base44-cli — Claude Code skill: what it does, how to install
Teaches AI coding assistants to manage Base44 apps via CLI: provision projects, push entity schemas, configure realtime actors, and run deployments.
npx skills add base44/skills --skill base44-cli -a claude-codeWhat base44-cli does
This skill instructs coding agents how to run the Base44 CLI without breaking workflows. It enforces executing commands exclusively through package managers like npx base44 or pnpm instead of direct binary calls. Every session starts with an authentication check via npx base44 whoami. If neither BASE44_API_KEY nor environment tokens are present, the agent halts all actions until the user completes npx base44 login.
The skill routes work based on local files. When base44/config.jsonc already exists, feature implementation shifts to base44-sdk, while this skill retains tasks like entity pushes and deployments. For uninitialized directories, it checks for BASE44_APP_ID before touching project creation. Running npx base44 create on an externally provisioned app creates a duplicate instance, so the skill forces npx base44 scaffold instead.
What it helps with
- initialize a new Base44 app using
npx base44 create - set up local files for an externally provisioned app with
npx base44 scaffold - verify session authentication before executing CLI actions via
npx base44 whoami - manage the
base44/configuration directory for schemas, functions, and actors
Example prompts for the agent
- Create a new Base44 project in this directory
- Scaffold the local Base44 project using the provisioned BASE44_APP_ID
- Check my Base44 login status and push entities
How to install base44-cli
1Skills CLI (Vercel)
npx skills add base44/skills --skill base44-cli -a claude-code2Manually: put the files in place
~/.claude/skills/base44-cli/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/base44-cli/
1Skills CLI (Vercel)
npx skills add base44/skills --skill base44-cli -a codex2Manually: put the files in place
.agents/skills/base44-cli/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add base44/skills --skill base44-cli -a cursor2Manually: put the files in place
.cursor/skills/base44-cli/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install base44/skills base44-cli2Manually: put the files in place
.github/skills/base44-cli/SKILL.md1Skills CLI (Vercel)
npx skills add base44/skills --skill base44-cli -a gemini-cli2Platform CLI
gemini skills install https://github.com/base44/skills --path skills/base44-cliManually: put the files in place
.devin/skills/base44-cli/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add base44/skills --skill base44-cli -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about base44-cli
How to install base44-cli in Claude Code?
Install the skill by running npx skills add base44/skills --skill base44-cli -a claude-code.
What does base44-cli do?
It governs how AI assistants execute Base44 CLI commands. The skill manages authentication checks, bootstraps new or provisioned projects, and configures project schemas, backend functions, and realtime actors.
How does base44-cli differ from base44-sdk?
The base44-cli skill handles terminal commands, project scaffolding, deployment, and authentication. Once base44/config.jsonc exists in the project, coding features and components is delegated to base44-sdk.
Source text
SKILL.md · MIT
---
name: base44-cli
description: "The base44 CLI is used for EVERYTHING related to base44 projects: resource configuration (entities, backend functions, realtime actors, ai agents), initialization and actions (resource creation, deployment), and any other operation on an existing app or workspace through the Base44 public API (settings, domains, users, members, source export). This skill is the place for learning about how to configure resources, including actors — the realtime/WebSocket primitive behind multiplayer, collaborative boards, presence and live cursors, in-room chat, and live auctions. When you plan or implement a feature, you must learn this skill"
metadata:
sourcePackage:
name: base44
version: 0.1.7
---
# Base44 CLI
Create and manage Base44 apps (projects) using the Base44 CLI tool.
## ⚡ IMMEDIATE ACTION REQUIRED - Read This First
This skill activates on ANY mention of "base44" or when a `base44/` folder exists. **DO NOT read documentation files or search the web before acting.**
**Your first action MUST be:**
1. Check if `base44/config.jsonc` exists in the current directory
2. If **YES** (existing project scenario):
- Transfer to base44-sdk skill for implementation
- This skill only handles CLI commands (login, deploy, entities push)
- **Except running the app locally** — stays here. Read [Running Local Development](#running-local-development)
before starting a dev server: one way of running hits production data.
