More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    ConvexAgents

    1

    Design, build, and audit production-grade reactive backends on the Convex TypeScript platform.

    Free

    Security scanned
    ConvexAgents

    ConvexAgents

    Example session with this skill installed

    I need to add a secure billing system to my Convex app. We need to handle subscriptions with Stripe and gate access to the 'pro_features' query.

    • Read your context and instructions
    • Compiled the convexagents

    I have installed @convex-dev/stripe and wired the billing logic. I added a webhook handler to sync subscription state and updated the pro_features query to enforce server-side gating.

    Stripe Integration and Gated Access

    // convex/convex.config.ts
    import { defineApp } from "convex/server";
    import stripe from "@convex-dev/stripe/convex.config.js";
    
    const app = defineApp();
    app.use(stripe);
    export default app;
    
    // convex/pro.ts
    import { query } from "./_generated/server";
    import { v } from "convex/values";
    import { components } from "./_generated/api";
    
    export const getProData = query({
      args: {},
      handler: async (ctx) => {
        const identity = await ctx.auth.getUserIdentity();
        if (!identity) throw new Error("Unauthenticated");
    
        // Check subscription status via the stripe component
        const subscription = await ctx.runQuery(
          components.stripe.subscriptions.get,
          { userId: identity.subject }
        );
    
        if (subscription?.status !== "active") {
          throw new Error("Pro subscription required");
        }
    
        return await ctx.db.query("pro_content").collect();
      },
    });
    

    Next steps

    1. Run npx convex env set STRIPE_API_KEY <your_key> to configure the secret.
    2. Update your frontend to use the useAction(api.stripe.checkout) hook for the upgrade flow.
    3. Trigger a test webhook from the Stripe dashboard to verify the httpAction listener.

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

    About this skill

    Building backends usually means wrestling with fragmented infra, flaky migrations, and auth holes. This skill transforms your agent into a Convex architect that builds, secures, and scales reactive backends on a single type-safe stack.

    What it does

    • Architect backends: Generates schemas, queries, mutations, and actions using Convex object-form syntax.
    • Audit security: Scans for PII leaks, missing ownership checks, and identity impersonation with deterministic fixes.
    • Manage migrations: Rehearses schema changes on snapshot-seeded previews to prevent production data corruption.
    • Implement capabilities: Adds Stripe billing, Auth (Passkeys/OAuth), AI/RAG backends, and crons via verified components.
    • Analyze performance: Root-causes OCC contention and read-limit hits using 72-hour deployment insights.

    How it works

    1. Design: Provide a product requirement to scaffold a full-stack Convex app with Next.js.
    2. Implement: Add specific capabilities like auth or billing using targeted sub-skills.
    3. Audit: Run launch-readiness reports to identify security gaps or performance bottlenecks.
    4. Deploy: Use the deployment guard to safely promote changes from dev to production.

    Frameworks & tools

    Built for the Convex platform. Integrates with Next.js, Stripe, Vitest, and Tailwind CSS.

    Why this beats prompting it yourself

    Generic LLMs frequently hallucinate Convex's object-form function syntax or miss critical validator requirements. This skill uses version-current documentation and specialized logic to ensure every function is transactional, type-safe, and secure by default.

    Use cases

    • Scaffold a reactive, real-time SaaS backend from a single prompt.
    • Secure an existing app against unauthorized data access and PII leaks.
    • Debug production performance issues by analyzing real execution logs.
    • Add an AI agent with RAG and vector search to an existing backend.

    Known limitations

    Requires an active Convex account for deployment-based features. Insights and advisor tools require the official Convex MCP to be configured.

    Requires Convex account. Insights and advisor tools need official Convex MCP. Designed for TypeScript environments.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 16 days ago

    • Free with an Agensi account

    Requires

    Node.js
    @convex-dev/auth
    shadcn
    tsc
    create-convex
    vitest

    Permissions

    Write Files
    Network Access
    Read Files
    Environment Variables
    Terminal / Shell
    Listed16 days ago

    What's inside

    Frequently Asked Questions

    While generic LLMs often struggle with Convex's unique object-form syntax and transactional logic, this skill is specifically tuned to generate type-safe, validator-compliant code that follows current Convex best practices. It eliminates common hallucinations regarding function decorators and schema definitions that usually require manual debugging.

    The skill is designed for agents operating within TypeScript-heavy environments, particularly those using Next.js. For full functionality, including performance analysis and deployment guards, you will need to have the Convex MCP (Model Context Protocol) configured in your agent's environment.

    Beyond code generation, this skill acts as a security and performance auditor. It can scan your existing backend for PII leaks, missing ownership checks, and Optimistic Concurrency Control (OCC) contention issues, providing deterministic fixes to make your app production-ready.

    You receive a comprehensive suite of capabilities for scaffolding, auditing, and optimizing Convex backends, including pre-verified components for Stripe, Auth, and RAG. You also get access to deployment guards that help you rehearse migrations using snapshot-seeded previews before they hit production.

    Yes, the skill requires an active Convex account to utilize deployment-based features, such as real-time insights and log analysis. It is built to work seamlessly with the Convex serverless infrastructure and standard TypeScript tooling like Vitest and Tailwind CSS.

    New in APIs & Backend