ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

Convex

Build and maintain Convex backends with schema-safe modeling, query and mutation patterns, auth guards, and production rollout checks.

Why use this skill?

Build scalable, secure Convex backends with expert guidance on schema-safe modeling, authentication guards, and production-ready operational patterns.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/ivangdavila/convex
Or

What This Skill Does

The Convex skill is an expert-level engineering tool designed to help developers build, maintain, and scale backend services using the Convex platform. It provides a structured, pattern-based approach to data modeling, state management, and operational security. Instead of focusing on generic tutorials, this skill acts as a technical architect, emphasizing schema-safe database design, robust authentication strategies, and safe production deployment practices.

By utilizing a dedicated memory structure in ~/convex/, the skill keeps track of your project's technical history, schema evolution, and incident learnings. This allows the AI to provide context-aware suggestions that adhere to your established project decisions rather than generic advice. It enforces rigorous boundaries between queries, mutations, and actions to ensure your backend remains predictable, performant, and secure.

Installation

To add this skill to your workspace, execute the following command in your terminal:

clawhub install openclaw/skills/skills/ivangdavila/convex

Ensure your project root is initialized so that the skill can manage the ~/convex/ directory, which is necessary for tracking your schema, auth, and operational notes.

Use Cases

  • Database Schema Design: Designing tables and secondary indexes based on actual read-path requirements rather than hypothetical needs.
  • Authentication & Authorization: Implementing tenant-based access control and validating user identity across all query and mutation endpoints.
  • Production Rollouts: Managing incremental schema changes and documenting deployment strategies to minimize downtime or data inconsistency.
  • Debugging & Optimization: Analyzing function performance and identifying bottlenecks in data-fetching patterns.

Example Prompts

  1. "I am adding a collaborative workspace feature. How should I update my schema notes and index definitions to ensure efficient filtering by workspaceId while maintaining data isolation?"
  2. "Review my current mutation logic for updating user profiles. Are there any edge cases where authorization is bypassed or input validation is insufficient?"
  3. "We are planning a breaking schema migration. Help me draft a rollout plan in rollout-notes.md that addresses data transformation and rollback procedures."

Tips & Limitations

  • Follow the Memory Structure: Always initialize and update the files in ~/convex/. The skill is most effective when it has access to your schema-notes.md and auth-notes.md.
  • Prioritize Security: Treat all incoming data as untrusted. The skill strictly mandates server-side auth validation—never rely on the client for permission checks.
  • Keep Functions Pure: Do not mix network calls or external side effects inside queries. Always delegate these to Actions to keep your data layer deterministic.
  • Limitations: This skill does not manage your cloud credentials. It is a logic and patterns tool; you remain responsible for your environment variables and third-party API configurations.

Metadata

Stars2102
Views0
Updated2026-03-06
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-ivangdavila-convex": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#convex#backend#database#typescript#architecture
Safety Score: 4/5

Flags: file-read, file-write