transport-and-passes
Use when recommending transit for a trip — drive vs train vs fly, rail-pass selection, seat reservations and supplements, drive-time honesty. Invoked by trip-planner.
Best use case
transport-and-passes is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when recommending transit for a trip — drive vs train vs fly, rail-pass selection, seat reservations and supplements, drive-time honesty. Invoked by trip-planner.
Teams using transport-and-passes should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/transport-and-passes/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How transport-and-passes Compares
| Feature / Agent | transport-and-passes | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when recommending transit for a trip — drive vs train vs fly, rail-pass selection, seat reservations and supplements, drive-time honesty. Invoked by trip-planner.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# transport-and-passes The mechanics of getting between bases. Mistakes here cascade into the entire trip — a missed reservation, an underbought pass, or a lied-to drive estimate ruins everything downstream. ## Drive-time honesty (load-bearing) Houston is a 9-hour drive from Kansas Flint Hills. Houston to Florida 30A is 9–10 hours. These are not "weekend" trips. The rule: | One-way drive from home base | Trip-shape that fits | |---|---| | ≤ 2 hours | True weekend (Fri eve → Sun) | | 2–4 hours | 2-night weekend, leave Friday | | 4–6 hours | 3-night long weekend; whole Friday is travel | | 6–8 hours | Minimum 4 nights; first and last day are pure transit | | 8–10 hours | Minimum 5–6 nights; consider flying | | > 10 hours | Fly OR break the drive into 2 days each direction | **Always state the realistic drive time in the Trip parameters table** — round up, not down. Google Maps shows the optimistic time; with kids, plan × 1.25. ## When to recommend a rail pass | Country | Default pass | When NOT to buy | |---|---|---| | Switzerland | Swiss Travel Pass (4/6/8/15-day, consecutive or flex) | Single-city stay (point-to-point cheaper) | | Japan | JR Pass (7/14/21-day) — but post-2024 price hike means do the math | Trip is mostly Tokyo / single region | | France/Italy/Spain | Eurail Pass (only if 4+ countries OR 7+ travel days) | 1–2 country trip; just buy advance fares | | UK | BritRail Pass | Mostly London; just use Oyster + advance fares | | Germany | Deutschland-Ticket if doing slow regional trains | Long-distance ICE-heavy trip | | US (multi-state) | No rail pass exists; Amtrak USA Rail Pass is rarely worth it | Unless you're explicitly doing a 30-day cross-country rail adventure | ## What rail passes DON'T cover (the supplement gotcha) This is where families get blindsided. A "comprehensive" rail pass usually does NOT cover: - **Seat reservations** on premium / panoramic / international trains (Glacier Express, Bernina Express, TGV, AVE, Eurostar, Frecciarossa, Shinkansen Nozomi) - **Sleeper berths** on overnight trains - **Mountain railways** at full price — most are 25%–50% discounted, not free - **Some boats / cable cars** that the marketing implies are included - **Reservation supplements** for the panoramic-window cars on scenic trains **Always state explicitly what the pass includes vs what costs extra.** Use the #68 phrasing pattern: > The Swiss Travel Pass covers free travel on the entire SBB network plus … and gives **50% off** mountain railways like Jungfraujoch, Gornergrat, Pilatus, and Schilthorn; and panoramic-train **base fare is included** (you still pay seat-reservation supplements). ## Reservation reality | Train type | Reservation policy | |---|---| | Glacier Express, Bernina Express | **Mandatory**, fills weeks ahead in summer | | Jungfrau Railway / Top of Europe | Strongly recommended; ascent slots fill same-day in peak | | Italian Frecciarossa, Spanish AVE | Mandatory, advance fares much cheaper than walk-up | | French TGV | Mandatory | | Japanese Shinkansen | Optional but recommended; non-reserved cars exist | | Most other European IC trains | Open seating, no reservation | | US Amtrak | Reserved by default | When in doubt, **say "verify reservation policy on the operator's site"** rather than guessing. ## When to fly instead of drive/train Flying is the right answer when: - Drive > 10 hours one-way (almost always) - Train transit > 8 hours and not itself a scenic experience - Time on the trip is the binding constraint - The destination's main airport has direct flights from the home airport - The family includes someone with mobility issues for whom long road trips are punishing Flying is the wrong answer when: - The transit IS the experience (Glacier Express, ferry to a Greek island, ROAD trip down PCH) - The destination is small enough that the airport is