gemini-system
1
总安装量
1
周安装量
#50043
全站排名
安装命令
npx skills add https://github.com/del-taiseiozaki/claude-code-orchestra --skill gemini-system
Agent 安装分布
claude-code
1
Skill 文档
Gemini System â Research & Multimodal Specialist
Gemini CLI (gemini-3-pro-preview) is your research specialist with 1M token context.
詳細ã«ã¼ã«:
.claude/rules/gemini-delegation.md
Context Management (CRITICAL)
ãµãã¨ã¼ã¸ã§ã³ãçµç±ãæ¨å¥¨ã Geminiåºåã¯å¤§ãããªããã¡ãªããã
| ç¶æ³ | æ¹æ³ |
|---|---|
| ã³ã¼ããã¼ã¹åæ | ãµãã¨ã¼ã¸ã§ã³ãçµç±ï¼æ¨å¥¨ï¼ |
| ã©ã¤ãã©ãªèª¿æ» | ãµãã¨ã¼ã¸ã§ã³ãçµç±ï¼æ¨å¥¨ï¼ |
| ãã«ãã¢ã¼ãã« | ãµãã¨ã¼ã¸ã§ã³ãçµç±ï¼æ¨å¥¨ï¼ |
| çã質å (1-2æåç) | ç´æ¥å¼ã³åºãOK |
Gemini vs Codex
| Task | Gemini | Codex |
|---|---|---|
| ãªãã¸ããªå ¨ä½çè§£ | â | |
| ã©ã¤ãã©ãªèª¿æ» | â | |
| ãã«ãã¢ã¼ãã« (PDF/åç»/é³å£°) | â | |
| ææ°ããã¥ã¡ã³ãæ¤ç´¢ | â | |
| è¨è¨å¤æ | â | |
| ãããã° | â | |
| ã³ã¼ãå®è£ | â |
When to Consult (MUST)
| Situation | Trigger Examples |
|---|---|
| Research | ã調ã¹ã¦ãããªãµã¼ãã / “Research” “Investigate” |
| Library docs | ãã©ã¤ãã©ãªããããã¥ã¡ã³ãã / “Library” “Docs” |
| Codebase analysis | ãã³ã¼ããã¼ã¹å ¨ä½ã / “Entire codebase” |
| Multimodal | ãPDFããåç»ããé³å£°ã / “PDF” “Video” “Audio” |
When NOT to Consult
- Design decisions (use Codex)
- Debugging (use Codex)
- Code implementation (use Codex)
- Simple file operations (do directly)
How to Consult
Recommended: Subagent Pattern
Use Task tool with subagent_type='general-purpose' to preserve main context.
Task tool parameters:
- subagent_type: "general-purpose"
- run_in_background: true (optional, for parallel work)
- prompt: |
Research: {topic}
gemini -p "{research question}" 2>/dev/null
Save full output to: .claude/docs/research/{topic}.md
Return CONCISE summary (5-7 bullet points).
Direct Call (Short Questions Only)
For quick questions expecting brief answers:
gemini -p "Brief question" 2>/dev/null
CLI Options Reference
# Codebase analysis
gemini -p "{question}" --include-directories . 2>/dev/null
# Multimodal (PDF/video/audio)
gemini -p "{prompt}" < /path/to/file.pdf 2>/dev/null
# JSON output
gemini -p "{question}" --output-format json 2>/dev/null
Workflow (Subagent)
- Spawn subagent with Gemini research prompt
- Continue your work â Subagent runs in parallel
- Receive summary â Subagent returns key findings
- Full output saved â
.claude/docs/research/{topic}.md
Language Protocol
- Ask Gemini in English
- Receive response in English
- Synthesize and apply findings
- Report to user in Japanese
Output Location
Save Gemini research results to:
.claude/docs/research/{topic}.md
This allows Claude and Codex to reference the research later.
Task Templates
Pre-Implementation Research
gemini -p "Research best practices for {feature} in Python 2025.
Include:
- Common patterns and anti-patterns
- Library recommendations (with comparison)
- Performance considerations
- Security concerns
- Code examples" 2>/dev/null
Repository Analysis
gemini -p "Analyze this repository:
1. Architecture overview
2. Key modules and responsibilities
3. Data flow between components
4. Entry points and extension points
5. Existing patterns to follow" --include-directories . 2>/dev/null
Library Research
See: references/lib-research-task.md
Multimodal Analysis
# Video
gemini -p "Analyze video: main concepts, key points, timestamps" < tutorial.mp4 2>/dev/null
# PDF
gemini -p "Extract: API specs, examples, constraints" < api-docs.pdf 2>/dev/null
# Audio
gemini -p "Transcribe and summarize: decisions, action items" < meeting.mp3 2>/dev/null
Integration with Codex
| Workflow | Steps |
|---|---|
| New feature | Gemini research â Codex design review |
| Library choice | Gemini comparison â Codex decision |
| Bug investigation | Gemini codebase search â Codex debug |
Why Gemini?
- 1M token context: Entire repositories at once
- Google Search: Latest information and docs
- Multimodal: Native PDF/video/audio processing
- Fast exploration: Quick overview before deep work
- Shared context: Results saved for Claude/Codex