--- name: pp-jr-east-status description: "Compare JR East line impacts with bilingual identity, source freshness and reporting limits. Trigger phrases: `check JR East delays`, `compare JR East itinerary lines`, `JR East delay certificate`, `use jr-east-status`, `run jr-east-status`." author: "zjsng" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - jr-east-status-pp-cli install: - kind: go bins: [jr-east-status-pp-cli] module: github.com/mvanhorn/printing-press-library/library/travel/jr-east-status/cmd/jr-east-status-pp-cli --- # JR East Status — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `jr-east-status-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install jr-east-status --cli-only ``` 2. Verify: `jr-east-status-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/travel/jr-east-status/cmd/jr-east-status-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. Discover lines and inspect suspensions, affected sections and planned notices. Compare itinerary lines and follow currently published certificate links with explicit unknowns. ## Source contract Operational commands read JR East anonymously with bounded standard HTTPS; no browser, account or key is needed. Read `README.md` under “Reading results” for source coverage and “Planned work and certificates” for the handoff semantics. Public installer/release instructions in this generated skill apply after publication; the current verified source checkout builds with `go build -o ./jr-east-status-pp-cli ./cmd/jr-east-status-pp-cli`. Choose a region with `areas`, resolve the exact native line using `lines`, then fetch `status` or compare selected components using `impact`. Read `meta.sources`, reporting state, fetch failures and truncation before answering. Normal labels never establish zero delay. Closed hours are 02:00–04:00 JST; `coverage` classifies the service day. Japanese planned facts stay authoritative when the English AI translation is malformed; notice facts preserve their languages. Use only actual links returned by `certificates`. They certify a rounded route/time-slot maximum, not an individual train or boarding. Historical dates, travelled-section eligibility and complex planned schedules require official handoffs. Learning may retain native IDs and command routes; fetch current status every time and never teach an operational snapshot as reusable truth. ## When to Use This CLI Use for JR East regional and line service status checks, affected sections, itinerary line comparison and published certificate handoffs. Read source timing and coverage before making planning claims. ## Anti-triggers Do not use this CLI for: - Exact train lateness or train positions - Reservations, refunds, push notifications or account actions ## Unique Capabilities These commands add source-aware decisions to the underlying public-page reads. ### Source-aware decisions - **`status`** — Reconcile native Japanese IDs with English row labels, keeping multiple notices and source uncertainty. _Reconcile native Japanese IDs with English row labels, keeping multiple notices and source uncertainty._ ```bash jr-east-status-pp-cli status --line sobuline --region kanto --agent ``` - **`impact`** — Compare selected itinerary lines with per-region source timing and affected sections. _Compare selected itinerary lines with per-region source timing and affected sections._ ```bash jr-east-status-pp-cli impact --lines kanto:yamanoteline,kanto:sobuline --agent ``` - **`coverage`** — Explain reporting hours, threshold conflicts, midnight service-day rollover and remaining unknowns. _Explain reporting hours, threshold conflicts, midnight service-day rollover and remaining unknowns._ ```bash jr-east-status-pp-cli coverage --agent ``` ### Planning handoffs - **`planned`** — Inspect construction evidence without promoting future notices to current service suspension. _Inspect construction evidence without promoting future notices to current service suspension._ ```bash jr-east-status-pp-cli planned --line koumiline --region kanto --agent ``` - **`certificates`** — Return actual published route/time-slot links and source coverage limits. _Return actual published route/time-slot links and source coverage limits._ ```bash jr-east-status-pp-cli certificates --line yamanoteline --agent ``` ## Command Reference | Command | Input and result | |---|---| | `areas` | Regional/service aggregate labels and canonical links. | | `lines` | One `--region`, optional `--query` and bounded `--limit`; returns native IDs/names. | | `status` | `--line` native ID/exact name, optional region; bounded bilingual notice facts. | | `impact` | `--lines` with up to eight comma-separated `region:id` components; gaps remain explicit. | | `planned` | `--line` and region; selected construction tables and line notice facts. | | `certificates` | Optional native `--line` and source `--slot` 01–05; currently published handoffs. | | `coverage` | Optional