React + TypeScript Review

    1

    Paste a component, hook, diff or page and get a focused code review instead of a wall of nitpicks.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    React + TypeScript Review

    Example session with this skill installed

    Review this component for bugs

    const Search = ({ query }) => {
      const [data, setData] = useState(null);
      useEffect(() => {
        fetch('/api?q=' + query)
          .then((r) => r.json())
          .then(setData);
      }, [query]);
      return <div>{data?.name}</div>;
    };
    
    • Read your context and instructions
    • Compiled the react + typescript

    Review: Search

    Must fix

    Stale response can overwrite newer data (the useEffect)
    The fetch has no abort, so if query changes quickly an older request can resolve last and win.

    useEffect(() => {
      const controller = new AbortController();
      fetch(`/api?q=${encodeURIComponent(query)}`, { signal: controller.signal })
        .then((r) => r.json())
        .then(setData)
        .catch((e) => { if (e.name !== "AbortError") console.error(e); });
      return () => controller.abort();
    }, [query]);
    

    Should fix

    • Query is not encoded: '/api?q=' + query breaks on &, # or spaces. The fix above uses encodeURIComponent.
    • No HTTP error handling: fetch does not reject on 4xx/5xx; check r.ok before r.json().
    • Loose state type: useState(null) infers null. Use useState<{ name: string } | null>(null).

    Optional

    • Add loading and error states so the UI is not blank while waiting.

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

    About this skill

    Paste a component, hook, diff or page and get a focused code review instead of a wall of nitpicks.

    What it checks

    • Correctness: effects that should be plain render logic, missing cleanup and abort handling, wrong dependency arrays, state mutation, unstable list keys, stale closures.
    • Types: any, unchecked casts and ! assertions, props that allow impossible combinations.
    • Next.js: "use client" placed too high, secrets reachable from client code, data fetched in effects when the server could do it.
    • UX and accessibility: clickable divs, unlabeled controls, missing loading/error/empty states, modal focus handling.
    • Performance: only with a stated reason. It does not push memo/useMemo by default.

    How it reports

    Findings are grouped into Must fix, Should fix and Optional. Each one has the location, why it matters in practice and a minimal code fix. If the code is fine, it says so.

    Notes

    • Instructions only: no scripts, no network access, no file writes.
    • It adapts to your setup (React Compiler, App Router vs Pages Router, TypeScript strictness).
    • It reports only what it can point to in the code and labels guesses as questions.

    MIT licensed.

    Does not perform runtime profiling. Cannot verify behavior for external API dependencies not present in the code context.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    • Free with an Agensi account

    Permissions

    Read Files

    File Scopes

    **/*.tsx
    **/*.ts
    **/*.jsx
    **/*.js

    Read-only. The skill only reads the files you point it at (components, hooks, diffs and the types they import). It does not run commands, write files, use the network or read environment variables.

    Listed5 days ago

    What's inside

    Frequently Asked Questions

    This skill focuses on critical runtime reliability, such as async race conditions and hydration mismatches, rather than stylistic nitpicks like naming conventions or indentation.

    It is not tied to a specific version. It checks which React and Next.js version your project uses (and whether you are on App Router or Pages Router) and adapts its advice. Tell it your versions if it cannot see them.

    The skill requires the source code of the component and its associated hooks or types; it cannot analyze external third-party dependencies where the source code isn't provided.

    You receive the specialized React/TS analysis engine, which can be deployed to any AI agent or platform that supports skill integration via standard API or markdown inputs.

    It checks whether your project uses the React Compiler and, if so, avoids recommending manual useMemo/useCallback unless there is a measured reason.

    New in Frontend & Web Apps