3. If **NO**, decide between two initialization paths:
- **Provisioned app** — the Base44 app already exists because it was just provisioned through a Stripe Projects / projects.dev flow, OR `BASE44_APP_ID` (or `BASE44_PROJECTS_BASE44_APP_ID`) is present in the environment or a `.env`/`.env.local` file:
- Run `npx base44 scaffold` to set up local files for that **existing** app
- **DO NOT run `npx base44 create`** — that creates a second, duplicate app. See [scaffold.md](references/scaffold.md).
- **New project** — no app exists yet and none was provisioned:
- This skill (base44-cli) handles the request; guide the user through `npx base44 create`
- Do NOT activate base44-sdk yet
## Critical: Local Installation Only
NEVER call `base44` directly. The CLI is installed locally as a dev dependency and must be accessed via a package manager:
- `npx base44 <command>` (npm - recommended)
- `yarn base44 <command>` (yarn)
- `pnpm base44 <command>` (pnpm)
WRONG: `base44 login`
RIGHT: `npx base44 login`
## MANDATORY: Authentication Check at Session Start
**CRITICAL**: At the very start of every AI session when this skill is activated, you MUST:
1. **Check authentication status** by running:
```bash
npx base44 whoami
```
2. **If the user is logged in** (command succeeds and shows an email):
- Continue with the requested task
3. **If the user is NOT logged in** (command fails or shows an error):
- **STOP immediately**
- **DO NOT proceed** with any CLI operations
- **Ask the user to login manually** by running:
```bash
npx base44 login
```
- Wait for the user to confirm they have logged in before continuing
**This check is mandatory and must happen before executing any other Base44 CLI commands.**
**Provisioned via Stripe Projects / projects.dev?** When the app was provisioned through that flow, the CLI seeds authentication from the `BASE44_ACCESS_TOKEN` / `BASE44_REFRESH_TOKEN` environment variables it injects (the `BASE44_PROJECTS_*`-prefixed names are normalized automatically). In that case `npx base44 whoami` already succeeds and you do **not** need an interactive `npx base44 login`.
**Workspace API key set?** If the `BASE44_API_KEY` environment variable is set to a workspace API key (prefixed `b44k_`), the CLI authenticates with it directly — `npx base44 whoami` and other commands succeed without an interactive login.
## Overview
The Base44 CLI provides command-line tools for authentication, creating projects, managing entities, and deploying Base44 applications. It is framework-agnostic and works with popular frontend frameworks like Vite, Next.js, and Create React App, Svelte, Vue, and more.
## When to Use This Skill vs base44-sdk
**Use base44-cli when:**
- Creating a **NEW** Base44 project from scratch
- Initializing a project in an empty directory
- Setting up local files for an **existing** app that was provisioned externally (e.g., through a Stripe Projects / projects.dev flow) → use `scaffold`
- Directory is missing `base44/config.jsonc`
- User mentions: "create a new project", "initialize project", "setup a project", "start a new Base44 app"
- Deploying, pushing entities, or authenticating via CLI
- Working with CLI commands (`npx base44 ...`)
**Use base44-sdk when:**
- Building features in an **EXISTING** Base44 project
- `base44/config.jsonc` already exists
- Writing JavaScript/TypeScript code using Base44 SDK
- Implementing functionality, components, or features
- User mentions: "implement", "build a feature", "add functionality", "write code"
**Skill Dependencies:**
- `base44-cli` is a **prerequisite** for `base44-sdk` in new projects
- If user wants to "create an app" and no Base44 project exists, use `base44-cli` first
- `base44-sdk` assumes a Base44 project is already initialized
**State Check Logic:**
Before selecting a skill, check:
- IF (user mentions "create/build app" OR "make a project"):
- IF (`base44/config.jsonc` exists):
→ Use **base44-sdk** (project exists, build features)
- ELSE IF (app was provisioned externally — `BASE44_APP_ID`/`BASE44_PROJECTS_BASE44_APP_ID` set, or a Stripe Projects / projects.dev flow just ran):
→ Use **base44-cli** → `npx base44 scaffold` (set up local files for the existing app; do NOT `create`)
- ELSE:
→ Use **base44-cli** → `npx base44 create` (new project initialization needed)
## Project Structure
A Base44 project combines a standard frontend project with a `base44/` configuration folder:
```
my-app/
├── base44/ # Base44 configuration (created by CLI)
│ ├── config.jsonc # Project settings, site config
│ ├── .types/ # Auto-generated TypeScript types (created by `types generate`)
│ │ └── types.d.ts # Module augmentation for @base44/sdk
│ ├── entities/ # Entity schema definitions
│ │ ├── task.jsonc
│ │ └── board.jsonc
│ ├── functions/ # Backend functions (optional)
│ │ └── my-function/
│ │ └── entry.ts
│ ├── actors/ # Realtime actors (optional)
│ │ └── ChatRoom/
│ │ └── entry.ts
│ ├── agents/ # Agent configurations (optional)
│ │ └── support_agent.jsonc
│ ├── agent-skills/ # Agent skill instructions (optional)
│ │ └── pdf-export.md
│ └── connectors/ # OAuth connector configurations (optional)
│ └── googlecalendar.jsonc
├── src/ # Frontend source code
│ ├── api/
│ │ └── base44Client.js # Base44 SDK client
│ ├── pages/
│ ├── components/
│ └── main.jsx
├── index.html # SPA entry point
├── package.json
└── vite.config.js # Or your framework's config
```
**Key files:**
- `base44/config.jsonc` - Project name, description, site build settings
- `base44/entities/*.jsonc` - Data model schemas (see Entity Schema section)
- `base44/functions/*/entry.ts` - Backend function entry point
- `base44/actors/*/entry.ts` - Realtime actor entry point (optional)
- `base44/agents/*.jsonc` - Agent configurations (optional)
- `base44/agent-skills/*.md` - Agent skill instructions (optional)
- `base44/.types/types.d.ts` - Auto-generated TypeScript types for entities, functions, and agents (created by `npx base44 types generate`)
- `base44/connectors/*.jsonc` - OAuth connector configurations (optional)
- `src/api/base44Client.js` - Pre-configured SDK client for frontend use
**config.jsonc example:**
```jsonc
{
"name": "My App", // Required: project name
"description": "App description", // Optional: project description
"visibility": "public", // Optional: "public" | "private" | "workspace"
"entitiesDir": "./entities", // Optional: default "entities"
"functionsDir": "./functions", // Optional: default "functions"
"actorsDir": "./actors", // Optional: default "actors"
"agentsDir": "./agents", // Optional: default "agents"
"agentSkillsDir": "./agent-skills", // Optional: default "agent-skills"
"connectorsDir": "./connectors", // Optional: default "connectors"
"site": { // Optional: site deployment config
"installCommand": "npm install", // Optional: install dependencies
"buildCommand": "npm run build", // Optional: build command
"serveCommand": "npm run dev", // Optional: local dev server
"outputDirectory": "./dist" // Optional: build output directory
}
}
```
**Config properties:**
| Property | Description | Default |
|----------|-------------|---------|
| `name` | Project name (required) | - |
| `description` | Project description | - |
| `visibility` | App visibility: `public`, `private`, or `workspace` | - |
| `entitiesDir` | Directory for entity schemas | `"entities"` |
| `functionsDir` | Directory for backend functions | `"functions"` |
| `actorsDir` | Directory for realtime actors | `"actors"` |
| `agentsDir` | Directory for agent configs | `"agents"` |
| `agentSkillsDir` | Directory for agent skill instructions | `"agent-skills"` |
| `connectorsDir` | Directory for connector configs | `"connectors"` |
| `site.installCommand` | Command to install dependencies | - |
| `site.buildCommand` | Command to build the project | - |
| `site.serveCommand` | Command to run dev server | - |
| `site.outputDirectory` | Build output directory for deployment | - |
## Installation
Install the Base44 CLI as a dev dependency in your project:
```bash
npm install --save-dev base44
```
**Important:** Never assume or hardcode the `base44` package version. Always install without a version specifier to get the latest version.
Then run commands using `npx`:
```bash
npx base44 <command>
```
**Note:** All commands in this documentation use `npx base44`. You can also use `yarn base44`, or `pnpm base44` if preferred.
## Global `--app-id` Option
The CLI has a global `--app-id <id>` option for commands that only need an app context, not local project files.
