agentleFS
andrmazandrmaz/spec-driven-architecture/.agents/skills/cli/SKILL.md

cli

Skill1 starsChanged 9 months agoMITView on GitHub

Tambo CLI reference for project setup and component installation. Agent-friendly with non-interactive mode and exit codes. Use when running tambo init, tambo add, npx tambo commands, or browsing the component library. For guided project creation with tech recommendations, use start-from-scratch skill. For adding Tambo to existing projects, use add-to-existing-project skill.

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use desktop, api and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • zjl4616Skill

    desktop

    桌面操控。让 CC 看屏幕、动鼠标、点按钮、输文字。基于 macOS 原生 OCR 触觉反馈,不截全屏传 AI,极致省 token。触发词:"/desktop"、"帮我操作桌面"、"点一下那个按钮"、"看看屏幕上有什么

    Also in 4 projects that use this

  • VercelSkill

    api

    Publish HTTP handlers for external webhooks and callbacks on this agent's subdomain.

    Also in 5 projects that use this

  • VercelSkill

    mcp

    MCP Apps integration for json-render. Use when building MCP servers that render interactive UIs in Claude, ChatGPT, Cursor, or VS Code, or when integrating json-render with the Model Context Protocol.

    Also in 5 projects that use this

  • NVIDIASkill

    testing

    Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.

    Also in 4 projects that use this

The file

Files
SKILL.md

Tambo CLI

Agent-friendly CLI for project setup and component management.

Quick Start

npx tambo init --api-key=sk_...              # Initialize with API key
npx tambo add message-thread-full --yes      # Add a component
npx tambo create-app my-app --template=standard  # New app from template

Non-Interactive Mode

The CLI detects non-interactive environments and returns guidance instead of hanging:

# In CI or piped environments, this returns guidance (exit 2) instead of prompting
npx tambo init
# Error: Project name required.
# Run one of:
#   tambo init --project-name=myapp    # Create new project
#   tambo init --project-id=abc123     # Use existing project

Detection Logic

Non-interactive when ANY of these are true:

  • process.stdin.isTTY is false (piped input)
  • process.stdout.isTTY is false (piped output)
  • CI environment variable is set
  • GITHUB_ACTIONS=true

Override with FORCE_INTERACTIVE=1 (requires real TTY).

Exit Codes

CodeMeaning
0Success
1Error (network, invalid args, etc.)
2User action required - check stderr for exact command

Commands for Agents

Initialize Project

# Option 1: Direct API key (simplest for agents)
npx tambo init --api-key=sk_...

# Option 2: Create new project (requires prior auth)
npx tambo init --project-name=myapp

# Option 3: Use existing project
npx tambo init --project-id=abc123

# Skip all prompts with defaults
npx tambo init --yes --project-name=myapp

Add Components

npx tambo add form --yes                    # Skip confirmation
npx tambo add form graph --yes              # Multiple components
npx tambo add form --prefix=src/components  # Custom directory
npx tambo add form --dry-run                # Preview changes
npx tambo add form --legacy-peer-deps       # For dependency conflicts

Component Library

Browse and preview all components at ui.tambo.co.

Available Components

ComponentDescription
message-thread-fullComplete message thread with all content and interactions
message-thread-panelMessage thread in a side panel or modal context
message-thread-collapsibleMessage threads that can be expanded or collapsed
messageIndividual messages with markdown support
message-inputComposes and sends messages in a conversation
message-suggestionsAI-generated suggestions to help users compose responses
control-barControls and actions in the interface
input-fieldsReusable input fields with styles and validation
graphVisualizes graph-based data structures
formCollects user input with validation support
mapInteractive map with clustering and heatmap support
canvas-spaceDisplays rendered components from chat messages
thread-historyChronological history of a conversation thread
thread-dropdownDropdown menu for collapsible chat threads
thread-contentDisplays messages within a thread
scrollable-message-containerContainer that auto-scrolls to new messages
edit-with-tambo-buttonInline AI editor button for interactable components
elicitation-uiMCP elicitation UI for user input requests
mcp-componentsMCP prompt and resource picker buttons

What You Get

Each component includes:

  • Source code copied to your project (not a dependency)
  • Tambo integration pre-configured with hooks
  • Styling via Tailwind CSS (customizable)
  • TypeScript with full type definitions

Example: Full Chat Interface

npx tambo add message-thread-full control-bar --yes

This adds a complete chat UI with:

  • Message history display
  • AI-generated component rendering
  • Input bar with send button
  • Streaming status indicators

List Components (No Prompts)

npx tambo list --yes

Create New App

npx tambo create-app my-app --template=standard

Authentication

npx tambo auth login --no-browser   # Prints URL instead of opening browser
npx tambo auth status               # Check current auth (no prompts)

Full Setup (One Command)

npx tambo full-send    # Complete setup with components

Agent Docs

The CLI auto-creates/updates AGENTS.md with Tambo documentation:

npx tambo add form --yes   # Also updates AGENTS.md

The generated section includes CLI commands formatted for non-interactive use.

Key Flags Summary

FlagCommandsPurpose
--yes, -yinit, add, listSkip all prompts
--api-keyinitDirect API key input
--project-nameinitCreate new project
--project-idinitUse existing project
--no-browserauth loginOutput URL instead of opening
--dry-runaddPreview without installing
--prefixadd, listCustom component directory

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.