RFC3339 `--at`; no network. | | `sources` | Official source guide links; operational facts use domain commands. | ### Finding the right command MCP mirrors the seven bounded domain commands and the CLI `sources` guide, which extracts links. Its raw HTML typed endpoint is hidden from MCP. When you know what you want to do but not which command does it, ask the CLI directly: ```bash jr-east-status-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. `--json` (and other machine formats) keep that exit-2 contract and write `{"matches":[]}` on stdout so agents can inspect the envelope without treating a miss as success. ## Recipes ### Itinerary impact ```bash jr-east-status-pp-cli impact --lines kanto:yamanoteline,kanto:sobuline --agent ``` Compare selected lines with coverage and timestamps. ### Compact line discovery ```bash jr-east-status-pp-cli lines --region kanto --query Narita --agent --select id,name_ja,name_en ``` Keep only line identifiers and bilingual names. ### Published certificate ```bash jr-east-status-pp-cli certificates --line yamanoteline --agent ``` Follow published links; delay is a route maximum. ### Planned closure ```bash jr-east-status-pp-cli planned --line koumiline --region kanto --agent ``` Inspect scheduled-work evidence and official handoff. ## Auth Setup Anonymous first-party source reads; no key or login required. Run `jr-east-status-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color`. Global format flags share one contract on source, domain and `--deliver` paths: - `--json` — one JSON document on stdout - `--compact` — keep identity/status/timestamp fields; does not change the document vs stream shape - `--csv` / `--plain` — tabular rows (collection envelopes unwrap to the row array) - `--quiet` — one identity value per row, no envelope - **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 jr-east-status-pp-cli lines --region kanto --query Yamanote --select id,name_ja,assessment --agent ``` - **Previewable** — `--dry-run` shows the request without sending - **Source-aware** — operational commands always fetch live pages; `coverage` classifies embedded reporting policy without a network request - **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 With `--agent`, domain reads return bounded facts with provenance: ```json { "meta": {"source": "live", "observed_at": "...", "sources": []}, "results": } ``` Parse `.results` for facts and `.meta.sources` for page timing and reporting state. `coverage` identifies its policy data as embedded. Operational reads reject `--data-source local`; no cached snapshot establishes current service. ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `JR_EAST_STATUS_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `JR_EAST_STATUS_CONFIG_DIR`, `JR_EAST_STATUS_DATA_DIR`, `JR_EAST_STATUS_STATE_DIR`, `JR_EAST_STATUS_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `JR_EAST_STATUS_HOME`, XDG (`XDG_CONFIG_HOME`, `XDG_DATA_HOME`, `XDG_STATE_HOME`, `XDG_CACHE_HOME`), then platform defaults. - `config` contains settings like `config.json` 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. - JR East reads require no credentials or stored auth secrets. - Run `jr-east-status-pp-cli doctor --fail-on warn` to surface path 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": { "jr-east-status": { "command": "jr-east-status-pp-mcp", "env": { "JR_EAST_STATUS_HOME": "/srv/jr-east-status" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `JR_EAST_STATUS_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 `JR_EAST_STATUS_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, pass the question as an argv or MCP tool argument to `recall --agent`. Do not interpolate user-controlled text into a shell command line. Quoted `recall ""` breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data: ```bash # Write the question verbatim with your file-writing tool (no shell involved). # Command substitution on a file only ever yields data — the shell never # parses the file's bytes as syntax. QUERY=$(cat /path/to/question.txt) jr-east-status-pp-cli recall "$QUERY" --agent ``` Prefer MCP: pass the question as the tool's query argument. `"$QUERY"` after a file read is argv-safe; putting the question itself in the command text is not. The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "jr-east-status-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$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 `jr-east-status-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; `jr-east-status-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. - 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. Pass the query the same way as recall — argv/MCP, or file-then-`$QUERY`. Do not splice the question into the command text: ```bash QUERY=$(cat /path/to/question.txt) jr-east-status-pp-cli teach --query "$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.