agentleFS
bethronbethron/travel-concierge/skills/monitor-fares/SKILL.md

monitor-fares

Skill1 starsChanged 4 months agoMITView on GitHub

This skill should be used whenever the user wants to watch or re-check flight prices — phrases like "track this fare", "watch prices for", "tell me if it gets cheaper", "has the price dropped", "check my fares", "should I book now or wait", or when a traveller hesitates on a flight and wants to keep an eye on it.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep a fare watchlist, re-check it on demand, and advise honestly on book-now versus wait.

    line 15
  2. Distinctive:

    Always state the risk both ways: waiting can save money and can lose the good fare.

    line 58
  3. Distinctive:

    When a watch's trip gets booked or its dates pass, offer to retire it.

    line 60

≈ “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

Monitor Fares

Keep a fare watchlist, re-check it on demand, and advise honestly on book-now versus wait.

Be honest about the mechanism

Claude cannot run in the background: fares are re-checked when asked (or whenever a session touches the watchlist), not continuously. Say this when a watch is created. Offer to create a recurring "Check my fares" reminder or Google Calendar event (every 2–3 days, via sync-calendar's connector) so the traveller remembers to ask — with their consent.

The watchlist — travel/watchlist.md

# Fare Watchlist

## LHR → LIS, out 07 Sep, back 12 Sep, 2 adults
- **Target:** ≤ £120 pp return · **Watching since:** 2026-07-06
- **History:**
  | Checked | Best price (pp) | Source | Airline |
  |---|---|---|---|
  | 2026-07-06 | £142 | Kiwi.com | TAP |

One section per watched route; append a history row on every check. Keep the search parameters exact (airports, dates or date window, party, cabin) so checks compare like with like.

Checking

On "check my fares" (or the /check-fares command): re-run each watch through the flight connectors (Kiwi.com, Expedia; Ryanair for its routes — its cheapest-per-day tool suits date windows), append results, then report per watch: current best, change since last check and since watching began, and whether the target is met.

Advice, honestly

  • Target met → say so plainly and offer to proceed to booking via find-flights.
  • Trend advice must come from the recorded history, not folklore: rising across checks near departure usually keeps rising; do not invent "prices drop on Tuesdays" claims.
  • Always state the risk both ways: waiting can save money and can lose the good fare. The decision stays with the traveller.
  • When a watch's trip gets booked or its dates pass, offer to retire it.

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.