convex-backend
convex-backend is an engineering AI skill with a core value of Build reactive backends with Convex functions, schema validation, auth integration, and deployment workflows. It
helps developers solve real-world problems in the engineering domain, boosting
efficiency, automating repetitive tasks, and optimizing workflows.
Build reactive backends with Convex functions, schema validation, auth integration, and deployment workflows. Use when building real-time apps with type-safe server functions and automatic caching.
Quick Facts
mkdir -p ./skills/convex-backend && curl -sfL https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/skills/convex-backend/SKILL.md -o ./skills/convex-backend/SKILL.mdRun in terminal / PowerShell. Requires curl (Unix) or PowerShell 5+ (Windows).
Skill Content
# Convex Backend
Use Convex to build type-safe backend logic with realtime data sync.
When to Use This Skill
Use this skill when:
- Building real-time collaborative apps (chat, dashboards, multiplayer)
- Need a backend with zero infrastructure management
- Want type-safe server functions with automatic caching
- Building AI apps that need reactive data (agent status, streaming results)
- Prototyping quickly with a managed database + functions
Prerequisites
- Node.js 18+
- npm or pnpm
- Convex account (free tier: 1M function calls/month)
Quick Start
# Initialize Convex in an existing project
npm install convex
npx convex dev # Start local development (syncs with cloud)
# In a new project
npm create convex@latestSchema Definition
// convex/schema.ts
import { defineSchema, defineTable } from "convex/server";
import { v } from "convex/values";
export default defineSchema({
users: defineTable({
name: v.string(),
email: v.string(),
role: v.union(v.literal("admin"), v.literal("member")),
avatarUrl: v.optional(v.string()),
createdAt: v.number(),
})
.index("by_email", ["email"])
.index("by_role", ["role"]),
messages: defineTable({
userId: v.id("users"),
channelId: v.id("channels"),
body: v.string(),
attachments: v.optional(v.array(v.string())),
createdAt: v.number(),
})
.index("by_channel", ["channelId", "createdAt"])
.index("by_user", ["userId"]),
channels: defineTable({
name: v.string(),
description: v.optional(v.string()),
isPrivate: v.boolean(),
}),
});Queries (Real-Time Reads)
// convex/messages.ts
import { query } from "./_generated/server";
import { v } from "convex/values";
export const listByChannel = query({
args: {
channelId: v.id("channels"),
limit: v.optional(v.number()),
},
handler: async (ctx, args) => {
const messages = await ctx.db
.query("messages")
.withIndex("by_channel", (q) => q.eq("channelId", args.channelId))
.order("desc")
.take(args.limit ?? 50);
// Resolve user data for each message
return Promise.all(
messages.map(async (msg) => {
const user = await ctx.db.get(msg.userId);
return { ...msg, user: user ? { name: user.name, avatarUrl: user.avatarUrl } : null };
})
);
},
});Mutations (Writes)
// convex/messages.ts
import { mutation } from "./_generated/server";
import { v } from "convex/values";
export const send = mutation({
args: {
channelId: v.id("channels"),
body: v.string(),
},
handler: async (ctx, args) => {
const identity = await ctx.auth.getUserIdentity();
if (!identity) throw new Error("Not authenticated");
// Find or create user
const user = await ctx.db
.query("users")
.withIndex("by_email", (q) => q.eq("email", identity.email!))
.unique();
if (!user) throw new Error("User not found");
return await ctx.db.insert("messages", {
userId: user._id,
channelId: args.channelId,
body: args.body,
createdAt: Date.now(),
});
},
});Actions (External APIs, AI)
// convex/ai.ts
import { action } from "./_generated/server";
import { v } from "convex/values";
import { api } from "./_generated/api";
export const generateResponse = action({
args: { prompt: v.string(), channelId: v.id("channels") },
handler: async (ctx, args) => {
// Call external AI API
const response = await fetch("https://api.anthropic.com/v1/messages", {
method: "POST",
headers: {
"Content-Type": "application/json",
"x-api-key": process.env.ANTHROPIC_API_KEY!,
"anthropic-version": "2023-06-01",
},
body: JSON.stringify({
model: "claude-sonnet-4-6",
max_tokens: 1024,
messages: [{ role: "user", content: args.prompt }],
}),
});
const data = await response.json();
const aiMessag🎯 Best For
- UI designers
- Product designers
- Claude users
- AI users
💡 Use Cases
- Generating component mockups
- Creating design system tokens
- Using convex-backend in daily workflow
- Automating repetitive engineering tasks
📖 How to Use This Skill
- 1
Install the Skill
Copy the install command from the Terminal tab and run it. The SKILL.md file downloads to your local skills directory.
- 2
Load into Your AI Assistant
Open Claude and reference the skill. Paste the SKILL.md content or use the system prompt tab.
- 3
Apply convex-backend to Your Work
Provide context for your task — paste source material, describe your audience, or share existing work to guide the AI.
- 4
Review and Refine
Edit the AI output for accuracy, tone, and completeness. Add human insight where the AI lacks context.
❓ Frequently Asked Questions
Does this work with Figma?
Some design skills integrate with Figma plugins. Check the Works With section for supported tools.
How do I install convex-backend?
Copy the install command from the Terminal tab and run it. The skill downloads to ./skills/convex-backend/SKILL.md, ready to use.
Can I customize this skill for my team?
Absolutely. Edit the SKILL.md file to add team-specific instructions, examples, or workflows.
⚠️ Common Mistakes to Avoid
Skipping usability testing
AI-generated designs should be validated with real users before development.
Not reading the full skill
Skills contain important context and edge cases beyond the quick start.