Pp Hello Cycling

<!-- GENERATED FILE — DO NOT EDIT.
     This file is a verbatim mirror of library/travel/hello-cycling/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/". -->

HELLO CYCLING — Printing Press CLI

Local build status

Station planning contract

Require explicit coordinates for nearby/trip commands; no location permission or geocoding is used. Read meta before interpreting counts. Missing counts are null; stale, closed, uninstalled, incompatible and source-missing rows are not available. Default freshness is five minutes. Trip comparison uses an explicit generic GBFS class; current class 2 cannot identify actual city/sports/e-Bike models or special electric-cycle eligibility. Confirm availability, vehicle rules and price in the official app via source rental URLs.

Run stations sync before using --offline or stations changes. A local snapshot preserves timestamps and cannot guarantee current availability. --snapshot-db chooses that cache. Regional price rows preserve municipality and model columns, and not_set means unknown/unset rather than free. No quote arithmetic, reservation, ride or payment is performed.

Prerequisites: Install the CLI

This skill drives the hello-cycling-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 hello-cycling --cli-only

2. Verify: hello-cycling-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/travel/hello-cycling/cmd/hello-cycling-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.

Search Japanese station names and addresses, rank explicit-coordinate pickup/return choices, and compare compatible trip endpoints. Source timestamps, missing counts, and model-dependent pricing constraints remain attached to every result.

When to Use This CLI

Use for HELLO CYCLING station discovery, observed bike/return-space counts and compatible pickup/dropoff comparison in Japan. Require explicit latitude/longitude for nearby searches. Use source app links to confirm the actual bike, rate and return eligibility.

Anti-triggers

Do not use this CLI for:

• Reservations, rides, payments or account changes
• Location-permission access or geocoding without explicit coordinates
• Guaranteed availability, model eligibility or a final ride quote

Unique Capabilities

These workflows combine source observations with explicit planning constraints.

Station planning

• stations nearby — Find nearby pickup or return choices while retaining closed, empty, full, stale and unknown states.

  Find nearby pickup or return choices while retaining closed, empty, full, stale and unknown states.

  hello-cycling-pp-cli stations nearby --lat 35.697315 --lon 139.704995 --purpose pickup --vehicle-type 2 --agent

• trip compare — Compare pickup and dropoff pairs with per-type return capacity and straight-line access distances.

  Compare pickup and dropoff pairs with per-type return capacity and straight-line access distances.

  hello-cycling-pp-cli trip compare --from-lat 35.697315 --from-lon 139.704995 --to-lat 35.707252 --to-lon 139.777587 --vehicle-type 2 --agent

• stations sync — Save a provider snapshot for offline station discovery with original source timestamps.

  Save a provider snapshot for offline station discovery with original source timestamps.

  hello-cycling-pp-cli stations sync --agent

• stations changes — Inspect count and operational changes since an explicitly saved snapshot.

  Inspect count and operational changes since an explicitly saved snapshot.

  hello-cycling-pp-cli stations changes --query 新宿 --agent

• pricing show — Read current source tables including municipal exceptions without asserting a station bike price.

  Read current source tables including municipal exceptions without asserting a station bike price.

  hello-cycling-pp-cli pricing show --area tokyo --agent

HTTP Transport

Provider feed and website reads use bounded standard HTTP and require no browser process.

Command Reference

feeds — Inspect the provider-published GBFS discovery and vehicle type metadata.

• hello-cycling-pp-cli feeds discovery — Get advertised anonymous HELLO CYCLING GBFS feed URLs.
• hello-cycling-pp-cli feeds vehicles — Get generic source vehicle classes without assigning station bike models.

Finding the right command

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

hello-cycling-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. --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

Find station IDs

hello-cycling-pp-cli stations find --query 新宿 --limit 5 --agent --select results.id,results.name,results.rental_state,results.return_state

Narrow Japanese name/address matches to station identity and observed state.

Inspect one station

hello-cycling-pp-cli stations show --id 5112 --agent

Read counts, per-type dock compatibility and original timestamps.

Compare both ends

hello-cycling-pp-cli trip compare --from-lat 35.697315 --from-lon 139.704995 --to-lat 35.707252 --to-lon 139.777587 --vehicle-type 2 --agent

Choose short access distances with compatible snapshot capacity.

Read published Tokyo prices

hello-cycling-pp-cli pricing show --area tokyo --agent

Keep Chiyoda and Itabashi exceptions separate.

Auth Setup

No account, API key or location permission is required. Anonymous provider-published GBFS and first-party price pages are read through HTTP. Reserve rides only in the official app.

Run hello-cycling-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 promoted, novel, sync, and --deliver paths:

• --json — one JSON document on stdout (sync progress events go to stderr)

• --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:

  hello-cycling-pp-cli feeds discovery --agent --select last_updated,ttl,version

• 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 HELLO_CYCLING_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: HELLO_CYCLING_CONFIG_DIR, HELLO_CYCLING_DATA_DIR, HELLO_CYCLING_STATE_DIR, HELLO_CYCLING_CACHE_DIR.

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

• config contains JSON settings and saved profiles. data contains data.db, including the explicit station snapshot and local learning tables. state contains runtime state and teach.log. cache contains regenerable HTTP metadata/cache files.

• Run hello-cycling-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:

  {
    "mcpServers": {
      "hello-cycling": {
        "command": "hello-cycling-pp-mcp",
        "env": {
          "HELLO_CYCLING_HOME": "/srv/hello-cycling"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use HELLO_CYCLING_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 HELLO_CYCLING_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 "<question>" 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:

# 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=$(cat /path/to/question.txt)
hello-cycling-pp-cli recall "$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:

{
  "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>", "hello-cycling-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 `hello-cycling-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; hello-cycling-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.
• Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.