Skill

gemini-deep-research

Conducts comprehensive, autonomous deep research on specific topics using Google's Gemini Deep Research API. Initiates long-running background research tasks that synthesize multiple sources into detailed reports. Use when users request deep analysis, comprehensive research, or multi-source synthesis on complex topics. Triggered by phrases like "research", "deep dive", "comprehensive analysis", or when simple fact lookups are insufficient.

From gemini-deep-research
Install
1
Run in your terminal
$
npx claudepluginhub fprochazka/claude-code-plugins --plugin gemini-deep-research
Tool Access

This skill is limited to using the following tools:

Bash(gemini-deep-research:*)
Skill Content

Gemini Deep Research

Perform autonomous deep research using the gemini-deep-research CLI tool, which leverages Google's Gemini Deep Research API to synthesize information from multiple sources.

Usage

Execute research with the gemini-deep-research command:

gemini-deep-research research "Your detailed research query here"

Optional flags:

  • --verbose - Show detailed progress updates
  • --poll-interval N - Check status every N seconds (default: 10)

IMPORTANT:

  • This is a long-running operation that typically takes 3-10 minutes or longer depending on query complexity
  • The tool saves the report to /tmp/gemini-deep-research/<timestamp>/research.md
  • You MUST read this file after the command completes to access the research results

Workflow

  1. Run the gemini-deep-research research command with the user's query
  2. Wait for the command to complete - This will take several minutes (typically 3-10+ minutes). Do not timeout or cancel the operation prematurely.
  3. Read the generated markdown file at the path printed by the tool
  4. Present the research findings to the user

Commands

research

Start a new research task:

gemini-deep-research research "What are the latest developments in quantum computing?"
gemini-deep-research research "Impact of AI on software development" --poll-interval 15
gemini-deep-research research "Future of renewable energy" --verbose

status

Check the status of a running or completed research task:

gemini-deep-research status <interaction-id>

fetch-results

Retrieve and save completed research results (useful if polling was interrupted):

gemini-deep-research fetch-results <interaction-id>

Example

User: "Research the history and architectural evolution of transformer models in NLP"

gemini-deep-research research "Research the history and architectural evolution of transformer models in NLP"

After completion, use the Read tool to access the research report at the path printed by the tool (e.g., /tmp/gemini-deep-research/2025-12-29T08-15-00/research.md).

Similar Skills
cache-components

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.

138.5k
Stats
Parent Repo Stars3
Parent Repo Forks1
Last CommitFeb 15, 2026