How do I install the Using Gemini skill?

Run npx skillmds@latest add majiayu000/using-gemini in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Using Gemini safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Using Gemini?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Using Gemini free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Using Gemini?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Using Gemini by majiayu000 — Agent Skill

Name: Using Gemini
Rating: 4.2 (5 reviews)
Author: majiayu000

Using Gemini

Use when needing to analyze images (screenshots, diagrams, photos), analyze videos (screencasts, recordings), summarize YouTube videos, fetch and analyze web content, or perform web searches with Google. Gemini CLI provides multimodal and web access capabilities Claude lacks natively. Do NOT use for tasks Claude can handle directly (text analysis, code review, file reading of text files).

majiayu000 Updated Sep 9, 2026 567 repo stars

File contents

Using Gemini CLI

Gemini CLI extends Claude's capabilities with multimodal and web access features. Use it for tasks Claude cannot do natively: analyzing images, analyzing videos, accessing YouTube content, fetching web pages, and searching the web with Google.

Base Command Syntax

gemini --allowed-mcp-server-names "" [other-flags] "Your prompt here"

Always use --allowed-mcp-server-names "" to disable MCP servers for faster startup.

Controlling Detail Level

Control the detail level of Gemini's responses through your prompt wording:

For comprehensive analysis: Add "in detail" to your prompt
For quick summaries: Use "briefly" in your prompt

Note: Each use case may have specific wording requirements. Check the reference file for use-case-specific guidance on prompt wording.

Use Cases

Read the specific reference file for the action you need to perform. Each reference contains the exact command patterns, flags, and examples for that use case.

Image Analysis

When: Analyze screenshots, diagrams, photos, or extract text from images Read: references/image-analysis.md

Video Analysis

When: Analyze local video files (screencasts, recordings, demos) Read: references/video-analysis.md

YouTube Videos

When: Summarize YouTube videos, extract information, or get key points Read: references/youtube.md

Web Fetch

When: Fetch and analyze content from any URL (articles, documentation, pages) Read: references/web-fetch.md

Web Search

When: Search Google for current information or documentation Read: references/web-search.md

---name: using-geminidescription: Use when needing to analyze images (screenshots, diagrams, photos), analyze videos (screencasts, recordings), summarize YouTube videos, fetch and analyze web content, or perform web searches with Google. Gemini CLI provides multimodal and web access capabilities Claude lacks natively. Do NOT use for tasks Claude can handle directly (text analysis, code review, file reading of text files).--- # Using Gemini CLI **Gemini CLI extends Claude's capabilities with multimodal and web access features.** Use it for tasks Claude cannot do natively: analyzing images, analyzing videos, accessing YouTube content, fetching web pages, and searching the web with Google. ## Base Command Syntax ```bash gemini --allowed-mcp-server-names "" [other-flags] "Your prompt here" ``` **Always use `--allowed-mcp-server-names ""` to disable MCP servers for faster startup.** ## Controlling Detail Level Control the detail level of Gemini's responses through your prompt wording: - **For comprehensive analysis:** Add "in detail" to your prompt - **For quick summaries:** Use "briefly" in your prompt **Note:** Each use case may have specific wording requirements. Check the reference file for use-case-specific guidance on prompt wording. ## Use Cases **Read the specific reference file for the action you need to perform.** Each reference contains the exact command patterns, flags, and examples for that use case. ### Image Analysis **When:** Analyze screenshots, diagrams, photos, or extract text from images **Read:** [references/image-analysis.md](references/image-analysis.md) ### Video Analysis **When:** Analyze local video files (screencasts, recordings, demos) **Read:** [references/video-analysis.md](references/video-analysis.md) ### YouTube Videos **When:** Summarize YouTube videos, extract information, or get key points **Read:** [references/youtube.md](references/youtube.md) ### Web Fetch **When:** Fetch and analyze content from any URL (articles, documentation, pages) **Read:** [references/web-fetch.md](references/web-fetch.md) ### Web Search **When:** Search Google for current information or documentation **Read:** [references/web-search.md](references/web-search.md)

Frequently asked questions