# Vault Ingest

> ALWAYS invoke when capturing voice memos, screenshots, PDFs, YouTube videos, or images into the vault as fleeting notes. Triggers ingest audio, transcribe voice, capture screenshot, ingest PDF, capture YouTube.

- **Type:** Skill
- **Install:** `agentstack add skill-doctormozg-claude-pipelines-vault-ingest`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [DoctorMozg](https://agentstack.voostack.com/s/doctormozg)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [DoctorMozg](https://github.com/DoctorMozg)
- **Source:** https://github.com/DoctorMozg/claude-pipelines/tree/master/plugins/mz-knowledge/skills/vault-ingest

## Install

```sh
agentstack add skill-doctormozg-claude-pipelines-vault-ingest
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Vault Ingest

## Overview

Discipline skill for multimodal capture into the vault as fleeting notes. Detects input modality (voice, image, PDF, YouTube, screenshot), verifies the required transcription or OCR tool is installed, dispatches `capture-normalizer` to produce a clean transcript, presents the transcript for user approval, and writes a frontmatter-annotated fleeting note to the vault inbox. Every capture produces a note with `status: draft`, `type: fleeting`, and full provenance fields so downstream skills (`process-notes`, `vault-schema`) can reason about it.

## When to Use

- Ingesting voice memos (`.m4a`, `.wav`, `.mp3`) into the vault with transcription.
- Capturing screenshots or images (`.png`, `.jpg`, `.heic`) via OCR.
- Importing PDF content into a single fleeting note.
- Capturing YouTube videos via auto-subtitle download.

### When NOT to use

- Processing fleeting notes that are already in the vault — use `process-notes`.
- Atomizing long captured notes into permanent atomic notes — use `process-notes` as a follow-up after capture.
- Proposing `[[wikilinks]]` between notes — use `vault-connect`.
- Importing research reports or brainstorm outputs — use `vault-research`.

## Constants

- **TASK_DIR**: `.mz/task/`
- **INBOX_FOLDER**: `inbox/`
- **MAX_TRANSCRIPT_PREVIEW**: 500 (words shown in the approval gate; longer transcripts are truncated with `...`)
- **VOICE_MAX_DURATION_SEC**: 3600 (warn before transcribing audio longer than 1 hour)
- **PDF_MAX_PAGES**: 50 (warn before extracting from PDFs longer than this)

## Core Process

| Phase | Goal                         | Details                           |
| ----- | ---------------------------- | --------------------------------- |
| 0     | Setup                        | Inline below                      |
| 1     | Detect tooling + transcribe  | `phases/detect_and_transcribe.md` |
| 1.5   | User approval — transcript   | Inline below                      |
| 2     | Write fleeting note to vault | `phases/approve_and_write.md`     |

### Phase 0: Setup

1. Parse `$ARGUMENTS`. First argument is the input path or URL. Second argument (optional) is an explicit modality hint: `voice`, `image`, `pdf`, or `youtube`.
1. If the first argument is empty, ask the user via AskUserQuestion what to ingest. Never guess.
1. Detect modality from the input:
   - Extension `.m4a`, `.wav`, `.mp3` → `voice`.
   - Extension `.png`, `.jpg`, `.jpeg`, `.heic` → `image` (record `source_type: screenshot` if user confirmed it is a screenshot, else `image`).
   - Extension `.pdf` → `pdf`.
   - URL containing `youtube.com` or `youtu.be` → `youtube`.
   - If the second argument is present, it overrides the detected modality.
   - If modality cannot be inferred and no hint was given, ask via AskUserQuestion.
1. Resolve the vault path with precedence: `$OBSIDIAN_VAULT_PATH` → `$MZ_VAULT_PATH` → walk up from cwd to the nearest `.obsidian/` directory. If none found, ask via AskUserQuestion.
1. Derive `task_name = _vault-ingest_` where `` is today's date (underscores); on same-day collision append `_v2`, `_v3`. Create `TASK_DIR/` on disk.
1. Write `state.md` with `schema_version: 2`, `Status: running`, `Phase: 0`, `Started: `, `Input: `, `Modality: `, `Vault: `, `phase_complete: false`, `what_remains: []`.

### Phase 1.5: User Approval — Transcript

**This orchestrator** (not a subagent) presents this gate. This step is interactive and must not be delegated.

**Pre-read**: Read `.mz/task//transcript.md` and capture the full contents into context. Note the modality, tool, and duration/pages from the frontmatter.

**Surface 1 — emit the plan message.** Output the transcript verbatim as a normal markdown chat message (truncated at `MAX_TRANSCRIPT_PREVIEW` words with a trailing `...` when longer):

```
## Transcript ready for review — vault-ingest

Transcript produced from . Modality: , transcription tool: , duration/pages: .

