Skip to content
Agentmart
Submit a tool

flight-search

Discovers and compares flight options with price, duration, and layover filtering via MCP

Skill by SathishKumar140

IndexedMIT
Write a review

Chalk Labs

Need help deploying flight-search?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sathishkumar140-flight-search

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Discovers and compares flight options with price, duration, and layover filtering via MCP

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/flight-search

What's inside

Skill name
flight-search
Description
Discovers and compares flight options with price, duration, and layover filtering via MCP
License
MIT
Compatibility
Python 3.10+
Metadata
subagent: travel_specialist
Instructions
21 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Flight Search Skill

## Overview
Queries specific flights or a bounded sample of travel windows via MCP. A sampled minimum is not the cheapest fare across the entire month.

## When to Use
- When users mention specific travel dates between cities (use `search_flights`).
- When users ask to "find the cheapest", "suggest dates", or look for the best price for a trip duration (e.g. 5 days) across a month (use `search_cheapest_flights_in_month`).

## Instructions
1. **Specific Dates**: If the user provides specific departure/return dates, call `search_flights(departure_id, arrival_id, outbound_date, return_date)`.
2. **Find Cheapest / Suggest Dates across Month**: If the user asks for the cheapest dates, asks to suggest dates, or gives a duration and month (e.g. "five days in November", "cheapest for 5 days next month"):
   - When departure, destination, month, and duration are known, immediately call `search_cheapest_flights_in_month(departure_id, arrival_id, month, duration_days)`. Default adults to 1 if not specified. Do not defer or block searching by asking for traveler count or currency.
   - Present the recommended cheapest dates, price comparisons across the tested windows, and top flight options with airlines, dates, and fares!
3. **Completely Missing Route/City**: If departure or destination is completely unknown, clarify the missing city.
4. Format response highlighting the best travel dates, prices, carrier, departure times, and total travel time.
5. The actual tool schema is authoritative. Supply departure_evidence_id and departure_text from this topic's user messages. Never default to SIN, a currency, or another trip's origin.
6. Use future dates exactly as requested; ask about ambiguous years. Forward adults and currency. State whether fares are per person or total only if the provider establishes it.
7. Report unavailable searches honestly. Cite only returned public URLs; distinguish sampled dates and search leads from confirmed fares or bookings.

From SathishKumar140/roam.ai, MIT.

More from SathishKumar140/roam.ai

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 19, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from SathishKumar140

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get flight-search running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying flight-search?

CallGet help
Cite this page

flight-search skill. Agent Mart. https://agentmart.dev/skills/sathishkumar140-flight-search (last updated 2026-10-24)