cleanunicorn

Earheart — Development skill for Claude Code

Development community

Talk to your coding agents — press a hotkey, speak your prompt, and it lands in Claude Code, Codex, or Cursor.

How to install Earheart

This entry records only its repository, not the path inside it, so there is no exact command to give. Open cleanunicorn/earheart and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Earheart does

Talk to your coding agents — press a hotkey, speak your prompt, and it lands in Claude Code, Codex, or Cursor. Fully local voice dictation (Parakeet + Gemma), nothing leaves your machine. Windows, macOS & Linux.

Alternatives in Development

Device Control Agent — You are an autonomous macOS agent with full control of this device via two CLI tools: - steer — GUI automation 250 ★
LiveBrowser — Browser tools (browser_navigate, browser_get_state, browser_snapshot, browser_get_text, browser_click, browser 250 ★
Ctthandoff — Generate a handoff summary, copy to clipboard, and speak via Tabz TTS 146 ★

README

Earheart

Talk to your coding agents.
Press a hotkey, speak your prompt, press again — it lands in Claude Code, Codex, Cursor, or whatever else has focus.
Fully local. No cloud, no account, nothing leaves your machine.

Earheart overlay showing a live transcript while recording
Earheart overlay showing a progress bar while the transcript is cleaned up
Earheart overlay confirming the transcript was pasted

The overlay transcribes live as you speak, shows progress while it finishes up, then confirms where the text landed — without stealing focus.

Working with an agent is a conversation, but you type it like a form. The prompts that actually work are long — context, constraints, the three things you already tried, the "no, not like that." Typing all of that is the slow part of the loop, and the reason people send a one-liner instead and then spend four turns correcting it.

Earheart turns that part into talking. Press a global hotkey, say what you want, press it again: your speech is transcribed on-device (NVIDIA Parakeet), tidied up on-device (a small Gemma model drops the *ums*, false starts and backtracking), and **pasted straight into whatever app has focus** — the terminal running Claude Code, the Codex composer, Cursor's chat box, a GitHub issue, an email.

**Nothing leaves your machine**, which matters more for agent prompts than for ordinary dictation: what you say to an agent is your own code, your file layout, your architecture, your unshipped work. Out of the box both models run **inside the app, on your computer** — n