---
**Approve** → proceed to Phase 2, write the fleeting note to the vault  ·  **Reject** → task marked aborted, no fleeting note written  ·  reply with feedback to revise
```

Emit the full verbatim contents of `.mz/task//transcript.md` (transcript body, up to `MAX_TRANSCRIPT_PREVIEW` words) — do not substitute a path, summary, or placeholder.

**Surface 2 — call AskUserQuestion.** A short selector — do not re-embed the transcript in the question body, it lives in the plan message above:

- question: `The transcript above is ready for review.`
- options:
  - **Approve** — proceed to Phase 2, write the fleeting note to the vault
  - **Reject** — abort, no fleeting note written

Response handling:

- **Approve** → update state to `transcript_approved`, proceed to Phase 2.
- **Reject** → update state to `aborted_by_user` and stop. Do not proceed.
- **Any other reply (feedback)** → common feedback is "try a different tool" (switch `whisper-cpp` → `whisper`, `ocrit` → `tesseract`) or "the transcript is truncated, rerun". Incorporate the feedback, re-run Phase 1 with the adjusted tool choice, return to this gate, re-read `.mz/task//transcript.md`, and re-emit the entire plan message from scratch (never diff-only). This is a loop — repeat until the user explicitly approves. Never proceed to Phase 2 without explicit approval.

## Techniques

Techniques: delegated to phase files — see Phase Overview table above.

## Common Rationalizations

| Rationalization                                                               | Rebuttal                                                                                                                                                                                         |
| ----------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| "The tool is missing — just write an empty fleeting note with a source link." | "An empty note with provenance metadata masquerading as captured content is worse than no note at all — it pollutes future search and appears 'processed' when it is not. Escalate via BLOCKED." |
| "Skip the approval gate — the user already chose to capture this."            | "Tool output is noisy: VTT timestamps survive, whisper inserts `[inaudible]`, OCR mangles layout. The approval gate exists so the user sees what the vault will actually contain."               |
| "Transcript has garbage — ship it anyway, the user can fix it in Obsidian."   | "Captured notes are the raw intake layer for the entire pipeline. Bad captures propagate into atomization, linking, and Q&A. Either a fallback tool recovers quality or the user says BLOCKED."  |

## Red Flags

- Dispatching `capture-normalizer` before running `which ` detection.
- Writing a fleeting note with an empty body because the transcription tool failed.
- Presenting the approval gate as a path or one-line status instead of the verbatim transcript.
- Skipping the modality detection step and guessing from filename alone when `$ARGUMENTS[2]` was provided.
- Writing to the vault root or to `/permanent/` instead of `//`.
- Omitting `source_type`, `captured_at`, or `status: draft` from the frontmatter.

## Verification

Print this block before concluding — silent checks get skipped:

```
vault-ingest verification:
  [ ] Tool detection logged to tooling.md before capture-normalizer dispatch
  [ ] Transcript shown verbatim via AskUserQuestion before any vault write
  [ ] Fleeting note written under // with source_type + captured_at + status: draft
  [ ] state.md Status is `complete` with Completed timestamp
```

If any box is unchecked, the skill did not run correctly — report the failure explicitly rather than claiming success.

## State Management

State persists to `.mz/task//state.md`. Schema is **v2**: the file's first line is `schema_version: 2`, and alongside the skill's existing `Status` / `Phase` / `Started` keys it carries `phase_complete` (boolean) and `what_remains` (YAML list of strings). Set `phase_complete: false` on phase entry and `true` once the phase's artifacts are written and its gates pass; refresh `what_remains` on every phase transition; `what_remains` MUST be `[]` when `Status: complete`. On reading a `schema_version: 1` or unversioned file, add the missing keys, set `schema_version: 2`, and log the upgrade.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [DoctorMozg](https://github.com/DoctorMozg)
- **Source:** [DoctorMozg/claude-pipelines](https://github.com/DoctorMozg/claude-pipelines)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-doctormozg-claude-pipelines-vault-ingest
- Seller: https://agentstack.voostack.com/s/doctormozg
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.