agentleFS
QuixiAIQuixiAI/Hexis/skills/installed/travel-prep/SKILL.md

travel-prep

Skill623 starsChanged 10 months agoMITView on GitHub

Turn calendar events, confirmations, current research, and personal context into a practical trip brief

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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. Distinctive:

    Gather owned facts: Read the relevant calendar events and, when useful, search email for booking confirmations.

    line 19
  2. Very specific:

    Recover personal context: Use recall for stated preferences, accessibility needs, previous promises, and destination context.

    line 20
  3. Very specific:

    Research what can change: Use web_search and web_fetch for current entry requirements, transit disruptions, opening hours, …

    line 21
  4. Distinctive:

    Never book, buy, cancel, check in, or submit traveler information.

    line 27
  5. Distinctive:

    Never silently move an event or infer a missing date, traveler, currency, visa status, or reservation.

    line 28
  6. Distinctive:

    If calendar or email access is unavailable, continue from details the user provides and state exactly what is missing.

    line 30
  7. Distinctive:

    Keep unknowns visible. A short plan with an explicit gap is better than a complete-looking fiction.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Travel Preparation

Build a source-grounded plan for a trip without turning planning into an unauthorized booking or purchase.

Workflow

  1. Establish the trip. Confirm the destination, dates, travelers, origin, time zone, and any constraints the user supplied. If several calendar events could be the trip, show the candidates and ask which one they mean.
  2. Gather owned facts. Read the relevant calendar events and, when useful, search email for booking confirmations. Treat confirmation numbers, addresses, times, and baggage or check-in rules as sensitive. Include them only when they help the user and do not persist them unless asked.
  3. Recover personal context. Use recall for stated preferences, accessibility needs, previous promises, and destination context. Never convert a weak or unrelated memory into a trip requirement.
  4. Research what can change. Use web_search and web_fetch for current entry requirements, transit disruptions, opening hours, weather-dependent advice, and other time-sensitive facts. Name the source and checked date. Separate official requirements from suggestions.
  5. Build the brief. Present a chronological itinerary, unresolved gaps, departure checklist, local logistics, reservations, contacts, and a short contingency section. Preserve local times and label time zones when ambiguity is possible.
  6. Offer actions. Propose calendar blocks or tasks after the brief. Create or update them only when the user explicitly chooses the exact action and destination system. Prefer the local backlog when no external task service is configured.

Control and Failure Boundaries

  • Never book, buy, cancel, check in, or submit traveler information. This skill prepares; it does not transact.
  • Never silently move an event or infer a missing date, traveler, currency, visa status, or reservation.
  • A request to "prepare" authorizes reading and drafting, not calendar changes, outbound mail, or task creation.
  • If calendar or email access is unavailable, continue from details the user provides and state exactly what is missing. Give the concrete setup or input needed next instead of ending at an error.
  • Keep unknowns visible. A short plan with an explicit gap is better than a complete-looking fiction.

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.