--- name: pp-motogp description: "The first CLI and MCP server for MotoGP — human-friendly commands, offline SQLite history, and analyses no single endpoint provides. Trigger phrases: `who won the motogp race`, `motogp standings`, `motogp calendar`, `compare two motogp riders`, `check moto2 results`, `use motogp`, `run motogp`." author: "waterpig" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - motogp-pp-cli --- # MotoGP — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `motogp-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install motogp --cli-only ``` 2. Verify: `motogp-pp-cli --version` 3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill. If the `npx` install fails before this CLI has a public-library category, install Node or use the category-specific Go fallback after publish. 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. Query MotoGP, Moto2, and Moto3 results, standings, riders, and calendars by name instead of chained UUIDs. Every command resolves year, class, event, and rider names against the live API, and layered analyses — round-by-round title races, rider head-to-heads, and circuit histories — answer questions the official API can't in one call. ## When to Use This CLI Reach for this CLI whenever an agent needs MotoGP, Moto2, or Moto3 facts: race winners, championship standings, rider stats, season calendars, or head-to-head comparisons. It is the right choice over a raw API call because it resolves human names to UUIDs and answers cross-season questions the API cannot. ## When Not to Use This CLI Do not activate this CLI for requests that require creating, updating, deleting, publishing, commenting, upvoting, inviting, ordering, sending messages, booking, purchasing, or changing remote state. This printed CLI exposes read-only commands for inspection, export, sync, and analysis. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Human-friendly access - **`results`** — Query races by year, class name, event name, and session type instead of chained UUIDs. _Lets an agent answer 'who won the Dutch MotoGP race in 2024' in one call instead of four UUID lookups._ ```bash motogp results 2024 assen motogp race --agent ``` - **`career`** — Merge a rider's profile with career and season-by-season stats into one timeline. _Full career context in one command instead of stitching multiple endpoints._ ```bash motogp career "Marc Marquez" --agent ``` - **`since`** — Show finished events and winners for a season window. _Fast catch-up on results without paging the whole calendar._ ```bash motogp since 2026 --agent ``` - **`live`** — Fetch the current live-timing feed as an agent-friendly JSON snapshot. _Lets an agent poll race state during a session and get a defined empty result otherwise._ ```bash motogp live --agent ``` ### Local analyses that compound - **`title-race`** — See how championship points evolved round-by-round across a season. _Answers 'when did the title get decided' without pulling every race by hand._ ```bash motogp title-race 2024 motogp --rounds 6 --agent ``` - **`h2h`** — Compare two riders' career and season stats side by side. _One call to settle a rider-versus-rider debate with real numbers._ ```bash motogp h2h "Marc Marquez" "Francesco Bagnaia" --agent ``` - **`circuit-history`** — List winners at a given circuit across every synced season. _Surfaces track specialists and streaks an agent can't get from one API call._ ```bash motogp circuit-history mugello motogp --seasons 3 --agent ``` - **`calendar`** — Export a season calendar to an ICS file from the local store. _Drop the race calendar straight into any calendar app, offline._ ```bash motogp calendar 2026 --ics motogp-2026.ics ``` ## Command Reference **broadcast-categories** — Broadcast API: categories by season year - `motogp-pp-cli broadcast-categories` — List broadcast categories for a season year **broadcast-events** — Broadcast API: events with schedules and circuits - `motogp-pp-cli broadcast-events get` — Get a single broadcast event by ID - `motogp-pp-cli broadcast-events list` — List broadcast events (schedules, circuits) for a season year **categories** — Racing categories (MotoGP, Moto2, Moto3) for a season or event - `motogp-pp-cli categories` — List categories for a season (--season-uuid) or event (--event-uuid) **classification** — Session classification (finishing order, times, points) - `motogp-pp-cli classification ` — Get the classification/results for a session **events** — Race events (rounds) within a season - `motogp-pp-cli events` — List events for a season (pass --season-uuid; see 'seasons list' for UUIDs) **grid** — Grid / qualifying positions for an event category - `motogp-pp-cli grid ` — Get grid positions and qualifying times **riders** — Rider profiles, career stats and statistics - `motogp-pp-cli riders get` — Get a single rider profile and career history - `motogp-pp-cli riders list` — List all riders across categories for the current season - `motogp-pp-cli riders statistics` — Season-by-season rider statistics - `motogp-pp-cli riders stats` — Career statistics (wins, podiums, poles, etc.) **seasons** — Championship seasons - `motogp-pp-cli seasons` — List all MotoGP seasons with year and current flag **sessions** — Practice, qualifying and race sessions - `motogp-pp-cli sessions get` — Get a single session by ID - `motogp-pp-cli sessions list` — List sessions for an event and category **standings** — Championship standings and points - `motogp-pp-cli standings bmwaward` — BMW Award (pole/qualifying) standings for a season - `motogp-pp-cli standings files` — Official standings document (PDF) URLs - `motogp-pp-cli standings list` — Championship standings for a season and category **teams** — Teams and rosters - `motogp-pp-cli teams` — List teams with rosters for a category and season year (use broadcast category UUIDs from 'broadcast-categories list') ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash motogp-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 ### Who won a specific race ```bash motogp results 2024 mugello motogp race --agent ``` Resolves year, circuit, class, and session to the classification without any UUIDs. ### Narrow a nested result ```bash motogp results 2024 qatar motogp race --agent --select event,finishers ``` Trim the response to just the fields an agent needs from a nested payload. ### Rider head-to-head ```bash motogp h2h "Marc Marquez" "Francesco Bagnaia" --agent ``` Career stats for both riders side by side in one structured payload. ### Catch up on the season ```bash motogp since 2026 --agent ``` Finished rounds so far this season; add --winners for race winners. ### Export the calendar ```bash motogp calendar 2026 --ics motogp-2026.ics ``` Write an ICS file of the season's Grand Prix rounds for any calendar app. ## Auth Setup No authentication required. Run `motogp-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 motogp-pp-cli broadcast-categories --season-year 2026 --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 `MOTOGP_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `MOTOGP_CONFIG_DIR`, `MOTOGP_DATA_DIR`, `MOTOGP_STATE_DIR`, `MOTOGP_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `MOTOGP_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 `motogp-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": { "motogp": { "command": "motogp-pp-mcp", "env": { "MOTOGP_HOME": "/srv/motogp" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `MOTOGP_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 `MOTOGP_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 motogp-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": ["", "motogp-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 `motogp-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; `motogp-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 `motogp-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 motogp-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 ne