メニュー
Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/s1366560/agi-demos --skill researchコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Sandbox MCP Server 是一个隔离的代码执行环境，提供完整的文件系统操作、命令执行、 代码分析、测试运行和远程桌面能力。当你需要执行代码、操作文件、运行测试、 分析代码结构、或需要图形界面操作时使用此技能。支持 Python、Node.js、Java 等多语言环境。
Evidence-led triage and scoped recovery for local MemStack development runtime incidents. Use when FastAPI, React/Vite Web, Ray, the agent actor, Docker infrastructure, Redis, Postgres, Neo4j, the sandbox, or the Electron desktop sidecar fails to start, crashes, consumes abnormal resources, or becomes unresponsive.
Deliver and verify MemStack native desktop changes in agi-demos against the design-prototype or Web product surface while preserving the Electron shell, Rust sidecar, IPC, encrypted-vault, signing, and updater boundaries. Use for implementation, parity repair, or QA work scoped to agi-stack/apps/desktop; do not use for generic Web QA, mobile work, or unrelated desktop applications.
SKILL.md を表示中
SOC 職業分類に基づく
| name | research |
| description | Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports. |
Conduct comprehensive research on any topic with automatic source gathering, analysis, and response generation with citations.
The script uses OAuth via the Tavily MCP server. No manual setup required - on first run, it will:
~/.mcp-auth/Note: You must have an existing Tavily account. The OAuth flow only supports login — account creation is not available through this flow. Sign up at tavily.com first if you don't have an account.
If you prefer using an API key, get one at https://tavily.com and add to ~/.claude/settings.json:
{
"env": {
"TAVILY_API_KEY": "tvly-your-api-key-here"
}
}
Tip: Research can take 30-120 seconds. Press Ctrl+B to run in the background.
./scripts/research.sh '<json>' [output_file]
Examples:
# Basic research
./scripts/research.sh '{"input": "quantum computing trends"}'
# With pro model for comprehensive analysis
./scripts/research.sh '{"input": "AI agents comparison", "model": "pro"}'
# Save to file
./scripts/research.sh '{"input": "market analysis for EVs", "model": "pro"}' ./ev-report.md
# Quick targeted research
./scripts/research.sh '{"input": "climate change impacts", "model": "mini"}'
| Field | Type | Default | Description |
|---|---|---|---|
input | string | Required | Research topic or question |
model | string | "mini" | Model: mini, pro, auto |
Rule of thumb: "what does X do?" -> mini. "X vs Y vs Z" or "best way to..." -> pro.
| Model | Use Case | Speed |
|---|---|---|
mini | Single topic, targeted research | ~30s |
pro | Comprehensive multi-angle analysis | ~60-120s |
auto | API chooses based on complexity | Varies |
./scripts/research.sh '{"input": "What is retrieval augmented generation?", "model": "mini"}'
./scripts/research.sh '{"input": "LangGraph vs CrewAI for multi-agent systems", "model": "pro"}'
./scripts/research.sh '{"input": "Fintech startup landscape 2025", "model": "pro"}' fintech-report.md