is generic and your codebase is specific. This skill closes that gap.

    What it does

    1. Reads the locked current version (not the manifest range) and classifies the jump
    2. Pulls the migration guide + changelog between the two versions — removed/renamed APIs, changed defaults (the silent killers), official codemods
    3. Intersects breaking changes with YOUR code — greps real usage and reports only what touches you, with file:line
    4. Produces an ordered migration plan with exact commands (codemod-able first, then manual, then verify, then the bump)
    5. Adds a verification + rollback plan

    Read-only. Produces the plan and the commands; you apply them on a branch. It never runs the install, a codemod, or edits your lockfile.

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

    Read-only planner. Does not execute installs, edits, or codemods. Coverage is limited to items found in migration guides and changelogs. Cannot detect runtime-only behavior changes.

    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 18 days ago

    Permissions

    Read Files
    Write Files
    Listed18 days ago

    What's inside

    Frequently Asked Questions

    The skill performs a deep intersection of your current lockfile and target version changelogs, identifying exactly which files and line numbers in your codebase will break before you run an install.

    It is designed for any AI agent that has file-system access, such as AutoGPT or custom IDE agents, and works across ecosystems like npm, pip, Maven, and Gradle.

    No, this is a read-only planning tool designed to provide a safe, step-by-step roadmap and verification strategy without making destructive changes to your source code.

    By forcing a strict comparison between your specific locked version and the target documentation, the skill prevents the version-mixing and 'hallucinated' methods common in general LLM prompts.

    You receive the full skill logic and a structured workflow that enables your agent to scan local files, analyze version deltas, and generate prioritized migration reports.

    New in APIs & Backend