Pp Lightroom Classic

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/media-and-entertainment/lightroom-classic/SKILL.md,
     regenerated post-merge by tools/generate-skills/. Hand-edits here are
     silently overwritten on the next regen. Edit the library/ source instead.
     See the repository agent guide, section "Generated artifacts: registry.json, cli-skills/". -->

Lightroom Classic — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the lightroom-classic-pp-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:

1. Install via the Printing Press installer. It defaults binaries to $HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:

   npx -y @mvanhorn/printing-press-library install lightroom-classic --cli-only

2. Verify: lightroom-classic-pp-cli --version
3. Ensure the reported install directory is on $PATH for the agent/runtime that will invoke this skill.

If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:

go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/lightroom-classic/cmd/lightroom-classic-pp-cli@latest

If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.

Reads the .lrcat SQLite catalog Lightroom already maintains, strictly read-only. Built for daily photo practices: pick-of-day resolves the one image a publish pipeline needs, streaks and project track consistency, and photos turns any criteria into a JSON shot list.

When to Use This CLI

Use for any question about a Lightroom Classic catalog: what was shot when, with what gear, which images are picked or rated, and where the files live on disk. Built for photographers running daily practices and for build scripts that need per-day shot lists as JSON.

Anti-triggers

Do not use this CLI for:

• Do not use to edit photos, change ratings, or write anything into the catalog — it is strictly read-only
• Do not use for Lightroom (cloud) or Apple Photos libraries; this reads .lrcat files only
• Do not use to render or export image files; it resolves paths but never touches image pixels

Unique Capabilities

These capabilities aren't available in any other tool for this API.

Daily practice

• streaks — See your current and longest daily-shooting streaks and every missed day in a range.

  Reach for this when asked about daily practice consistency or missed days.

  lightroom-classic-pp-cli streaks --since 2026-01-01 --json

• pick-of-day — Get exactly one image per day — flag beats rating beats recency — with its file path resolved for publishing.

  Use this when a build pipeline needs the day's photo, not a list of candidates.

  lightroom-classic-pp-cli pick-of-day --date 2026-07-12 --json

• on-this-day — Everything shot on this calendar date across all years, grouped by year.

  Use for month/day browse pages and anniversary lookbacks; find only does date ranges.

  lightroom-classic-pp-cli on-this-day --month 7 --day 19 --json

• project — Progress report for a fixed-length photo project: day N of target, missed days, projected finish.

  Use when tracking a bounded series backed by a collection.

  lightroom-classic-pp-cli project --collection "100 Faces" --target 100 --json

Catalog intelligence

• stats — Histograms of your shooting by focal length, hour, weekday, month, camera, lens, or ISO.

  Use for gear and habit questions; returns buckets, not image rows.

  lightroom-classic-pp-cli stats --by lens --since 2025-01-01

• doctor — Health sweep: masters missing on disk, images without capture time, orphan keywords, empty collections.

  Run before backups or migrations to find catalog rot.

  lightroom-classic-pp-cli doctor --json

• funnel — Conversion rates from shot to picked to rated to developed to collected, optionally per year.

  Use for selectivity and culling-discipline questions.

  lightroom-classic-pp-cli funnel --by year --json

• backlog — Keepers you flagged or rated but never developed.

  Use to surface workflow debt before publishing deadlines.

  lightroom-classic-pp-cli backlog --picked-only --json

Command Reference

catalog — Catalog-level listings and health

• lightroom-classic-pp-cli catalog cameras — List camera bodies with counts and first/last-seen dates
• lightroom-classic-pp-cli catalog collections — List collections with image counts
• lightroom-classic-pp-cli catalog keywords — List keywords with image counts
• lightroom-classic-pp-cli catalog lenses — List lenses with counts and first/last-seen dates

photos — Find and inspect photos in the catalog

• lightroom-classic-pp-cli photos — Search photos by date, rating, pick, label, keyword, collection, camera, lens, and EXIF criteria

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

lightroom-classic-pp-cli which "<capability in your own words>"

which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match — fall back to --help or use a narrower query.

Recipes

Today's pick for the photo-a-day site

lightroom-classic-pp-cli pick-of-day --date "$(date +%F)" --json

Returns the single best image for today with its absolute path, ready for a publish script.

Which days this month have no photos

lightroom-classic-pp-cli streaks --since "$(date +%Y-%m-01)" --json --select gaps

Narrow the streak report to just the missing dates.

Shot list of recent keepers

lightroom-classic-pp-cli photos --rating ">=4" --since 2026-06-01 --json --select id,capture_time,path,camera

Uses --select to keep the JSON small for agent consumption.

Gear reality check

lightroom-classic-pp-cli stats --by lens

Counts by lens with first/last-seen dates — what glass actually gets used.

Pre-backup health sweep

lightroom-classic-pp-cli doctor --json

Finds masters missing on disk and other catalog rot before it bites.

Auth Setup

No authentication. The CLI opens the catalog file in SQLite read-only immutable mode and refuses all writes. Point it at a different catalog with --catalog or LIGHTROOM_CLASSIC_CATALOG.

Run lightroom-classic-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.

