name	poi-discovery-briefing
description	Extracts specific local activity recommendations and sentiment from travel vlogs into a shareable HTML BD report.

Skill: POI & Activity Discovery Briefing (Travel BD)

Objective: Equip an Online Travel Agency (OTA) Business Development (BD) team with actionable data on local activities around a specific Point of Interest (POI). Extract recommendations from travel vloggers, gauge audience sentiment, and package it into a shareable HTML report.

Execution Steps:

Locate Context: Use search_youtube to find highly relevant travel vlogs about the requested POI (e.g., "Mount Fuji travel vlog", "Things to do in Tokyo").
Extract Activities (Read): Use get_video_transcript on the top 2-3 longest vlogs. Travel vloggers often list 10+ activities in a single video. Scan the transcript to identify the specific names of activities, restaurants, or sub-locations they mention.
Map Timestamps: Crucially, use generate_timestamp_url to create a direct jump link to the exact second the vlogger begins talking about each specific activity.
Community Audit: Use get_video_comments for the videos to see if the audience is agreeing with the vlogger's recommendations or complaining about them (e.g., "The boat ride is a tourist trap").
Synthesize Report: You must automatically format this data into a professional HTML "BD Briefing" document.
- For each activity discovered, list: The Activity Name, The Vlogger's Verdict, The Audience Sentiment, and the <a href="..."> direct timestamp link.
- Embed the high-res thumbnail of the source video at the top of the report to make it visually appealing. (You can get this from get_video_details).
Deliver & Publish: Call publish_file(content=html_string, filename="poi_briefing.html") to upload the final HTML string to the cloud. Return the generated public URL directly to the user in the chat so they can immediately share it with their BD team.

Más de este repositorio

mismo repositorio

scaffold-python-sample

google/adk-samples

This skill should be used when the user wants to "create a new Python ADK sample", "scaffold a new Python sample recipe", "generate a new Python sample in contrib", "add a new Python sample to the adk-samples repository", or "create a Python adk sample". It utilizes an automated script to copy template files and resolve basic placeholders.

2026-07-109.9k

generate-manifest

google/adk-samples

Scan an ADK recipe directory and generate a manifest.yaml for it based on the schema at .github/schemas/manifest-schema.json. Use when the user wants to create or generate a manifest.yaml for a recipe under core/ or contrib/.

2026-07-099.9k

travel-concierge

google/adk-samples

Accesses real-time spatial data, weather, and traffic routing to design accurate itineraries.

2026-05-229.9k

abcd-framework-audit

google/adk-samples

Performs a strict evaluation of a video asset using Google's official 'ABCD' framework (Attract, Brand, Connect, Direct) based on transcript and metadata.

2026-04-029.9k

creative-insight-analyzer

google/adk-samples

Deconstructs high-performing or viral videos to extract actionable creative insights from metadata and transcript.

2026-04-029.9k

daily-briefing

google/adk-samples

Provides a high-signal briefing on events in a specific location and timeframe, backed by primary video sources and transcripts.

2026-04-029.9k

name	poi-discovery-briefing
description	Extracts specific local activity recommendations and sentiment from travel vlogs into a shareable HTML BD report.

Skill: POI & Activity Discovery Briefing (Travel BD)

Execution Steps:

Locate Context: Use search_youtube to find highly relevant travel vlogs about the requested POI (e.g., "Mount Fuji travel vlog", "Things to do in Tokyo").
Extract Activities (Read): Use get_video_transcript on the top 2-3 longest vlogs. Travel vloggers often list 10+ activities in a single video. Scan the transcript to identify the specific names of activities, restaurants, or sub-locations they mention.
Map Timestamps: Crucially, use generate_timestamp_url to create a direct jump link to the exact second the vlogger begins talking about each specific activity.
Community Audit: Use get_video_comments for the videos to see if the audience is agreeing with the vlogger's recommendations or complaining about them (e.g., "The boat ride is a tourist trap").
Synthesize Report: You must automatically format this data into a professional HTML "BD Briefing" document.
- For each activity discovered, list: The Activity Name, The Vlogger's Verdict, The Audience Sentiment, and the <a href="..."> direct timestamp link.
- Embed the high-res thumbnail of the source video at the top of the report to make it visually appealing. (You can get this from get_video_details).
Deliver & Publish: Call publish_file(content=html_string, filename="poi_briefing.html") to upload the final HTML string to the cloud. Return the generated public URL directly to the user in the chat so they can immediately share it with their BD team.