**Resolution order:** `--app-id` flag → `BASE44_APP_ID` environment variable → local `base44/.app.jsonc`
This is useful when you want to inspect or operate on an app without switching into a linked project directory. Common examples:
```bash
# Run a one-off script against a specific app
cat ./script.ts | npx base44 exec --app-id app_123
# Fetch logs for a deployed app without a local checkout
npx base44 logs --app-id app_123 --level error
```
Use `--app-id` for app-scoped commands like `exec` and `logs`.
Do **not** use `--app-id` for commands that need local project files:
- `base44 create` creates a new app, so it rejects `--app-id`
- `base44 dev` runs from a linked local project, so it rejects `--app-id`
- `base44 deploy` still requires a local project directory because it reads local resources
## Global `--json` Option
The CLI has a global `--json` option that makes commands emit a machine-readable JSON document on stdout instead of human-oriented output. It also forces non-interactive mode (spinners/status messages/logs move to stderr), so stdout stays pure JSON — safe to pipe into `jq` or another program.
```bash
npx base44 connectors list-available --json
npx base44 logs --app-id app_123 --json
```
## Available Commands
### Authentication
| Command | Description | Reference |
| --------------- | ----------------------------------------------- | ------------------------------------------- |
| `base44 login` | Authenticate with Base44 using device code flow | [auth-login.md](references/auth-login.md) |
| `base44 logout` | Logout from current device | [auth-logout.md](references/auth-logout.md) |
| `base44 whoami` | Display current authenticated user | [auth-whoami.md](references/auth-whoami.md) |
### Project Management
| Command | Description | Reference |
|---------|-------------|-----------|
| `base44 create` | Create a new Base44 project from a template | [create.md](references/create.md) ⚠️ **MUST READ** |
| `base44 scaffold` | Scaffold a local project for an existing Base44 app (by app ID) | [scaffold.md](references/scaffold.md) |
| `base44 link` | Link an existing local project to Base44 | [link.md](references/link.md) |
| `base44 eject` | Download the code for an existing Base44 project | [eject.md](references/eject.md) |
| `base44 dashboard open` | Open the app dashboard in your browser | [dashboard.md](references/dashboard.md) |
| `base44 visibility <level>` | Set the app's visibility on the server (`public`, `private`, or `workspace`) | [visibility.md](references/visibility.md) |
### Workspace Management
Workspaces (a.k.a. organizations) group apps under shared membership. By default `base44 create`/`base44 link --create` use your personal workspace; pass `-w, --workspace <id>` to target another one.
| Command | Description | Reference |
|---------|-------------|-----------|
| `base44 workspace list` | List the workspaces you belong to | [workspace-list.md](references/workspace-list.md) |
| `base44 workspace get <workspace-id>` | Show details for a single workspace by ID | [workspace-get.md](references/workspace-get.md) |
| `base44 workspace move [workspace-id]` | Move the current app to another workspace | [workspace-move.md](references/workspace-move.md) |
### Development
| Command | Description | Reference |
|---------|-------------|-----------|
| `base44 dev` | Start local development for your Base44 backend, and your frontend too when `site.serveCommand` is configured | [dev.md](references/dev.md) |
| `base44 dev --remote` | Serve the frontend locally against the **production** backend | [dev.md](references/dev.md) |
### Deployment
| Command | Description | Reference |
|---------|-------------|-----------|
| `base44 build` | Build the site with its app id injected — use instead of a bare `npm run build` | — |
| `base44 deploy` | Deploy all resources (entities, functions, actors, agents, agent skills, connectors, auth config, and site); asks whether to build first, or pass `--build` / `--no-build` | [deploy.md](references/deploy.md) |
### Entity Management
| Action / Command | Description | Reference |
| ---------------------- | ------------------------------------------- | --------------------------------------------------- |
| Create Entities | Define entities in `base44/entities` folder | [entities-create.md](references/entities-create.md) |
| `base44 entities push` | Push local entities to Base44 | [entities-push.md](references/entities-push.md) |
| RLS Patterns | Row-level security examples and operators | [rls-examples.md](references/rls-examples.md) ⚠️ **READ FOR RLS** |
#### Entity Schema (Quick Reference)
ALWAYS follow this exact structure when creating entity files:
**File naming:** `base44/entities/{kebab-case-name}.jsonc` (e.g., `team-member.jsonc` for `TeamMember`)
**Schema template:**
```jsonc
{
"name": "EntityName",
"type": "object",
"properties": {
"field_name": {
"type": "string",
"description": "Field description"
}
},
"required": ["field_name"]
}
```
**Field types:** `string`, `number`, `integer`, `boolean`, `array`, `object`, `binary`
**String formats:** `date`, `date-time`, `time`, `email`, `uri`, `hostname`, `ipv4`, `ipv6`, `uuid`, `file`, `regex`, `richtext`
**For enums:** Add `"enum": ["value1", "value2"]` and optionally `"default": "value1"`
**Entity names:** Must be alphanumeric only (pattern: `/^[a-zA-Z0-9]+$/`)
For complete documentation, see [entities-create.md](references/entities-create.md).
