vault-ingest

Captures voice memos, images, PDFs, and YouTube videos into an Obsidian vault as fleeting notes.

2|Updated Apr 4, 2026
One-click install
npx skills add https://github.com/DoctorMozg/claude-pipelines --skill vault-ingest-doctormozg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vault-ingest
Source: https://github.com/DoctorMozg/claude-pipelines/tree/main/plugins/mz-knowledge/skills/vault-ingest
Command: npx skills add https://github.com/DoctorMozg/claude-pipelines --skill vault-ingest-doctormozg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Getting raw multimodal content — voice memos, screenshots, PDFs, YouTube videos — into a personal knowledge vault requires manual transcription, OCR, and note formatting. This Skill automates that intake pipeline so every capture lands in the vault inbox as a properly frontmattered fleeting note. ## Core Features & Use Cases - Multimodal capture: Detects input modality (voice, image, PDF, YouTube) from file extension or URL and selects the right transcription or OCR tool (whisper-cpp, tesseract, pdftotext, yt-dlp) with fallback support. - Approval-gated writes: Presents the verbatim transcript for user approval before anything is written to the vault, with a feedback loop to retry with a different tool. - Provenance-rich notes: Writes fleeting notes to the vault inbox with status: draft, type: fleeting, source_type, and captured_at so downstream skills like process-notes can atomize them later. - Use Case: Record a voice memo on your phone, drop the .m4a file into your project, and have it transcribed, reviewed, and filed as an inbox note ready for later atomization into permanent notes. ## Quick Start Capture the attached voice memo into my Obsidian vault as a fleeting note using vault-ingest.

Frequently Asked Questions about vault-ingest

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe a voice memo into an Obsidian note?

Provide the audio file path (.m4a, .wav, or .mp3) and the skill detects the voice modality, transcribes it with whisper-cpp or the whisper fallback, shows you the transcript for approval, then writes a fleeting note to your vault inbox.

How do I capture a YouTube video as a note in Obsidian?

Pass the YouTube URL as the input. The skill uses yt-dlp to download auto-generated subtitles, strips VTT timestamps and duplicate lines, and files the cleaned transcript as a fleeting note after your approval.

What OCR tools does image capture support?

Image capture uses ocrit on macOS as the primary tool with tesseract as the fallback. If neither is installed, the skill escalates with the brew install command and lets you retry or abort.

What happens if the transcription tool is not installed?

The skill runs which checks for all tools before dispatching and records results to tooling.md. If the required tool is missing, it names the install command and asks whether to retry after installation or abort the capture.

Does vault-ingest create permanent notes automatically?

No. Every capture is written as a fleeting note with status: draft and the inbox tag. Promotion to permanent notes is a separate explicit step run through the process-notes skill, which the skill offers as a follow-up.

Why is my captured note empty or missing content?

The skill never writes an empty note — if transcription produces no body, it asks whether to retry with the fallback tool or abort. An empty capture indicates the run was aborted before the write phase.