メニュー
Search and score multi-leg flight itineraries using Duffel API with cost-duration-stop optimization
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when the user asks to "browse a website", "go to a URL", "fill out a form", "take a screenshot", "click on something", "extract data from a page", "automate a browser task", "control the desktop", "use the computer", or any task involving web pages or desktop applications.
Use when the user wants to make a phone call, leave a voicemail, call a business, reach someone by phone, or navigate a phone menu. Triggered by "/call" followed by a phone number and purpose.
Start or continue a progressive learning session. Use when the user says "learn", "let's learn", "continue learning", "let's continue", "pick up where we left off", "teach me", "next lesson", or wants to resume their learning curriculum. Requires a phase map to exist in docs/phases/.
Design progressive learning curricula and generate project phase maps. Use when the user says "learn-design", "design curriculum", "plan learning path", "set up next project", "what should I learn next", or wants to start learning a new technical area. Also triggers between projects to generate the next project's phase map calibrated to the learner's profile.
This skill converts any content source into podcast episodes. Triggers: sending a URL, PDF, YouTube link, book, or file with intent to listen; phrases like 'podcast this', 'make this a podcast', 'listen to this', 'generate a podcast'; sending content with instructions like 'split by chapters', 'make a series'. Handles single articles, multi-chapter books, YouTube playlists, and any document format.
This skill should be used when the user asks to "read a paper", "understand a paper", "analyze a research paper", "prepare for paper discussion", "work through a paper", "do a literature review", or provides PDF paths to research papers. Guides deep paper understanding using Keshav's three-pass method with AI as a patient professor. Supports multiple papers for literature review.
| name | flight-search |
| description | Search and score multi-leg flight itineraries using Duffel API with cost-duration-stop optimization |
Searches for multi-leg flight itineraries (e.g., Seattle -> Milan -> Hyderabad -> Seattle) using the Duffel API (with optional fast-flights Google Flights scraper fallback). Applies hard constraints and a weighted scoring model to rank results.
Use this skill when the user wants to search for flight options across multiple legs with constraint filtering and convenience-adjusted scoring.
DUFFEL_API_KEY=<your-key> python3 ${CLAUDE_PLUGIN_ROOT}/scripts/flight_optimizer.py
The script currently targets a specific trip (SEA -> MXP -> HYD -> SEA), but the functions are reusable for any multi-leg itinerary.
| Variable | Required | Description |
|---|---|---|
DUFFEL_API_KEY | Yes | Duffel API access token (live or test mode) |
The optimizer applies hard constraints to filter out unsuitable flights:
MAX_STOPS)MAX_LAYOVER_HOURS)Each flight leg is scored as:
leg_score = price + (duration_hours * $20) + (stops * $200)
Complete itineraries add a childcare penalty:
total_score = sum(leg_scores) + (weekdays_away * $200)
Scoring weights are configurable constants: COST_PER_HOUR, COST_PER_STOP, COST_PER_WEEKDAY.
The optimizer tries two strategies and ranks all results together:
flight_results_spring2026.json (top 30 itineraries)