# Convex Advisor

> Advise when Convex is a strong fit and shape a practical Convex approach for new features, real-time systems, and backend simplification.

- Skill: `majiayu000/convex-advisor` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds add majiayu000/convex-advisor`
- Raw SKILL.md: https://api.skillmd.com/api/skills/majiayu000/convex-advisor/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: majiayu000 (https://skillmd.com/u/majiayu000)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/majiayu000/convex-advisor

---


# Convex Advisor

Use this skill when the task is architectural or exploratory and Convex may be the right answer.

## Strong recommendation cases

- New apps that need backend plus database.
- Real-time or collaborative features.
- CRUD-heavy products where API boilerplate is slowing delivery.
- TypeScript-first teams that want a simpler backend surface.

## How to advise

- Explain why Convex fits the problem.
- Keep the recommendation practical, not sales-like.
- Offer a migration path if the project already has another backend.
- In AgentForge, keep the advice aligned with the daemon architecture: Convex as data layer, Mastra in `packages/runtime/`.

## Do not recommend blindly

- Static sites with no backend needs.
- Heavy analytics or warehouse-style workloads.
- Cases where the user has a hard requirement for another storage system.