Skip to content
Arete
For the complete documentation index optimized for AI agents, see llms.txt or llms-full.txt. A markdown version of this page is available by appending .md to the URL or sending Accept: text/markdown.

Agent Skills

For AI agents: the documentation index is at llms.txt (full corpus: llms-full.txt). A markdown source for this page is /agent-skills/overview.md.

Arete is designed to be built with AI agents. This page explains the three pieces that make that work: the CLI, the agent skills, and agent.md.

The CLI

Section titled “The CLI”

The Arete CLI (a4) is the primary interface between your agent and Arete. It handles scaffolding, deployment, SDK generation, and — most importantly — live schema discovery.

Terminal window
# Install via Cargo (recommended)
cargo install a4-cli


# Or via npm
npm install -g @usearete/a4

The key command for agents is a4 explore:

Terminal window
a4 explore --json

This queries the Arete API and returns the live schemas for all available stacks — their entities, fields, views, and types. Because your agent runs this at setup time, it always works with accurate, up-to-date type information rather than guessing from training data.

Agent Skills

Section titled “Agent Skills”

Agent skills are markdown files that teach your agent how to use Arete correctly. They’re installed into your project so your agent picks them up automatically as context.

Three skills are installed:

SkillWhat it teaches
areteRouter skill — detects intent and routes the agent to the right sub-skill
arete-consumeSDK patterns for connecting to streams in TypeScript, React, and Rust
arete-buildRust DSL syntax for building custom stacks from Solana program IDLs

Install them manually with:

Terminal window
npx skills add AreteA4/skills

Once installed, your agent knows the correct hook names, view patterns, subscription syntax, and CLI commands. Without the skills, an agent will hallucinate API shapes based on outdated training data.

agent.md

Section titled “agent.md”

agent.md is a plain text file hosted at https://docs.arete.run/agent.md. It’s the bootstrap instruction set — a single URL your agent can read to set everything up from scratch.

When your agent reads agent.md, it:

  1. Installs the Arete CLI (prefers Cargo, falls back to npm)
  2. Installs the agent skills into the project
  3. Runs a4 explore --json to load live schemas
  4. Understands it’s ready to build

This is why the one-liner works:

Read https://docs.arete.run/agent.md and follow the instructions to set up Arete in this project

How They Fit Together

Section titled “How They Fit Together”
agent.md  ──▶  CLI installed  ──▶  a4 explore --json  ──▶  live schemas
               Skills installed ─▶  SDK patterns + DSL syntax


                         ┌────────────────────────────┐
                         │         AI Agent            │
                         │  (Cursor, Claude Code, etc) │
                         │                             │
                         │  Skills  +  Live schemas    │
                         └────────────┬───────────────┘
                                      │
                              builds correct code
                                      │
                                      ▼
                               Your Arete app

The CLI gives the agent live data. The skills give the agent correct patterns. Together they remove the two main failure modes: wrong types and wrong API usage.

Prefer to Set Up Manually?

Section titled “Prefer to Set Up Manually?”
Terminal window
cargo install a4-cli
# Or: npm install -g @usearete/a4


npx @usearete/a4 create my-app --template react-ore
cd my-app


npx skills add AreteA4/skills

For editor-specific file locations and manual configuration, see Editor Setup.

Next Steps

Section titled “Next Steps”