gemini-system
Gemini CLI leverages 1M context for three roles: codebase analysis, external research (Google Search grounding), and multimodal file reading. MUST use when PDF, video, audio, or image files need content extraction. Also use for large-scale codebase understanding and external research/survey. Planning/design → use Codex instead.
npx skills add majiayu000/claude-skill-registry --skill gemini-system-del-taiseiozaki-claude-code-orchestr --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Gemini System — Analysis, Research & Multimodal **Gemini CLI は 1M context を活用し、大規模分析・リサーチ・マルチモーダル読取を担当する。** > **詳細ルール**: `.claude/rules/gemini-delegation.md` ## Gemini の3つの役割 ### 1. コードベース・リポジトリ理解 Gemini の 1M context でプロジェクト全体を分析する（Claude の 200K では収まらない場合）。 ```bash # プロジェクト構造の分析 gemini -p "Analyze this codebase: directory structure, key modules, patterns, dependencies, and architecture" 2>/dev/null # 特定ファイルの詳細分析 gemini -p "Analyze this code: purpose, patterns, dependencies" < /path/to/file 2>/dev/null ``` ### 2. 外部リサーチ・サーベイ Gemini の Google Search grounding で最新情報を調査する。 ```bash # ライブラリ調査 gemini -p "Research: {library}. Latest version, features, constraints, best practices, pitfalls" 2>/dev/null # ベストプラクティス調査 gemini -p "Research best practices for {topic}. Latest recommendations, patterns, anti-patterns" 2>/dev/null # 技術比較 gemini -p "Compare {A} vs {B} for {use case}. Pros, cons, performance, community" 2>/dev/null ``` ### 3. マルチモーダルファイル読取 PDF、動画、音声、画像ファイルの内容を抽出する。 ```bash # PDF gemini -p "Extract: {what to extract}" < /path/to/file.pdf 2>/dev/null # Video gemini -p "Summarize: key concepts, timestamps" < /path/to/video.mp4 2>/dev/null # Audio gemini -p "Transcribe and summarize: de
- Gemini の3つの役割
- 1. コードベース・リポジトリ理解
- 2. 外部リサーチ・サーベイ
- 3. マルチモーダルファイル読取
- Auto-Trigger（自動発動）
- Gemini を使わないこと
- How to Use
- Subagent Pattern（出力が大きい場合）
- Direct Call（短い抽出の場合）
- Language Protocol
gemini -p "Analyze this codebase: directory structure, key modules, patterns, dependencies, and architecture" 2>/dev/null
gemini -p "Analyze this code: purpose, patterns, dependencies" < /path/to/file 2>/dev/null
gemini -p "Research: {library}. Latest version, features, constraints, best practices, pitfalls" 2>/dev/null
gemini -p "Research best practices for {topic}. Latest recommendations, patterns, anti-patterns" 2>/dev/null
gemini -p "Compare {A} vs {B} for {use case}. Pros, cons, performance, community" 2>/dev/null
PDF
gemini -p "Extract: {what to extract}" < /path/to/file.pdf 2>/dev/null
Video
gemini -p "Summarize: key concepts, timestamps" < /path/to/video.mp4 2>/dev/null
AudioWhat does the gemini-system skill do?
Gemini CLI leverages 1M context for three roles: codebase analysis, external research (Google Search grounding), and multimodal file reading. MUST use when PDF, video, audio, or image files need content extraction. Also use for large-scale codebase understanding and external research/survey. Planning/design → use Codex instead.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill gemini-system-del-taiseiozaki-claude-code-orchestr --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.