MCP HubMCP Hub
スキル一覧に戻る

research

danielmiessler
更新日 Today
39 閲覧
14
1
14
GitHubで表示
その他ai

について

このスキルは、最大10台の並列エージェント(Perplexity、Claude、Gemini)を起動して情報を迅速に収集・統合する、マルチソースリサーチを実行します。「Xについて調査して」「~に関する情報を探して」「トレンドを分析して」など、あらゆる調査関連のリクエストにご利用いただけます。質問をサブタスクに分解し、15~30秒で包括的な結果をお届けします。

クイックインストール

Claude Code

推奨
プラグインコマンド推奨
/plugin add https://github.com/danielmiessler/PAIPlugin
Git クローン代替
git clone https://github.com/danielmiessler/PAIPlugin.git ~/.claude/skills/research

このコマンドをClaude Codeにコピー&ペーストしてスキルをインストールします

ドキュメント

Research Skill

When to Use This Skill

This skill activates when the user requests research or information gathering:

  • "Do research on X"
  • "Research this topic"
  • "Find information about X"
  • "Investigate this subject"
  • "Analyze trends in X"
  • "Current events research"
  • Any comprehensive information gathering request

How to Execute

Execute the /conduct-research slash command, which handles the complete workflow:

  1. Decomposing research questions into 3-10 sub-questions
  2. Launching up to 10 parallel research agents (perplexity, claude, gemini)
  3. Collecting results in 15-30 seconds
  4. Synthesizing findings with confidence levels
  5. Formatting comprehensive report with source attribution

Available Research Agents

  • All agents with "researcher" in their name in the agents directory.

Speed Benefits

  • Old approach: Sequential searches → 5-10 minutes
  • New approach: 10 parallel agents → Under 1 minute

Full Workflow Reference

For complete step-by-step instructions: read ${PAI_DIR}/commands/conduct-research.md

GitHub リポジトリ

danielmiessler/PAIPlugin
パス: skills/research

関連スキル

evaluating-llms-harness

テスト

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

スキルを見る

sglang

メタ

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

スキルを見る

cloudflare-turnstile

メタ

This skill provides comprehensive guidance for implementing Cloudflare Turnstile as a CAPTCHA-alternative bot protection system. It covers integration for forms, login pages, API endpoints, and frameworks like React/Next.js/Hono, while handling invisible challenges that maintain user experience. Use it when migrating from reCAPTCHA, debugging error codes, or implementing token validation and E2E tests.

スキルを見る

langchain

メタ

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

スキルを見る