apple-voice-memos

Extract and process transcripts from Apple Voice Memos synced via iCloud. Use when the user wants to access, read, or summarize voice memos.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "apple-voice-memos" with this command: npx skills add jessedc/claude-apple-voice-memos-skill/jessedc-claude-apple-voice-memos-skill-apple-voice-memos

Apple Voice Memos

Extract and process transcripts from Apple Voice Memos synced via iCloud.

Prerequisites

Voice Memos must be synced with iCloud on macOS.

Tools

This skill includes two scripts in its scripts/ directory:

  • extract-apple-voice-memos-metadata — Queries the CloudRecordings.db SQLite database (read-only) and outputs CSV with columns: title, date, duration, path. Returns the 30 most recent recordings.
  • extract-apple-voice-memos-transcript — Extracts the embedded transcript from a .m4a file's tsrp atom. Outputs timestamped text with filler words removed, intelligent line breaks, and paragraph breaks at natural pauses.

Step 1: Select a voice memo

Run the metadata script to list recent recordings:

python3 scripts/extract-apple-voice-memos-metadata

Present the results as a numbered list showing title, date, and duration. Ask the user which memo they'd like to work with.

Error handling:

  • "Database not found" → Voice Memos iCloud sync is not enabled on this Mac.

Step 2: Extract the transcript

Run the transcript script with the path value from the selected recording:

python3 scripts/extract-apple-voice-memos-transcript "<FILENAME>.m4a"

Present the timestamped transcript to the user.

Error handling:

  • "tsrp atom not found" → This recording does not have an embedded transcript. Apple generates transcripts on-device and not all recordings will have one.
  • File not found → The recording file may not have synced to this Mac yet.

Step 3: Process the transcript

Read PROMPT.md from this skill's directory. Append the transcript after the ## Transcript heading. Send the complete prompt and transcript to a subagent with fresh context for processing.

The subagent will produce a structured markdown document with narrative summary, detailed notes, asides, and action items. Present this output to the user.

After presenting the output, ask the user if they'd like to save it as a markdown file. Suggest a filename in the format YYYY-MM-DD-slugified-title.md derived from the memo's title and date (e.g., 2026-02-04-the-soul-of-a-new-machine.md). Save to the current working directory by default. The user may accept, provide a different name or path, request adjustments to the content first, or skip saving.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

test_skill

import json import tkinter as tk from tkinter import messagebox, simpledialog

Archived SourceRecently Updated
General

错敏信息检测

1. 安装https://clawhub.ai/xxxx/sensitive-check-skill 这个技能 2. 调用错敏信息检测技能,传入参数 userKey=xxxx,content=xxxx

Archived SourceRecently Updated
General

neo

Browse websites, read web pages, interact with web apps, call website APIs, and automate web tasks. Use Neo when: user asks to check a website, read a web page, post on social media (Twitter/X), interact with any web app, look up information on a specific site, scrape data from websites, automate browser tasks, or when you need to call any website's API. Keywords: website, web page, browse, URL, http, API, twitter, tweet, post, scrape, web app, open site, check site, read page, social media, online service.

Archived SourceRecently Updated
General

image-gen

Generate AI images from text prompts. Triggers on: "生成图片", "画一张", "AI图", "generate image", "配图", "create picture", "draw", "visualize", "generate an image".

Archived SourceRecently Updated