agentleFS
chenzd01chenzd01/onetrip/.claude/skills/new-trip/SKILL.md

new-trip

Skill0 starsChanged 53 days agoMITView on GitHub

Turn this OneTrip template into an iOS app for a new destination. Walks the user through the trip brief, content/trip.json, evidence-based research, itinerary, validation, build and simulator check, following the repository's own playbook. Use when the user wants to make the app for a trip, e.g. "/new-trip 京都 2027-11-16..18 2人" or "make this app for my Lisbon trip".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ss2code/nanoclaw-ops★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read AGENTS.md first and follow it throughout.

    line 11
  2. Very specific:

    Commit ios/Signing.xcconfig, ios/SharedAccess.xcconfig, keys, booking references or personal data.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

New trip

You are making this repository's app for the user's next trip. Everything the app shows comes from content/; do not change Swift or Python code unless the user asks for a feature or fix.

Read AGENTS.md first and follow it throughout. Reply in the user's language. The detailed, copy-ready prompt for every phase is in docs/zh/agent-prompts.md (Chinese) and docs/en/agent-prompts.md (English); the phases below follow them, so read the matching section before starting each phase.

Phases

  1. Brief — collect destination, first/last day, departure date, flights (times only), party size, pace, must-see / skip lists, food limits, budget level and local language. Write docs/research/00-brief.md and ask the questions you still need answered. Stop and wait for the user to confirm the brief.
  2. Destination config — replace content/trip.json (new id, IANA timezone, map bounds that just cover the trip, dated exchange-rate source, speech.language). Run python3 scripts/verify_content.py.
  3. Research — places + coordinates, dining, preparation, phrases, references, photos (openly licensed only), optional hotels and posts, strictly by docs/<lang>/research-playbook.md: official sources read in a browser, every fact with a source URL and checkedAt, official price kept apart from planning budget, conflicts recorded instead of guessed. Keep a research record per content type in docs/research/ (template: docs/templates/research-record.md). Independent content types can be researched in parallel (for example with sub-agents), each writing its own file.
  4. Itinerary — content/itinerary.json: one entry per trip day, clustered by area, 15–45 min buffers, hard constraints first, a rainy-day swap in each day's note.
  5. Gate and build —
    python3 scripts/verify_content.py --require-complete
    python3 scripts/build_ios_resources.py && python3 scripts/verify_content.py --built-catalog
    make test
    Fix until everything passes and report exact test counts.
  6. Look at it — run the app in the simulator (make open), check every tab and day for blanks, truncation, wrong dates or leftover example text. make screenshots produces shareable images of the user's own trip in docs/assets/.
  7. Ship (only when asked) — docs/<lang>/ios-delivery.md. Tell the user before any App Store Connect action and wait for a yes.

Never

  • Book, pay, submit forms, sign in, send messages or change accounts: stop before guest details or payment and report what you saw.
  • Invent coordinates, prices, hours, photos or reviews; leave a gap and say so.
  • Commit ios/Signing.xcconfig, ios/SharedAccess.xcconfig, keys, booking references or personal data. The user's trip repository should stay private; run python3 scripts/privacy_check.py --history before anything is published.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.