Skip to main content
prompt GP ChatGPT

spoken — Claude Code prompt: what it does, how to install

This Claude Code prompt marks answer content that should stay on screen rather than be spoken aloud. It handles items such as code blocks, tables, links, and images.

MIT ★ 395 updated 2026-11-16

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/commands/spoken.md
Open on GitHub

What spoken does

The prompt creates short stand-ins for parts of an answer that should remain visible but should not be read aloud. The voice model can tell that the screen contains an item, such as a code block or a link.

The template handles code, tables, links, images, file paths, lines, hashes, and code snippets. English and Japanese have dedicated branches; other languages use a separate fallback branch. In Claude Code, place the command file at .claude/commands/spoken.md.

What it helps with

  • mark a code block for the voice model without reading it aloud
  • signal that a link or image remains on screen
  • refer to a file path without speaking its contents

Example prompts for the agent

  • Prepare this answer for speech: keep the code block on screen and tell the voice model it is there.
  • Mark the link with a short spoken placeholder.
  • Leave voice/spoken.go visible, but do not read its contents aloud.

How to install spoken

Manually: put the files in place

.claude/commands/spoken.md

Questions about spoken

How do I install spoken in Claude Code?

Place the command file at .claude/commands/spoken.md.

What does spoken do?

It replaces answer content that should not be spoken with short labels. The voice model is told that the content is visible on screen.

Which content types does spoken handle?

The template distinguishes code blocks, tables, links, images, file paths and lines, hashes, and code snippets.

Source text

spoken.md · MIT
{{- /* Stand-ins for what an answer holds that is not to be read out (voice/spoken.go): the voice model hears that it is
there and that the screen has it. */ -}}
{{- if eq .Lang "en" -}}
{{- if eq .Kind "code"}}(a code block of {{.N}} {{if eq .N 1}}line{{else}}lines{{end}}, on the screen)
{{- else if eq .Kind "table"}}(a table of {{.N}} {{if eq .N 1}}row{{else}}rows{{end}}, on the screen)
{{- else if eq .Kind "link"}}(a link)
{{- else if eq .Kind "image"}}(an image)
{{- else if eq .Kind "path"}}the file {{.Name}}
{{- else if eq .Kind "line"}}line {{.N}} of {{.Name}}
{{- else if eq .Kind "hash"}}(a hash)
{{- else if eq .Kind "snippet"}}(a piece of code)
{{- else}}(… the middle is left out; the whole answer is on the screen …)
{{- end -}}
{{- else if eq .Lang "ja" -}}
{{- if eq .Kind "code"}}({{.N}} 行のコード、画面に表示)
{{- else if eq .Kind "table"}}({{.N}} 行の表、画面に表示)
{{- else if eq .Kind "link"}}(リンク)
{{- else if eq .Kind "image"}}(画像)
{{- else if eq .Kind "path"}}ファイル {{.Name}}
{{- else if eq .Kind "line"}}{{.Name}} の {{.N}} 行目
{{- else if eq .Kind "hash"}}(ハッシュ)
{{- else if eq .Kind "snippet"}}(コード)
{{- else}}(……中略、全文は画面に……)
{{- end -}}
{{- else -}}
{{- if eq .Kind "code"}}(一段 {{.N}} 行的代码,在屏幕上)
{{- else if eq .Kind "table"}}(一张 {{.N}} 行的表,在屏幕上)
{{- else if eq .Kind "link"}}(一个链接)
{{- else if eq .Kind "image"}}(一张图)
{{- else if eq .Kind "path"}}文件 {{.Name}}
{{- else if eq .Kind "line"}}文件 {{.Name}} 第 {{.N}} 行
{{- else if eq .Kind "hash"}}(一串哈希)
{{- else if eq .Kind "snippet"}}(一段代码)
{{- else}}(……中间省略,全文在屏幕上……)
{{- end -}}
{{- end -}}

© nwverse · MIT · nwverse/persona

Similar prompts

All prompts for Agent setup: memory, context, orchestration →

From the same set61

The whole set →
memory_dream The memory_dream Claude Code prompt maintains a short note of stable user preferences and recurring workflows. It updates the note with explicit corrections and recent messages. GP ChatGPT ★ 395repo stars room_header The room_header prompt for Claude Code sets the context at the start of a meeting room. It passes along the title, start time, language, and assistant role. GP ChatGPT ★ 395repo stars pick The pick Claude Code prompt selects a tool and its arguments for a Persona subscription. It sets up recurring pulls of new data from an app source. GP ChatGPT ★ 395repo stars workout_report workout_report — a Claude Code prompt that turns workout measurements into a report. It charts heart rate and pace, then compares the session with recent workouts of the same activity. GP ChatGPT ★ 395repo stars answer_input The answer_input Claude Code prompt builds an answer from meeting context. It can use spoken lines, calendar details, photos, and notes from earlier meetings. GP ChatGPT ★ 395repo stars followup_seed The followup_seed Claude Code prompt prepares the opening message for a meeting follow-up. It places meeting material in context before the owner’s message. GP ChatGPT ★ 395repo stars map This Claude Code prompt defines how to read responses from a Persona subscription tool. It maps a sample response to fields, item types, and grouping rules. GP ChatGPT ★ 395repo stars answer This Claude Code prompt answers questions using material from a recorded meeting. If no question was typed, it picks the latest spoken question addressed to Persona or the meeting owner. GP ChatGPT ★ 395repo stars

Project sponsors

Companies that keep this analytics open