--- name: pp-booksy description: "Book a haircut in Poland from the terminal — search barbers, compare prices and reviews, check open slots, and book, with a dry-run-by-default booking guard. Trigger phrases: `book a haircut`, `find a barber in Warszawa`, `cheapest haircut near me`, `when can I get a haircut at`, `check booksy availability`, `use booksy`, `run booksy`." author: "Max Tomago" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - booksy-pp-cli install: - kind: go bins: [booksy-pp-cli] module: github.com/mvanhorn/printing-press-library/library/commerce/booksy/cmd/booksy-pp-cli --- # Booksy — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `booksy-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install booksy --cli-only ``` 2. Verify: `booksy-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/commerce/booksy/cmd/booksy-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. A CLI over Booksy's Polish marketplace. Public commands (search, business, reviews, suggest) need no login; add BOOKSY_ACCESS_TOKEN for your account and the guided `book` command. `book` previews the exact appointment and only commits with --confirm, so agents can plan safely and you approve the real booking. ## When to Use This CLI Use this CLI to search Booksy businesses in Poland, compare barbers/salons on price and rating, check when a service has open slots, and book an appointment from the terminal or an agent. It is the fastest path from 'find me a haircut near X' to a confirmed booking. ## Anti-triggers Do not use this CLI for: - Do not use it for Booksy Biz / provider-side management (staff, calendars, POS) — this is the customer surface only. - Do not use it to bulk-scrape all Booksy businesses; it is built for booking and comparison, not crawling. - Do not use it outside Poland; it is wired to the pl.booksy.com marketplace. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Booking funnel - **`book`** — Book an appointment end to end — it previews the exact service, staffer, time, and price first, and only sends the real booking when you pass --confirm. _This is the one command that turns 'find me a haircut' into an actual appointment; the dry-run-by-default guard means an agent can plan safely and the human confirms._ ```bash booksy-pp-cli book 297360 --service-variant 20193554 --date 2026-08-19 --time 10:00 ``` - **`availability`** — List open time slots for a service at a business over a date range, grouped by day. No login required. _Lets an agent answer 'when can I get in?' without loading the web calendar — no token needed._ ```bash booksy-pp-cli availability 297360 --service-variant 20193554 --from 2026-08-19 --to 2026-08-31 ``` - **`services`** — Flatten a business profile into a clean table of bookable services with price, duration, and the service-variant id you pass to book. _Surfaces the exact --service-variant id an agent needs for availability and booking, with prices to compare._ ```bash booksy-pp-cli services 297360 --query haircut ``` - **`cancel`** — Cancel one of your Booksy appointments by id — previews the appointment first and only cancels with --confirm. _Lets an agent undo a booking it made without opening the Booksy app._ ```bash booksy-pp-cli cancel 746784544 --confirm ``` ### Local intelligence - **`earliest`** — Find the single earliest open slot for a service across a date window in one call. _Answers 'what's the soonest I can get a haircut here?' directly instead of returning a whole calendar._ ```bash booksy-pp-cli earliest 297360 --service-variant 20193554 --within 14d ``` - **`compare`** — Compare several businesses side by side on rating, review count, and cheapest matching service price — from the local cache. _Turns 'which of these barbers is best value?' into one command instead of opening N tabs._ ```bash booksy-pp-cli compare 297360 161624 --service haircut ``` - **`cheapest`** — Scan search results in a city and rank businesses by the cheapest service matching your query (e.g. haircut), with rating alongside price. _Answers 'where's the cheapest decent haircut near me?' — a query Booksy's own UI cannot express._ ```bash booksy-pp-cli cheapest --location-id 47905 --service haircut --limit 10 ``` ## Command Reference **businesses** — Search and inspect Booksy businesses (barbers, salons) - `booksy-pp-cli businesses get` — Full business profile: services (with prices/variant ids), staff, hours, reviews summary. - `booksy-pp-cli businesses reviews` — Customer reviews for a business. - `booksy-pp-cli businesses search` — Search barbers/salons. Filter by query, city (location-id), and category; sort by score/distance/reviews. **discover** — Discovery helpers: query suggestions and location resolution - `booksy-pp-cli discover locations` — Resolve a place/city name to Booksy location ids for search. - `booksy-pp-cli discover suggest` — Query suggestions (treatments/categories) for free text. - `booksy-pp-cli discover treatments` — Popular treatments to browse/seed a search. **me** — Your Booksy account (requires BOOKSY_ACCESS_TOKEN) - `booksy-pp-cli me home` — Your Booksy home: active booking box, favorite/visited businesses, categories. Requires auth. - `booksy-pp-cli me profile` — Your customer profile (name, email, phone). Requires auth. ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash booksy-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 ### Cheapest haircut near a city ```bash booksy-pp-cli cheapest --location-id 47905 --service haircut --limit 10 ``` Ranks nearby barbershops by their cheapest haircut price with rating alongside. ### Soonest opening for a service ```bash booksy-pp-cli earliest 297360 --service-variant 20193554 --within 14d ``` Returns the single earliest open slot in the next two weeks. ### Narrow a search payload for an agent ```bash booksy-pp-cli businesses search --query barber --location-id 47905 --agent --select businesses.id,businesses.name,businesses.reviews_stars,businesses.reviews_count ``` Booksy business objects are large; --select trims to just the fields an agent needs to rank results. ### Safe booking preview then confirm ```bash booksy-pp-cli book 297360 --service-variant 20193554 --date 2026-08-19 --time 10:00 ``` Prints the exact service, staffer, time, and price; re-run with --confirm to place it. ## Auth Setup Public discovery works out of the box. Authenticated actions (your profile, open slots, booking) use your Booksy web session token: copy the `x-access-token` request header value from booksy.com (DevTools -> Network -> any /customer_api/me request) and set it via `booksy-pp-cli auth set-token ` or the BOOKSY_ACCESS_TOKEN env var. The public x-api-key and a device fingerprint are built in. Run `booksy-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color`. - **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 booksy-pp-cli businesses get mock-value --agent --select id,name,slug ``` - **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 `BOOKSY_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `BOOKSY_CONFIG_DIR`, `BOOKSY_DATA_DIR`, `BOOKSY_STATE_DIR`, `BOOKSY_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `BOOKSY_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 `credentials.toml`, `data.db`, cookies, and auth sidecars. `state` contains persisted queries, jobs, and `teach.log`. `cache` contains regenerable HTTP/cache files. - Stored secrets live in `credentials.toml` under the data dir. Existing legacy `config.toml` secrets are read for compatibility and leave `config.toml` on the first auth write. - Run `booksy-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": { "booksy": { "command": "booksy-pp-mcp", "env": { "BOOKSY_HOME": "/srv/booksy" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `BOOKSY_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 `BOOKSY_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 booksy-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": ["", "booksy-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 `booksy-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; `booksy-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. Run `booksy-pp-cli sync` to refresh entity lookups. - 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 booksy-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