Skip to content
TrustedSkillsbeta
Back to all skills

Agent Deep Research

Listed
24601·v1.0.0·ai-ml·MIT

Async deep research via Gemini Interactions API. RAG-ground queries on local files, preview costs with --dry-run, get structured JSON output. Universal skill for 30+ AI agents.

Repository

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $ openclaw skills install agent-deep-research

What we know about this skill

Publisher

24601

Taken from the source listing. We haven't verified who controls this account.

Install target

Pinned to 1b90f0df

Installs fetch a stored snapshot of that commit, so the code can't change after the fact.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 3 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: 169.254.169.254, aistudio.google.com, docs.astral.sh.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    github.comsource hostdocs.astral.shundeclaredaistudio.google.comundeclared169.254.169.254undeclared

    What it found (3 of 5)

    • scripts/onboard.py:142contacts docs.astral.sh
      "Install: https://docs.astral.sh/uv/getting-started/installation/",
    • scripts/onboard.py:283contacts docs.astral.sh
      "runtime": "uv (https://docs.astral.sh/uv/)",
    • scripts/onboard.py:368contacts docs.astral.sh
      console.print("    See: https://docs.astral.sh/uv/getting-started/installation/")

  • No credential access: failed

    Touches credential material in 2 places.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

    What it found

    • scripts/research.py:263SSH private keys or config
      "id_rsa", "id_ed25519", "id_ecdsa", "id_dsa",
    • scripts/upload.py:195SSH private keys or config
      "id_rsa", "id_ed25519", "id_ecdsa",

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned 24601/agent-deep-research at 1b90f0df29.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
1b90f0df29
Manifest
SKILL.md
Scanned
29 files, 6,117 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill enables deep research and retrieval-augmented generation (RAG) capabilities within AI agents. It leverages the Google Gemini Interactions API to search files and provide grounded responses, integrating seamlessly with a wide range of agent platforms. The skill utilizes the google-genai Python SDK directly via uv run, eliminating the need for the Gemini CLI.

When to use it

  • Complex Research Tasks: When an agent needs to gather information from multiple files and synthesize a comprehensive answer, such as researching competitor strategies or summarizing legal documents.
  • File-Based Knowledge Base: To enable agents to access and utilize specific data stored in files, like product documentation or internal reports.
  • Code Understanding & Assistance: Help an agent understand and debug code by searching relevant files within a project repository.
  • Automated Report Generation: Generate reports based on information extracted from various documents.

Key capabilities

  • Google Gemini Interactions API integration
  • Retrieval-Augmented Generation (RAG)
  • File search functionality
  • Compatibility with Claude Code, Amp, Codex, OpenCode, Cursor, Gemini CLI, Pi, and 30+ other agents.
  • Direct use of google-genai Python SDK

Example prompts

  • "Research the latest trends in sustainable energy and summarize your findings."
  • "Find all files related to 'Project Phoenix' and create a brief overview."
  • "What are the key differences between these two code snippets, based on available documentation?"

Tips & gotchas

  • A Google API key is required for this skill. Ensure you have configured either GEMINI_DEEP_RESEARCH_API_KEY, GOOGLE_API_KEY, or GEMINI_API_KEY environment variable.
  • The skill relies on uv; ensure it's installed correctly before attempting to use the skill.

Requirements

Required binaries

uv

Environment variables

GOOGLE_API_KEY

This skill expects these to be set in its environment — it will have access to their values.

Tags

researchgeminiraggroundingstructured-outputuniversal