Skill

capture-voice-idea

Capture a business idea from a voice memo / audio file. Transcribes the recording, preserves the raw transcript, then hands off to capture-idea so the user can optionally generate executive summary, elevator pitch, technical deep-dive, and timeline variants. Use when the user has an audio file or recording of an idea pitch.

npx claudepluginhub danielrosehill/claude-code-plugins --plugin business-idea-eval

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Pipeline: audio → transcript → structured idea workspace.

SKILL.md

Similar Skills

skill-lookup

159.9k

Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.

prompts.chat

next-compile

139.2k

Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.

1 file

vercel-next-js-2

angular-new-app

100.1k

Creates new Angular apps using Angular CLI with flags for routing, SSR, SCSS, prefixes, and AI config. Follows best practices for modern TypeScript/Angular development. Use when starting Angular projects.

angular-angular-1

Stats

Stars0

Forks0

Last CommitApr 28, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

capture-voice-idea

Capture Idea (voice)

Pipeline: audio → transcript → structured idea workspace.

Steps

Resolve config (workspace path, user context).

Take the audio file path from the user. Verify it exists and looks like an audio file.

Transcribe. Prefer the claude-transcription plugin's skills if installed:

claude-transcription:transcribe-gemini-cleaned — fastest path, removes filler words
claude-transcription:transcribe-gemini-raw — verbatim if the user wants every word preserved
Fallback: prompt the user to install claude-transcription or supply an existing transcript.

Save the raw transcript to a temp path. Show the user a short preview (first ~200 words) before proceeding.

Hand the transcript to capture-idea:

Pass the transcript text as the raw input
Tag the resulting idea.md frontmatter with source: voice and audio_file: <original-path>
Copy the audio file (or symlink) into <workspace_path>/ideas/<idea-slug>/source-audio.<ext> so the recording stays with the workspace

Continue through capture-idea's formatted-variant menu so the user can pick which derived versions to generate.

Notes

Voice captures often contain digressions and false starts. Prefer the cleaned transcription unless the user explicitly wants raw.

For long recordings (>30 min), suggest claude-transcription:truncate-silence first.

Always preserve the original audio file in the workspace — it's the ultimate source.

Capture Idea (voice)

Pipeline: audio → transcript → structured idea workspace.

Steps

Resolve config (workspace path, user context).
Take the audio file path from the user. Verify it exists and looks like an audio file.
Transcribe. Prefer the claude-transcription plugin's skills if installed:
- claude-transcription:transcribe-gemini-cleaned — fastest path, removes filler words
- claude-transcription:transcribe-gemini-raw — verbatim if the user wants every word preserved
- Fallback: prompt the user to install claude-transcription or supply an existing transcript.
Save the raw transcript to a temp path. Show the user a short preview (first ~200 words) before proceeding.
Hand the transcript to capture-idea:
- Pass the transcript text as the raw input
- Tag the resulting idea.md frontmatter with source: voice and audio_file: <original-path>
- Copy the audio file (or symlink) into <workspace_path>/ideas/<idea-slug>/source-audio.<ext> so the recording stays with the workspace
Continue through capture-idea's formatted-variant menu so the user can pick which derived versions to generate.

Notes

Voice captures often contain digressions and false starts. Prefer the cleaned transcription unless the user explicitly wants raw.
For long recordings (>30 min), suggest claude-transcription:truncate-silence first.
Always preserve the original audio file in the workspace — it's the ultimate source.