--- name: pp-lightroom-classic description: "Your Lightroom Classic catalog, queryable from the terminal — streaks, daily picks, and shot lists with zero exports and zero writes. Trigger phrases: `what did I shoot on`, `current photo streak`, `pick of the day from Lightroom`, `which days have no photos`, `lens usage stats from my catalog`, `use lightroom-classic`, `run lightroom-classic`." author: "Micah Baldwin" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - lightroom-classic-pp-cli install: - kind: go bins: [lightroom-classic-pp-cli] module: github.com/mvanhorn/printing-press-library/library/media-and-entertainment/lightroom-classic/cmd/lightroom-classic-pp-cli --- # 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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install lightroom-classic --cli-only ``` 2. Verify: `lightroom-classic-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/media-and-entertainment/lightroom-classic/cmd/lightroom-classic-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$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._ ```bash 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._ ```bash 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._ ```bash 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._ ```bash 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._ ```bash 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._ ```bash 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._ ```bash 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._ ```bash 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: ```bash lightroom-classic-pp-cli which "" ``` `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 ```bash lightroom-classic-pp-cli pick-of-day --date "$(date +%F)" --json ``` Returns the single best image for today with its absolute path, ready for a publish script. ### Which days this month have no photos ```bash lightroom-classic-pp-cli streaks --since "$(date +%Y-%m-01)" --json --select gaps ``` Narrow the streak report to just the missing dates. ### Shot list of recent keepers ```bash 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 ```bash lightroom-classic-pp-cli stats --by lens ``` Counts by lens with first/last-seen dates — what glass actually gets used. ### Pre-backup health sweep ```bash 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: ```bash 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: ```json { "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": } ``` 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 ` for one invocation, or set `LIGHTROOM_CLASSIC_HOME=` 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: ```json { "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: ```bash lightroom-classic-pp-cli recall "" --agent ``` The response envelope: ```json { "query": "...", "normalized": "", "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": ["", "lightroom-classic-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "", "canonical": "" } }, "notes": "" }, "notes": "" } ``` 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 ` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject `. -> 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 ` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject ` 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:` (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. ### Step 4: `teach &` after finalizing your response - always Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell `&` so the call returns immediately: ```bash lightroom-classic-pp-cli teach --query "" --resource-type --resource --resource # (append shell `&` to background it) ``` Silent on success. Errors only land in `teach.log` under the resolved state dir. Teach the **most specific** resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded `entity_lookups` for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically. PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning. ### Step 5: playbooks - optional flags, automatic synthesis You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a `playbook_candidate` from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the **integrated one-call form** - record the resource learning and the playbook in the same `teach` invocation: ```bash # Common case: record both the resource learning AND the playbook in one call. lightroom-classic-pp-cli teach \ --query "" \ --resource \ --playbook-file ~/playbooks/.json \ --playbook-notes-file ~/playbooks/-notes.md # (append shell `&` to background it) # Alternate: playbook-only (no resource to record alongside). lightroom-classic-pp-cli t