πŸŽ™οΈ
AI EngineeringPython

Input Branching

by autonomous-ai

Input Branching is an AI Engineering skill for Claude Code, published by autonomous-ai in autonomous-os.

258 stars39 forkson autonomous-ai/autonomous-osAdded 2026/09/02+23% in starsRepository updated 2026/08/30
agentic-aiai-agentsclaude-codeembeddedllmopen-source-roboticsopenclawoperating-systemphysical-airaspberry-pireachy-miniroboticsrobotsvoice-assistant
Install in seconds
Install Input Branching
Copy Input Branching into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/autonomous-ai/autonomous-os/tree/main/skills/input-branching ~/.claude/skills/input-branching

Requires Node.js. Downloads this skill only β€” not the rest of the repository β€” into your Claude Code skills folder.

Without Node.js

git clone https://github.com/autonomous-ai/autonomous-os.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/input-branching/SKILL.md in autonomous-ai/autonomous-os
Installs to
~/.claude/skills/input-branching
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering β€” 2631 skills

What Input Branching does

Input Branching routes realtime voice-agent messages using tags like [voice-instruction], [transcript], and [HANDLED]. It is used to choose the correct input path, ignore noisy transcripts, and return NO_REPLY for handled history entries.

Input Branching is cataloged under AI Engineering on DirSkills. Input Branching comes from a repository tagged agentic-ai, ai-agents, claude-code, embedded and llm.

Documentation

README

Input Branching

Voice input passes through a realtime voice agent before reaching you. The agent handles chit-chat directly and delegates everything else. Message tags tell you which path was taken.

Message Formats

Delegated with instruction

[voice-instruction] Play jazz music on Spotify
[transcript] play some jazz please on spotify
  • [voice-instruction] β€” the realtime agent's clean summary of what the user wants. Use this as the primary input.
  • [transcript] β€” raw STT transcript. Often inaccurate β€” STT is locked to one language while the user may speak another. Treat as noisy supplementary context only, never as the source of truth.

Delegated without instruction (fallback)

turn on the lights

No tags. Process as a normal voice event.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Input Branching

  • What else does autonomous-ai publish alongside Input Branching?

    Input Branching is one of 25 skills that DirSkills catalogs from autonomous-ai/autonomous-os, the repository it ships in. Its siblings there include Audio Control, Camera and Claude Buddy. Each one is a separate skill with its own page in this directory, installs the same way Input Branching does, and is maintained by autonomous-ai in that same repository. The rest of the collection is listed on the autonomous-ai/autonomous-os page.

  • How does Input Branching compare to other AI Engineering skills?

    Input Branching ranks #2281 by stars among the 2631 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Input Branching against them. Open each page to compare what they document and how they install.

More from autonomous-ai/autonomous-os

Input Branching is one of 25 skills cataloged on DirSkills from autonomous-ai/autonomous-os.

See all 25 skills β†’
πŸ”Š
1h ago

Audio Control

Audio Control adjusts speaker volume, plays test tones, and records raw microphone audio. Use it for hardware-level audio tasks like muting, diagnostics, or capturing WAV input, not for speech output.
Automation
25839
πŸ“·
1h ago

Camera

Camera controls the device camera to take snapshots, view a live stream, and toggle privacy. Use it when asked to look at something or to turn the camera on or off.
Automation
25839
πŸ—£οΈ
1h ago

Claude Buddy

Claude Buddy coordinates with Claude Desktop and Claude Code on a Mac by relaying approval prompts and activity state. Use it when you need to answer tool permission requests by voice instead of clicking.
AI Engineering
25839
πŸ’»
1h ago

Computer Use

Computer Use controls a paired Mac through Autonomous Buddy to open apps, navigate URLs, type, use shortcuts, copy text, and click labeled UI elements. Use it for explicit requests to do something on the user's computer; use vision for screen-reading or unlabeled UI tasks.
Automation
25839
πŸ”—
1h ago

Connectors

Connectors detects which linked services are available on this device and uses them to answer questions or take actions in Gmail, Calendar, Drive, Notion, Figma, Asana, Linear, and GitHub. Use it when you need to check connections or work with a connected account.
Automation
25839
πŸ–₯️
1h ago

Display

Display controls the device’s round LCD for manual eye expressions or brief info text like time and weather. Use it only when you need direct display changes; normal conversation reactions are auto-synced by Emotion.
Automation
25839