mcpField
D
deep-research

deep-research

github.com/cnemriProductivity128103 installsUpdated 38w ago
Repository

About deep-research

A command-line skill for autonomous research using the Gemini Deep Research Agent through the Interactions API. It plans searches, reads web and supplied files, and synthesizes cited reports, with options for follow-up research and saved output.

Key features

  1. 01Autonomous research planning and search
  2. 02Read web sources and local files
  3. 03Index large file collections for search
  4. 04Stream results with reconnect handling
  5. 05Save cited reports and continue sessions

Use cases

  1. 01Research a technical topic
  2. 02Analyze a report or meeting notes
  3. 03Find trends across a large PDF corpus
  4. 04Ask follow-up questions about a report

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cnemri/google-genai-skills --skill deep-research

After installing, type/deep-researchin Claude Code to confirm it loaded.

Bundled filesreferences/online_docs.mdscripts/research.py

Details

From the project README

Deep Research

Use this skill to conduct deep, autonomous research tasks that require planning, searching, reading, and synthesizing information.

This skill uses the Gemini Deep Research Agent (deep-research-pro-preview-12-2025) via the Interactions API.

Prerequisites

  • GOOGLE_API_KEY: Required for accessing the Interactions API (currently in Preview via AI Studio).
  • google-genai SDK v0.3.0+

Usage

Basic Research

Start a research task and stream the results to the console.

uv run skills/deep-research/scripts/research.py "Research the history of RISC-V architecture."
Research with Context (Files or Directories)

Provide local files (PDFs, text) or entire directories for the agent to read and incorporate into its research.

Direct Upload (Best for specific docs):

# Single file
uv run skills/deep-research/scripts/research.py "Analyze this report" --file report.pdf

# Entire directory
uv run skills/deep-research/scripts/research.py "Summarize these meeting notes" --file ./notes/

File Search Store (Best for large corpora): Use --use-file-store to index files into a searchable store (RAG) instead of uploading them into the context window.

uv run skills/deep-research/scripts/research.py "Find trends in these 1000 PDFs" --file ./large_corpus/ --use-file-store
Saving the Report

Save the final Markdown report to a file.

uv run skills/deep-research/scripts/research.py "Competitive landscape of EV batteries" --output report.md
Continuing Research (Follow-up)

Ask follow-up questions to an existing research session using the Interaction ID (displayed at the start of the previous run).

uv run skills/deep-research/scripts/research.py "Elaborate on the second point about lithium supply." --follow-up "INTERACTION_ID_HERE"

References

How it Works

  1. Planning: The agent breaks down your prompt into steps.
  2. Execution: It autonomously searches the web and reads your provided files.
  3. Resilience: The script automatically reconnects if the long-running stream drops.
  4. Synthesis: It produces a comprehensive, cited report.

Comments

Markdown supported