• Pipeable — JSON on stdout, errors on stderr

• Filterable — --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:

  lightroom-classic-pp-cli catalog cameras --agent --select id,name,status

• Previewable — --dry-run shows the request without sending

• Offline-friendly — sync/search commands can use the local SQLite store when available

• Non-interactive — never prompts, every input is a flag

• Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout.

Paths and state

Agents should treat the CLI's path resolver as part of the runtime contract:

• Use --home <dir> for one invocation, or set LIGHTROOM_CLASSIC_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: LIGHTROOM_CLASSIC_CONFIG_DIR, LIGHTROOM_CLASSIC_DATA_DIR, LIGHTROOM_CLASSIC_STATE_DIR, LIGHTROOM_CLASSIC_CACHE_DIR.

• Resolution order is per-kind env var, --home, LIGHTROOM_CLASSIC_HOME, XDG (XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME), then platform defaults.

• config contains settings like config.toml and profiles. data contains data.db (the local learnings store — not your photos; the .lrcat catalog is never copied). state contains persisted queries, jobs, and teach.log. cache contains regenerable cache files.

• This CLI stores no secrets: there is no authentication.

• Run lightroom-classic-pp-cli doctor --fail-on warn to surface path and credential-location warnings. agent-context exposes a schema v4 paths block for agents that need the resolved dirs.

• For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags:

  {
    "mcpServers": {
      "lightroom-classic": {
        "command": "lightroom-classic-pp-mcp",
        "env": {
          "LIGHTROOM_CLASSIC_HOME": "/srv/lightroom-classic"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use LIGHTROOM_CLASSIC_HOME or per-kind vars as durable fleet levers, and use --home only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing LIGHTROOM_CLASSIC_HOME, or doctor will not find credentials left under the former root.

Automatic learning

This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a flag_alias candidate, and a teach on a query family without a playbook auto-synthesizes a playbook_candidate from the session's journal. Your job is judgment only: recall first, act on surfaced candidates, teach the final answer, playbook amend when you observe a correction. You never record failures by hand.

Step 1: recall before any discovery

Before list/search/drill commands on a new user question, run:

lightroom-classic-pp-cli recall "<user's question>" --agent

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "query_entities": ["..."],
  "found": true | false,
  "match_score": 0.0,
  "results": [
    { "resource_id": "...", "resource_type": "...", "venue": "...",
      "confidence": 2, "entity_match": "exact|partial|unknown",
      "source": "taught|preseed|pattern", "warnings": ["..."] }
  ],
  "mismatches": [ /* only when --debug-mismatches */ ],
  "warnings": [ /* top-level */ ],
  "candidates": [
    { "id": 12, "class": "flag_alias | playbook_candidate",
      "summary": "...", "sightings": 3, "last_seen": "...",
      "rationale": "...",
      "next_action": ["<trial command>", "lightroom-classic-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and learnings list and learnings candidates are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught.

Step 2: decision tree

Read candidates, playbook, notes, results[0], and warnings in that order:

if Candidates present (warnings include "candidates_present"):
    -> candidates are try-then-confirm, never facts. Follow each candidate's
       two-step next_action verbatim: run the trial command first, then run
       `learnings confirm <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> NEVER re-teach something recall surfaced as a candidate; confirm or
       reject that candidate instead of teaching a duplicate.
    -> candidates ride alongside playbooks and resource hits, not instead of
       them; continue with the branches below after acting on them.

if Playbook present:
    -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose)
    -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries
       for the entity slot tokens. If a step's slot is unresolved, fall back to
       discovery for that step only.
    -> the Playbook's expected_tool_calls is a budget; if you find yourself running
       materially more, record the divergence via `lightroom-classic-pp-cli playbook amend`
       at end-of-session.

elif Notes present (no Playbook):
    -> read Notes verbatim before any discovery step; they carry known gotchas
       for this query family even when no structured choreography exists yet.

elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2:
    -> skip discovery; fetch live data for Results[*].ResourceID in parallel

elif Found AND Results[0].EntityMatch == "partial":
    -> candidate hint, NOT a hit; read the resource title to validate before trusting

elif (any row in Mismatches[] when --debug-mismatches was passed):
    -> treat as cold start; the stored learning is for a different entity
       (different canonical resolved from query_entities)

else:  // Found == false, no playbook, no notes
    -> cold start; run discovery normally; teach the answer afterward (Step 4).
       If the family has no playbook yet, that teach auto-synthesizes a
       playbook candidate from this session's journal - you do not need to
       record one by hand.

Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a Results[] hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping mismatches; pass --debug-mismatches only when investigating cold-start surprises.

Candidate judgment details: learnings confirm <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; lightroom-classic-pp-cli learnings candidates lists the full open set.

Graceful degradation: if learnings confirm is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol.

Step 3: always read warnings

• low_confidence: row exists at confidence<2. Treat as a hint, not a skip-discovery hit.
• resource_not_in_store: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate.
• cross_alias_match (per-result): the row was taught under a different alias and matched the live query's canonical via entity_lookups (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id.
• similar_shape_different_entity:<canonical> (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results.
• ambiguous_alias (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource.
• candidates_present (top-level): the envelope carries a candidates section. Handle it via the candidates branch in Step 2 before anything else.
• lookup_refresh_available (top-level): an entity in the query has no lookup row yet, but synced data could provide one. The catalog is already local; lookups read it directly.
• Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.