far / requires a connector flight - Total trip is ≤ 4 days (transit eats more proportionally) ## Local-transit defaults to mention In every international trip plan, name the local transit app / pass: | Region | Mention | |---|---| | Switzerland | SBB Mobile app, Swiss Travel Pass on phone | | Japan | Suica/Pasmo cards, Google Maps for routing | | London | Contactless tap with bank card (no Oyster needed since 2014) | | Paris | Navigo Easy / RATP app | | Iceland | Self-drive only; no public transit outside Reykjavík | | Scandinavia | Domestic apps (SJ in Sweden, NSB/Vy in Norway) | | US national parks | Park-specific shuttles (Zion, Acadia); state DMV for tolls | ## The "what if a leg falls through" question For every load-bearing transit leg, name a fallback. Example for #68: - If Glacier Express is sold out: take the regular SBB regional train Zermatt → Brig → Visp → Chur (same scenery, no panoramic windows, no supplement) - If Jungfraujoch closes due to weather: shift to Schilthorn / Mt. First / lower-altitude Lauterbrunnen valley walks - If a connection is missed: SBB rebooks for free on the next train This pattern — "Plan B for every load-bearing leg" — is what separates a real travel agent from generic itinerary writers. ## Reference patterns - **#41 Houston → Broken Bow (6.5 hrs):** drive is honest in the trip body; cabin destination is worth the long drive - **#45 Houston → Flint Hills (9–10 hrs):** drive time stated upfront; trip framed as 3–4 day, not weekend - **#68 Switzerland:** Swiss Travel Pass detailed; supplements called out; reservation policy per train type
Related Skills
test-oversized-skill
A test fixture skill that exceeds 200 lines with multiple H2/H3 sections for split testing.
interactive-report-generator
Generate interactive HTML reports with Plotly visualizations from data analysis results. Supports dashboards, charts, and professional styling.
data-validation-reporter
Generate interactive validation reports with quality scoring, missing data analysis, and type checking. Combines Pandas validation, Plotly visualization, and YAML configuration for comprehensive data quality reporting.
agent-os-framework
Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.
OrcaFlex Specialist Skill
```yaml
repo-ecosystem-hygiene
Interpret the daily read-only repo ecosystem hygiene audit and route remediation through approved workflows.
domain-knowledge-sweep
Systematic multi-source research of an engineering domain. Spawns parent issue → 6 research subissues (Standards, Academic, Industry, LinkedIn-marketing, Code-audit, Synthesis) → gap implementation subissues. Replaces LinkedIn-only extraction with defensible comprehensive sourcing.
subagent-write-verification
Independently verify subagent-claimed file writes with filesystem and git checks before treating the artifact as real, before committing it, and before referencing the path in downstream prompts.
git-operation-serialization-preflight
Before any commit, stash, merge, reset, rebase, or checkout in a multi-agent or shared-checkout environment, run a bounded preflight to detect active git writers and stale index/config locks, then serialize the mutating step under a single-writer guarantee.
public-knowledge-graph-governance
Maintain public-safe knowledge graph artifacts for llm-wiki and similar markdown knowledge bases. Use when changing graph generators, validators, schema docs, weekly freshness checks, or public/private source-scope boundaries.
llm-wiki-weekly-freshness
Class-level governance workflow for keeping llm-wiki-style markdown knowledge bases current, public-safe, graph/index-valid, and useful for code development. Use when reviewing llm-wiki architecture/content, scanning new LLM concepts, maintaining public knowledge graphs, producing an issue roadmap, or running recurring freshness cadence.
llm-wiki-source-extraction-coverage
Doc-type-aware extraction contract for llm-wiki source ingestion with measurable coverage and source-anchored traceability. Use when (1) ingesting a PDF, DOCX, XLSX, PPTX, HTML, or scanned-image source into a wiki `sources/` page, (2) computing the pre-extraction estimate (what fraction of the source we expect to recover) and post-extraction yield (what fraction we actually recovered), (3) anchoring wiki claims back to specific page / paragraph / cell / slide positions in the source so a reviewer can re-verify or revise against the actual document, (4) deciding whether OCR fallback or manual transcription is needed. Codifies workspace-hub's existing OCR fallback chain and python-docx / openpyxl / trafilatura patterns into a format-specific routing table. Companion to research/llm-wiki-page-shape-contract (Rule 7 input-layer pages) and research/llm-wiki — this skill is the defense against silent extraction failure.