Files
dl-organizer/skills/vlm-library-workflow/references/command-recipes.md
T
6f0df5a774 release: v0.2.0 repository hygiene, CI, and docs sync
Stop tracking personal workflow artifacts at repo root, add CI and MIT
license, align README and agent skills with artifacts/ defaults, and
enable Ruff in dev/CI so releases are verifiable without local-only runs.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-01 15:32:03 +08:00

2.0 KiB

Documentation Status

  • Synced with artifacts/ baseline on 2026-06-01.

VLM Command Recipes

Baseline

Run from repository root unless the user specifies otherwise.

vlm --help
vlm config show
vlm config validate

If vlm is not on PATH:

uv run vlm --help
uv run vlm config show
uv run vlm config validate

End-to-End Pipeline

Default artifact paths match CLI defaults under artifacts/:

vlm scan
vlm parse --inventory artifacts/inventory.csv
vlm enrich
vlm analyze --inventory artifacts/inventory.csv
vlm plan --analysis artifacts/analysis.json
vlm review-plan --input artifacts/plan.json --output artifacts/plan_manual_review.csv
vlm apply-review
vlm execute
vlm execute --confirm

Artifact Expectations

  1. artifacts/inventory.csv — discovered files with filesystem and optional ffprobe metadata.
  2. artifacts/identities.json — parsed identities (v2 when parse used --inventory).
  3. artifacts/analysis.json — completeness gaps and duplicate groups.
  4. artifacts/plan.json — planned operations (move, rename, quarantine, no-op).
  5. artifacts/plan_manual_review.csv — high-risk rows for human review before --confirm.

Do not commit these files to Git.

Focused Workflows

vlm parse --inventory artifacts/inventory.csv
vlm analyze --input artifacts/identities.json --output artifacts/analysis.json --inventory artifacts/inventory.csv
vlm plan --input artifacts/identities.json --analysis artifacts/analysis.json --output artifacts/plan.json
vlm rollback

Frequent Failure Triage

  1. Missing config: vlm config init, set library_root.
  2. Invalid config: vlm config validate.
  3. Missing input artifact: run prerequisite stage (scan → parse → analyze → plan).
  4. Unexpected duplicate decisions: check plan.duplicate_keep, rerun vlm plan --analysis artifacts/analysis.json.
  5. Unsafe execution: vlm rollback, re-run review-plan / apply-review.
  6. vlm not found: use uv run vlm ....
  7. TMDB rate limits: lower enrichment.max_concurrency in config and retry later.