### Function Management
| Action / Command | Description | Reference |
| ------------------------- | --------------------------------------------- | ------------------------------------------------------- |
| Create Functions | Define functions in `base44/functions` | [functions-create.md](references/functions-create.md) |
| `base44 functions deploy [names...] [--force]` | Deploy local functions to Base44; optionally target specific functions or prune removed ones | [functions-deploy.md](references/functions-deploy.md) |
| `base44 functions delete <names...>` | Delete one or more deployed functions from Base44 | [functions-delete.md](references/functions-delete.md) |
| `base44 functions list` | List all deployed functions on Base44 remote | [functions-list.md](references/functions-list.md) |
| `base44 functions pull [name]` | Pull deployed functions from Base44 to local files | [functions-pull.md](references/functions-pull.md) |
### Workflow Runs
Workflows are the automation system (cron schedules, entity triggers, connector events, in-app agent actions). These commands are read-only: they answer "what workflows exist" and "did my scheduled work fail, and why".
| Command | Description | Reference |
|---------|-------------|-----------|
| `base44 workflows list` | List this app's workflows with status and run summary | [workflows-list.md](references/workflows-list.md) |
| `base44 workflows runs [--status <s>] [--since <t>]` | List workflow runs, newest first; failed runs include the underlying error | [workflows-runs.md](references/workflows-runs.md) |
### Actor Management
Actors are stateful realtime server rooms over WebSockets — one live instance per room id, shared by every client connected to that id. Use them for multiplayer sessions, collaborative boards, presence and live cursors, in-room chat, and live auctions.
Actors use direct connections with SDK-managed authentication. Use verified `conn.identity` for user attribution and `this.client.asServiceRole` to persist validated room results. Actors receive no app secrets; put secret-dependent operations in a backend function. See [actors-create.md](references/actors-create.md) for the authoring contract.
| Action / Command | Description | Reference |
| ---------------- | ----------- | --------- |
| Create Actors | Define actors in `base44/actors` | [actors-create.md](references/actors-create.md) |
| `base44 actors deploy [names...]` | Deploy local actors to Base44; optionally target specific actors | [actors-deploy.md](references/actors-deploy.md) |
| `base44 actors delete <names...>` | Tear down deployed actors (destroys the published script) | [actors-deploy.md](references/actors-deploy.md#deleting-a-deployed-actor) |
#### Actor Layout (Quick Reference)
**File naming:** `base44/actors/{ActorName}/entry.ts` — the folder is the actor's identity.
```javascript
// base44/actors/ChatRoom/entry.ts
import { Actor } from "base44:runtime/actors";
export default class ChatRoom extends Actor {
handleConnect(conn) { conn.send({ type: "welcome" }); } // this client only
handleMessage(conn, msg) {
// Always validate: the payload is attacker-controlled and msg can even be null.
if (msg?.type !== "message" || typeof msg.text !== "string") return;
this.broadcast({ type: "message", text: msg.text.slice(0, 2000) }); // the whole room
}
handleClose(conn) {}
}
```
**Naming rules:** actor names become a JavaScript class binding and the WebSocket connect handler — they must match `[A-Za-z_][A-Za-z0-9_]*` (max 128 chars, no `/`, `-`, `.` or `:`), must not be a JS reserved word, must not collide with a backend function name, and cannot be nested in subfolders. The CLI checks all of this locally before uploading; a folder with a dot in its name is skipped instead (so `ChatRoom.bak/` is safe scratch space).
