Deep Exploration Agent Skill

Saves time by autonomously reading transcripts, synthesizing arguments, and generating direct jump-links to key moments.

475 tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

10025

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/google/adk-samples --skill deep-exploration

The instruction itself

1 sections, as written by the author

Skill: Deep Exploration & Timestamp Targeting

Objective: Save the user from watching hours of video by autonomously reading transcripts, synthesizing the core arguments, and generating direct jump-links to the exact moments of interest.

Execution Steps:

Locate: Use search_youtube to find 3 to 5 highly relevant videos on the specific query. Prioritize videos from different creators to get diverse perspectives.
Ingest (Read): For each video, use get_video_transcript(video_id) to pull the full closed captions with timestamps.
*Fallback*: If the transcript is unavailable, fall back to using get_video_details to read the video's description instead.
Cross-Reference & Target: Analyze the transcripts to find the exact moments where the creator answers the user's specific query.
Link Generation (MANDATORY): For the most valuable moments (clips), you MUST use generate_timestamp_url(video_id, timestamp) to create a direct clickable URL. Do NOT try to guess the ?t= parameter yourself.
Deliver: Present a highly curated "Knowledge Report". For each video, provide a 2-sentence summary of their unique angle, followed by the direct clickable URL to the exact timestamp where the key insight begins.

HTML Publishing Rule: If the user asks to publish this report to HTML, you MUST ensure that the <a> href attributes in your HTML string use the exact URLs returned by the generate_timestamp_url tool. Never use plain https://youtu.be/ID when a specific moment is discussed.

Next Actions: Ask the user if they want to publish this curated list of clips into a permanent HTML Knowledge Report, or if they have any feedback on the tool's accuracy.

Other skills for the same job

different authors, same section of the catalogue

Protocolsio Integration

by christophacham

×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens

Tailored Resume Generator

by frostant

×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens

Excalidraw Diagram Generator

by github

vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

Build and distribute Expo development clients locally or via TestFlight

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens

Benchling Integration

by christophacham

×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take google/deep-exploration from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.