Deep Research

This is a production-grade wrapper around Gemini's deep research API that actually handles the messy parts: async polling with adaptive intervals, RAG grounding against local codebases via ephemeral file stores, cost estimation before you commit, and structured output in markdown, HTML, or PDF. The security model is thoughtful: it auto-excludes .env files and credentials, shows you exactly what gets uploaded with dry-run, and cleans up ephemeral stores when done. You'd reach for this when Claude needs to answer questions that require synthesizing information from multiple sources or your own documentation, especially in codebases where context matters. The agent integration is clean with JSON contracts and decision trees, though you'll want to set cost guards since deep research runs can add up quickly.

skills.sh installs: 291
GitHub stars: 9
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add 24601/agent-deep-research --skill deep-research --agent claude-code

Installs into .claude/skills of the current project.

Files

Deep Research Skill

Perform deep research powered by Google Gemini's deep research agent. Upload documents to file search stores for RAG-grounded answers. Manage research sessions with persistent workspace state.

For AI Agents

Get a full capabilities manifest, decision trees, and output contracts:

uv run {baseDir}/scripts/onboard.py --agent

See AGENTS.md for the complete structured briefing.

Command	What It Does
`uv run {baseDir}/scripts/research.py start "question"`	Launch deep research
`uv run {baseDir}/scripts/research.py start "question" --context ./path --dry-run`	Estimate cost
`uv run {baseDir}/scripts/research.py start "question" --context ./path --output report.md`	RAG-grounded research
`uv run {baseDir}/scripts/store.py query <name> "question"`	Quick Q&A against uploaded docs