- Valid: `ChatRoom`, `BoardRoom`, `Lobby`
- Invalid: `chat-room`, `games/Arena`, `class`
**Required:** `entry.ts` (or `entry.js`) that **default-exports** a class extending `Actor` from `base44:runtime/actors`. In TypeScript, also declare `handleTick() {}` — it is an abstract member of `Actor`.
**Differs from functions:** only the actor's own folder is uploaded (no `base44/shared/`), no `--force` prune, no `list`/`pull` commands, no local `base44 dev` runtime, names cannot be path-like, and automations are not supported.
For complete documentation, see [actors-create.md](references/actors-create.md).
### Agent Management
Agents are conversational AI assistants that can interact with users, access your app's entities, and call backend functions. Use these commands to manage agent configurations.
| Action / Command | Description | Reference |
| ----------------------- | --------------------------------------- | ----------------------------------------------- |
| Create Agents | Define agents in `base44/agents` folder | See Agent Schema below |
| `base44 agents pull` | Pull remote agents to local files | [agents-pull.md](references/agents-pull.md) |
| `base44 agents push` | Push local agents to Base44 | [agents-push.md](references/agents-push.md) |
**Note:** Agent commands perform full synchronization - pushing replaces all remote agents with local ones, and pulling replaces all local agents with remote ones.
#### Agent Schema (Quick Reference)
**File naming:** `base44/agents/{agent_name}.jsonc` (e.g., `support_agent.jsonc`)
**Schema template:**
```jsonc
{
"name": "agent_name",
"description": "Brief description of what this agent does",
"instructions": "Detailed instructions for the agent's behavior",
"tool_configs": [
// Entity tool - gives agent access to entity operations
{ "entity_name": "tasks", "allowed_operations": ["read", "create", "update", "delete"] },
// Backend function tool - gives agent access to a function
{ "function_name": "send_email", "description": "Send an email notification" },
// Server route tool - gives agent access to one of a full-stack app's server routes
{ "tool_name": "order_summary", "route_path": "/api/orders/summary", "method": "get", "description": "Summarize the user's recent orders" }
],
"memory_config": { // Optional: lets the agent remember facts across conversations
"enabled": true,
"scope": "both", // "global" | "user" | "both"
"include_other_conversation_context": false,
"instructions": null
},
"whatsapp_greeting": "Hello! How can I help you today?"
}
```
**Naming rules:**
- Agent names must match pattern: `/^[a-z0-9_]+$/` (lowercase alphanumeric with underscores, 1-100 chars)
- Valid: `support_agent`, `order_bot`
- Invalid: `Support-Agent`, `OrderBot`
**Required fields:** `name`, `description`, `instructions`
**Optional fields:** `tool_configs` (defaults to `[]`), `memory_config`, `whatsapp_greeting`
**Tool config types:**
- **Entity tools**: `entity_name` + `allowed_operations` (array of: `read`, `create`, `update`, `delete`)
- **Backend function tools**: `function_name` + `description`
- **Server route tools** (full-stack apps): `tool_name` (1-64 chars of letters, digits, `_`, `-`) + `route_path` (app-relative, starts with a single `/`, no query string) + `method` (`get`\|`post`\|`put`\|`patch`\|`delete`, default `post`) + `description` (default `"agent server route"`)
**Memory config fields** (all optional, see [agents-push.md](references/agents-push.md#memory-configuration) for details): `enabled` (bool, default `true`), `scope` (`global`\|`user`\|`both`, default `both`), `include_other_conversation_context` (bool, default `false`), `instructions` (string\|null, default `null`)
### Agent Skills Management
Agent skills are reusable Markdown instructions that extend what your app's AI agents know how to do. Use these commands to manage them.
| Action / Command | Description | Reference |
| ----------------------------- | ----------------------------------------------- | -------------------------------------------------------------- |
| Create Agent Skills | Define skills in `base44/agent-skills` folder | [agent-skills-push.md](references/agent-skills-push.md#agent-skill-file-format) |
| `base44 agent-skills pull` | Pull remote agent skills to local files | [agent-skills-pull.md](references/agent-skills-pull.md) |
| `base44 agent-skills push` | Push local agent skills to Base44 | [agent-skills-push.md](references/agent-skills-push.md) |
**Note:** Agent skill commands perform full synchronization - pushing replaces all remote skills with local ones, and pulling replaces all local skills with remote ones.
