Convex Agents Fundamentals
Sets up and configures Convex agents for chat-based AI interactions. Use this when initializing agent instances, creating conversation threads, and generating basic text or structured responses from LLMs. Essential foundation for any Convex agent implementation.
npx skills add majiayu000/claude-skill-registry --skill convex-agents-fundamentals --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
## Purpose Guides you through the core patterns for setting up Convex agents, managing conversation threads, and generating LLM responses. This is the foundation upon which all other agent capabilities build. ## When to Use This Skill - Setting up your first Convex agent in a project - Creating or continuing conversation threads with users - Generating text responses or structured JSON objects from an LLM - Configuring agent defaults (system prompt, chat model, embedding model) - Building basic chat interfaces that need message history ## How to Use It ### 1. Install and Configure Add the agent component to your `convex.config.ts`: ```typescript // convex/convex.config.ts import { defineApp } from "convex/server"; import agent from "@convex-dev/agent/convex.config"; const app = defineApp(); app.use(agent); export default app; ``` Run `npx convex dev` to generate the required code. ### 2. Define Your Agent Create an agent instance with a chat model: ```typescript // convex/agents/myAgent.ts import { components } from "../_generated/api"; import { Agent } from "@convex-dev/agent"; import { openai } from "@ai-sdk/openai"; export const myAgent = new Agent(components.agent, { name: "My
- Purpose
- When to Use This Skill
- How to Use It
- 1. Install and Configure
- 2. Define Your Agent
- 3. Create Threads
- 4. Generate Responses
- Key Principles
- Common Patterns
- Next Steps
What does the Convex Agents Fundamentals skill do?
Sets up and configures Convex agents for chat-based AI interactions. Use this when initializing agent instances, creating conversation threads, and generating basic text or structured responses from LLMs. Essential foundation for any Convex agent implementation.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill convex-agents-fundamentals --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.