Skip to content
TrustedSkillsbeta
Back to all skills

Gemini

Checked
davila7·vlatest·ai-ml·MIT

Gemini provides creative text generation – ideal for brainstorming content, crafting stories, and exploring diverse writing styles efficiently.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add davila7/claude-code-templates --skill gemini -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

davila7

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

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

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 passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • 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 undeclared network calls: passed

    Makes no network calls.

    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.

  • 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 credential access: passed

    Reads no keys, tokens, keychains or credential files.

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

  • 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 davila7/claude-code-templates at 79182c51fb.

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

Commit
79182c51fb
Manifest
cli-tool/components/skills/ai-research/gemini/SKILL.md
Scanned
2 files, 518 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

The Gemini skill enables AI agents to perform comprehensive text generation and analysis, particularly suited for code review, plan review, and processing large amounts of context (over 200k tokens). It leverages various Gemini models – including gemini-3-pro-preview, gemini-3-flash, gemini-2.5-pro, gemini-2.5-flash, and gemini-2.5-flash-lite - to handle complex tasks efficiently. The skill is designed for both interactive and automated workflows, but requires careful configuration of approval modes.

When to use it

  • Code Review: Analyzing code across multiple files to identify potential issues.
  • Plan Review: Examining architectural plans, technical specifications, or project roadmaps for inconsistencies or areas needing improvement.
  • Large Context Processing: Tasks involving extensive documentation sets or entire codebases that exceed typical token limits.
  • Multi-file Analysis: Understanding relationships and patterns across numerous files within a project.

Key capabilities

  • Supports multiple Gemini models: gemini-3-pro-preview, gemini-3-flash, gemini-2.5-pro, gemini-2.5-flash, and gemini-2.5-flash-lite.
  • Offers different approval modes for interactive (default), automated editing (auto_edit), or fully automated execution (yolo).
  • Capable of processing contexts exceeding 200,000 tokens.
  • Designed for analyzing relationships and patterns across multiple files.

Example prompts

  • "Please review this codebase using the gemini-3-pro-preview model with YOLO approval mode."
  • "Can you analyze these architectural plans and identify any potential structural weaknesses, using the gemini-2.5-flash model?"
  • "Review these technical specifications for consistency and completeness, selecting the best available Gemini model."

Tips & gotchas

  • Approval Mode is Critical: Never use --approval-mode default in non-interactive environments (like automated tool calls) as it will cause the process to hang indefinitely. Use --approval-mode yolo for fully automated tasks or wrap execution with a timeout (timeout 300 gemini ...).
  • Model Selection: The skill requires you to specify which Gemini model to use in a single prompt. Consider gemini-3-pro-preview for complex reasoning and coding, while gemini-3-flash prioritizes speed.
  • Hung Process Symptoms: If the process runs for over 20 minutes with no CPU usage or network activity, it may be hung. Use ps aux | grep gemini | grep -v grep to check and pkill -9 -f "gemini.*gemini-3-pro-preview" to terminate if necessary.