Execute qualquer Skill no Manus
com um clique

Execute qualquer Skill no Manus com um clique

Começar

flight-sweep

Estrelas0

Forks0

Atualizado1 de março de 2026 às 01:31

Batch-collect flight data across date ranges and analyze with filtering, scoring, and HTML viewer generation

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Executar no Manus

Fonte

varunr89

varunr89/claude-marketplace

Abrir repositório GitHub Ver repositórios do creator

Download

Executar no Manus

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

name	flight-sweep
description	Batch-collect flight data across date ranges and analyze with filtering, scoring, and HTML viewer generation

Flight Sweep

A two-phase pipeline for comprehensive flight analysis:

Collect (flight_sweep_collect.py) -- Fetches flight data from Google Flights and Duffel API across multiple departure dates and trip configurations. Caches raw API responses to disk.
Analyze (flight_sweep_analyze.py) -- Reads cached data, applies constraint filters, builds trip scenarios, scores and ranks them, and generates an interactive HTML viewer.

When to use

Use this skill when the user wants to do a broad search across multiple departure dates and trip duration options, compare strategies, and generate a comprehensive ranked report.

Phase 1: Data Collection

DUFFEL_API_KEY=<your-key> python3 ${CLAUDE_PLUGIN_ROOT}/scripts/flight_sweep_collect.py

What it does:

Iterates over configured departure dates (Fridays and Saturdays)
For each date, calculates leg dates for all combinations of Europe nights (21/22/23) and India nights (5/6/7)
Searches both one-way flights (Google Flights + Duffel) and round-trip flights (Duffel only)
Caches each API response as a JSON file in flight_cache/
Skips already-cached searches for incremental re-runs
Rate-limits Duffel requests (0.5s delay between calls)

Cache format: {source}_{origin}_{dest}_{date}[_rt_{return_date}].json

Phase 2: Analysis

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/flight_sweep_analyze.py

What it does:

Reads all cached flight data from flight_cache/
Applies constraint filters:
- Max 1 stop per leg
- Max 4-hour layover
- Single carrier per leg
- Excludes test/synthetic airlines (e.g., "Duffel Airways")
Builds scenarios for both strategies (3 one-ways, 2 round-trips)
Scores each scenario: flight_cost + (hours * $20) + (stops * $200) + (weekdays * $200)
Prints top 10 results to terminal
Generates flight_sweep_viewer.html -- an interactive DataTables-powered HTML viewer with sorting and filtering
Saves full results to flight_sweep_results.json

Configuration

Both scripts share these configurable constants:

Constant	Default	Description
`DEPARTURE_DATES`	Apr 24 - May 8, 2026	List of departure dates to search
`EUROPE_NIGHTS_OPTIONS`	[21, 22, 23]	Europe stay duration options
`INDIA_NIGHTS_OPTIONS`	[5, 6, 7]	India stay duration options
`MAX_STOPS`	1	Maximum stops per leg
`MAX_LAYOVER_HOURS`	4	Maximum layover duration in hours
`COST_PER_HOUR`	20	Scoring penalty per hour of travel
`COST_PER_STOP`	200	Scoring penalty per stop
`COST_PER_WEEKDAY`	200	Scoring penalty per weekday away

Environment variables

Variable	Required	Description
`DUFFEL_API_KEY`	Yes (collect phase)	Duffel API access token

Dependencies

requests (pip install requests) -- Duffel API calls
fast-flights (pip install fast-flights) -- Optional Google Flights scraper

Mais deste repositório

mesmo repositório

computer-use

varunr89/claude-marketplace

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.

2026-03-280

call

varunr89/claude-marketplace

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.

2026-03-230

learn

varunr89/claude-marketplace

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/.

2026-03-150

learn-design

varunr89/claude-marketplace

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.

2026-03-140

article-podcast

varunr89/claude-marketplace

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.

2026-03-080

read-paper

varunr89/claude-marketplace

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.

2026-03-060

name	flight-sweep
description	Batch-collect flight data across date ranges and analyze with filtering, scoring, and HTML viewer generation

Flight Sweep

A two-phase pipeline for comprehensive flight analysis:

Collect (flight_sweep_collect.py) -- Fetches flight data from Google Flights and Duffel API across multiple departure dates and trip configurations. Caches raw API responses to disk.
Analyze (flight_sweep_analyze.py) -- Reads cached data, applies constraint filters, builds trip scenarios, scores and ranks them, and generates an interactive HTML viewer.

When to use

Use this skill when the user wants to do a broad search across multiple departure dates and trip duration options, compare strategies, and generate a comprehensive ranked report.

Phase 1: Data Collection

DUFFEL_API_KEY=<your-key> python3 ${CLAUDE_PLUGIN_ROOT}/scripts/flight_sweep_collect.py

What it does:

Iterates over configured departure dates (Fridays and Saturdays)
For each date, calculates leg dates for all combinations of Europe nights (21/22/23) and India nights (5/6/7)
Searches both one-way flights (Google Flights + Duffel) and round-trip flights (Duffel only)
Caches each API response as a JSON file in flight_cache/
Skips already-cached searches for incremental re-runs
Rate-limits Duffel requests (0.5s delay between calls)

Cache format: {source}_{origin}_{dest}_{date}[_rt_{return_date}].json

Phase 2: Analysis

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/flight_sweep_analyze.py

What it does:

Reads all cached flight data from flight_cache/
Applies constraint filters:
- Max 1 stop per leg
- Max 4-hour layover
- Single carrier per leg
- Excludes test/synthetic airlines (e.g., "Duffel Airways")
Builds scenarios for both strategies (3 one-ways, 2 round-trips)
Scores each scenario: flight_cost + (hours * $20) + (stops * $200) + (weekdays * $200)
Prints top 10 results to terminal
Generates flight_sweep_viewer.html -- an interactive DataTables-powered HTML viewer with sorting and filtering
Saves full results to flight_sweep_results.json

Configuration

Both scripts share these configurable constants:

Constant	Default	Description
`DEPARTURE_DATES`	Apr 24 - May 8, 2026	List of departure dates to search
`EUROPE_NIGHTS_OPTIONS`	[21, 22, 23]	Europe stay duration options
`INDIA_NIGHTS_OPTIONS`	[5, 6, 7]	India stay duration options
`MAX_STOPS`	1	Maximum stops per leg
`MAX_LAYOVER_HOURS`	4	Maximum layover duration in hours
`COST_PER_HOUR`	20	Scoring penalty per hour of travel
`COST_PER_STOP`	200	Scoring penalty per stop
`COST_PER_WEEKDAY`	200	Scoring penalty per weekday away

Environment variables

Variable	Required	Description
`DUFFEL_API_KEY`	Yes (collect phase)	Duffel API access token

Dependencies

requests (pip install requests) -- Duffel API calls
fast-flights (pip install fast-flights) -- Optional Google Flights scraper