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

---
name: vlm-library-workflow
description: Operate and extend the Video Library Manager (vlm) CLI. Use for organizing video libraries (scan/parse/enrich/analyze/plan/execute), reviewing plans, resolving duplicates, or developing VLM features.
---

# VLM Library Workflow

## Safety Contract

1. Before `execute --confirm`, always run `review-plan` and report `High-risk operations` count.
2. If high-risk > 0: **stop**, wait for explicit user decision.
3. `--confirm` requires `--require-review` to enforce review gate; default does not force.
4. Never run `execute --confirm` without user confirmation.

## Execution Threshold Semantics

- `high_risk_operations`: count of non-no-op operations with risk flags (printed by `review-plan`).
- `review_export_rows`: internal count (not printed); may be larger. Do not use `wc -l` on CSV.
- If export row count is needed, parse CSV data rows or add the count to CLI output.

## High-Risk Closed Loop

When high-risk > 0, use the same plan and CSV path throughout:

1. `vlm review-plan --input <plan> --output <csv>`
2. Human reviews CSV (modify decision or keep)
3. `vlm apply-review --plan <plan> --csv <csv>` — **required even if no changes** (writes `review_applied_at`)
4. `vlm execute --plan <plan>` (dry-run with updated plan)
5. Get explicit user confirmation
6. `vlm execute --plan <plan> --confirm --require-review --review-csv <csv>`

Three rejection paths: missing CSV, missing `review_applied_at`, CSV path mismatch.

## Workflow Phases

| Phase | Purpose | Artifact |
|-------|---------|----------|
| config | Set `library_root` | `~/.vlm/config.yaml` |
| scan | Discover files | `inventory.csv` |
| parse | Extract identities | `identities.json` |
| enrich | Add TMDB metadata | `identities.json` (updated) |
| analyze | Detect gaps/duplicates | `analysis.json` |
| plan | Generate operations | `plan.json` |
| review-plan | Export high-risk + preview | `plan_manual_review.csv` |
| apply-review | Sync manual decisions | `plan.json` (updated) |
| execute | Dry-run, then confirm | rollback log |
| rollback | Revert if needed | restored files |

## Decision Rules

**duplicate_keep strategies** (5): `by_quality`, `by_reputation`, `by_reputation_quality_time`, `first_seen`, `manual`.

**Parser boundary risks**: filenames with resolution-like `1920x1080`/`1440x1080` and `Sample` clips are high-risk; require review-plan output before confirmation.

**Metadata quality**: prefer `vlm parse --inventory` when duplicate quality ranking matters.

**Analysis-assisted planning**: prefer `vlm plan --analysis` for automatic duplicate quarantine.

## Output Contract

1. Commands executed and artifacts generated.
2. Key counts (files, identities, duplicates, operations).
3. Risk counts from review-plan; blocking errors with exact remediation command.

## References

- `references/triage.md`: failure triage mapping + preflight checks.
- `references/dev-map.md`: module → test → verification mapping.
- For CLI options: run `vlm <command> --help`. Do not trust memory.