dl-organizer/skills/vlm-library-workflow/references/workflow.md

Documentation Status

• Synced with refactor baseline on 2026-02-16.

VLM Workflow Guide

This guide details the standard end-to-end process for organizing a video library using VLM.

1. Setup and Discovery

Initialize Configuration

vlm config init

Edit ~/.vlm/config.yaml to set library_root.

Library Scan

vlm scan

• Goal: Create inventory.csv.
• Note: Ensure ffprobe is installed for resolution and codec metadata.

2. Identification

Filename Parsing

vlm parse --inventory inventory.csv

• Goal: Create identities.json.
• Why --inventory?: It embeds video metadata (v2 schema) required for quality-based duplicate resolution.

Metadata Enrichment

vlm enrich

• Goal: Update identities.json with TMDB data.
• Troubleshooting: If matches are missing, check enrichment.api_keys in config.

3. Analysis and Planning

Detect Issues

vlm analyze

• Goal: Create analysis.json.
• Outputs: Lists duplicate files and episode gaps in series.

Create Execution Plan

vlm plan --analysis analysis.json

• Goal: Create plan.json.
• Strategy: VLM uses the duplicate_keep policy (default: by_reputation) to decide which files to keep and which to quarantine.

4. Execution and Safety

Review the Plan

Open plan.json and check the human_summary field or the proposed operations.

Execute Changes

vlm execute           # Dry-run
vlm execute --confirm # Actual operations

Reverting Changes

vlm rollback

Restores files using the latest log in ~/.vlm/rollback/.