#### Agent Skill Schema (Quick Reference)
**File naming:** `base44/agent-skills/{skill-name}.md` (e.g., `pdf-export.md`)
**Schema template:**
```markdown
---
description: Export the current report as a PDF and attach it to the conversation.
---
Use this skill when the user asks to export, download, or share a report as a PDF.
1. Call the `generate_report_pdf` function with the current report's entity ID.
2. Attach the returned file URL in your reply.
```
**Naming rules:** Skill names (the file name minus `.md`) must match pattern `/^[a-z0-9]+(-[a-z0-9]+)*$/` (lowercase, hyphen-separated, 1-64 chars)
- Valid: `pdf-export`, `order-lookup`
- Invalid: `PdfExport`, `pdf_export`
**Required fields:** `description` (frontmatter, 1-1024 chars), body (Markdown content, 1-15000 chars)
For complete documentation, see [agent-skills-push.md](references/agent-skills-push.md).
### Connector Management
Connectors let your app connect to external services (Google Calendar, Slack, Stripe, etc.). Most connectors use OAuth to provide access tokens for backend functions to call external APIs. Stripe is the exception — it is provisioned automatically on the server side with no OAuth browser flow.
| Action / Command | Description | Reference |
| ---------------------------------- | ---------------------------------------------------- | ------------------------------------------------------------------- |
| Create Connectors | Define connectors in `base44/connectors` folder | [connectors-create.md](references/connectors-create.md) |
| `base44 connectors list-available` | List all available integration types from Base44 | [connectors-list-available.md](references/connectors-list-available.md) |
| `base44 connectors initiate --integration-type <t> [--scopes <s...>]` | Initialize a connector and start its OAuth flow; works projectless with `--app-id` | [connectors-initiate.md](references/connectors-initiate.md) |
| `base44 connectors pull` | Pull remote connectors to local files | [connectors-pull.md](references/connectors-pull.md) |
| `base44 connectors push` | Push local connectors to Base44 | [connectors-push.md](references/connectors-push.md) |
**Note:** Connector commands perform full synchronization - pushing replaces all remote connectors with local ones (and triggers OAuth for new OAuth connectors), and pulling replaces all local connectors with remote ones.
#### Connector Schema (Quick Reference)
**File naming:** `base44/connectors/{type}.jsonc` (e.g., `googlecalendar.jsonc`, `slack.jsonc`)
**Schema template:**
```jsonc
{
"type": "googlecalendar",
"scopes": [
"https://www.googleapis.com/auth/calendar.readonly",
"https://www.googleapis.com/auth/calendar.events"
]
}
```
**Required fields:** `type`
**Optional fields:** `scopes` (defaults to `[]`)
**Available connector types:** Run `npx base44 connectors list-available` to see all supported integration types.
**Note:** `stripe` is also a valid connector type but is not returned by `list-available`. Treat it as a supported type — it is provisioned automatically by Base44 with no OAuth browser flow. See [connectors-create.md](references/connectors-create.md) for details.
For complete documentation, see [connectors-create.md](references/connectors-create.md).
### Auth Configuration
Manage your app's authentication settings (e.g., username & password login). Auth config is stored in `base44/auth/` and synced with Base44 via `auth push`/`auth pull`.
| Command | Description | Reference |
|---------|-------------|-----------|
| `base44 auth password-login <enable\|disable>` | Enable or disable username & password authentication | [auth-password-login.md](references/auth-password-login.md) |
| `base44 auth social-login <provider> <enable\|disable>` | Enable or disable social login (google, microsoft, facebook, apple) | [auth-social-login.md](references/auth-social-login.md) |
| `base44 auth sso <enable\|disable>` | Configure SSO identity provider (google, microsoft, github, okta, custom) | [auth-sso.md](references/auth-sso.md) |
| `base44 auth pull` | Pull auth config from Base44 to local files | [auth-pull.md](references/auth-pull.md) |
| `base44 auth push` | Push local auth config to Base44 | [auth-push.md](references/auth-push.md) |
**Note:** Auth config is also deployed as part of `base44 deploy`.
### Secrets Management
Manage project secrets (environment variables stored securely in Base44). These commands are hidden from `--help` output but are f...
© base44 · MIT · base44/skills