スキル一覧に戻る
ainergiz

gemini

by ainergiz

New Mac setup documentation and scripts for job onboarding

0🍴 0📅 2026年1月7日
GitHubで見るManusで実行

SKILL.md


name: gemini description: Use Google Gemini for AI chat, research, image/video creation, and analysis. Use when user wants to use Gemini, ask complex questions, generate images or videos, do deep research, or use Gemini's thinking capabilities. allowed-tools: mcp__claude-in-chrome__*

Google Gemini

Browser automation for Google Gemini AI assistant at gemini.google.com.

Models

Access via model dropdown (bottom-right of input area):

ModelDescriptionBest For
FastQuick responsesSimple questions, fast interactions
ThinkingExtended reasoningComplex problem solving
ProAdvanced capabilitiesMath, code, detailed analysis

Tools

Access via sliders icon (left of model selector):

ToolDescription
Deep ResearchIn-depth research with sources
Deep ThinkExtended reasoning (shows thinking process)
Create videosVideo generation with Veo 3.1
Create imagesAI image generation
CanvasCollaborative document editing
Guided LearningEducational/tutorial mode

Enabling a Tool

  1. Click sliders icon next to input field
  2. Click tool name to enable (checkmark appears)
  3. Tool appears as pill in input area
  4. Click X on pill to disable

Deep Think

  • Takes several minutes for complex queries
  • Shows "Show thinking" toggle to reveal reasoning
  • Best for thorough analysis and research
  • Copy button at bottom of response

Deep Research

  • Generates comprehensive reports with citations
  • Returns multiple sources
  • Good for fact-checking and exploration

Input Options

Access via "+" button (left of input area):

OptionDescription
Upload filesAttach local files
Add from DriveImport Google Drive files
PhotosAccess photo library
Import codeAdd code snippets
NotebookLMDirect NotebookLM integration

Gems (Custom Assistants)

Access via "Gems" in sidebar:

  • Pre-made Gems: Google-created specialized assistants
  • My Gems: Create custom personas with specific instructions
  • Click "+ New Gem" to create custom assistant

Response Features

FeatureLocationDescription
CopyBottom of responseCopy full response text
Export to SheetsIn tablesExport data to Google Sheets
SourcesBelow responseView cited sources
Like/DislikeBottom of responseFeedback buttons
ShareResponse menuShare conversation

Sidebar:

  • New chat
  • My stuff (recent items)
  • Gems
  • Chat history
  • Activity
  • Settings and help

Retrieving Previous Chats:

  1. Click chat in sidebar under "Chats"
  2. Or use search icon (top-left)

Copying Responses

Best Practice: Use native "Copy response" button (two overlapping rectangles icon at bottom of response).

Avoid JavaScript clipboard API - can be overwritten by other processes. Paste immediately after copying.

Workflow Examples

Deep Think Research

1. Navigate to gemini.google.com
2. Click sliders icon → enable "Deep Think"
3. Select "Pro" model for best results
4. Enter research query
5. Wait for completion (may take minutes)
6. Click "Copy response" button

Image Generation

1. Navigate to gemini.google.com
2. Click sliders icon → enable "Create images"
3. Describe desired image in detail
4. Review generated options
5. Click to download or regenerate

Export to NotebookLM

1. Complete research in Gemini
2. Copy response using native button
3. Open NotebookLM (see notebooklm skill)
4. Create notebook → Copied text → Paste

Tips

  • Deep Think + Pro model = most thorough analysis
  • Use Deep Research for fact-based queries needing citations
  • Gems are useful for repeated specialized tasks
  • Chat history preserves all conversations
  • Export tables to Sheets for further analysis

スコア

総合スコア

40/100

リポジトリの品質指標に基づく評価

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

0/10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

レビュー

💬

レビュー機能は近日公開予定です