rey-web-search

Quick web search for information. Returns top results with summaries. Use when user says "search", "look up", "find info about".

16 stars

Best use case

rey-web-search is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Quick web search for information. Returns top results with summaries. Use when user says "search", "look up", "find info about".

Teams using rey-web-search should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/rey-web-search/SKILL.md --create-dirs "https://raw.githubusercontent.com/diegosouzapw/awesome-omni-skill/main/skills/fullstack-web/rey-web-search/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/rey-web-search/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How rey-web-search Compares

Feature / Agentrey-web-searchStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Quick web search for information. Returns top results with summaries. Use when user says "search", "look up", "find info about".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Web Search - ウェブ検索スキル

素早く情報を検索して結果を返す。

## いつ使う?

```
トリガー:
├── 「〜を検索して」
├── 「〜について調べて」
├── 「〜って何?」
├── 「最新の〜は?」
└── 「〜のニュース」
```

---

## 検索フロー

```
ユーザー: 「Claude 4.5の最新情報を検索して」

MoltBot:
1. 検索クエリを最適化
2. 複数ソースから検索
3. 結果をランキング
4. サマリーを生成

返答:
「Claude 4.5について検索しました:

📌 主な情報:
- 2025年10月リリース
- コンテキストウィンドウ200K
- 推論能力が大幅向上

📎 ソース:
1. Anthropic公式ブログ
2. Tech Crunch記事
3. X(Twitter)での反応

詳しく知りたい点はありますか?」
```

---

## 検索の種類

### 1. 即時検索(デフォルト)
```
用途: 簡単な事実確認
時間: 数秒
深さ: 上位3-5件
```

### 2. ニュース検索
```
用途: 最新ニュース
時間: 数秒
ソース: ニュースサイト優先
```

### 3. 技術検索
```
用途: プログラミング、API
時間: 数秒
ソース: Stack Overflow、GitHub、公式ドキュメント
```

---

## 検索結果フォーマット

```
📌 [トピック]について

🔍 検索結果:
1. [タイトル1]
   [要約 - 2-3文]
   出典: [URL]

2. [タイトル2]
   [要約 - 2-3文]
   出典: [URL]

3. [タイトル3]
   [要約 - 2-3文]
   出典: [URL]

💡 まとめ:
[全体の要約 - 2-3文]
```

---

## deep-research との違い

| 項目 | web-search | deep-research |
|------|------------|---------------|
| **速度** | 数秒 | 数分〜数十分 |
| **深さ** | 上位3-5件 | 10-20件以上 |
| **分析** | 簡易サマリー | 詳細分析 |
| **用途** | 事実確認 | 調査・研究 |
| **出力** | テキスト | レポート形式 |

---

## 検索最適化

### クエリ改善
```
ユーザー入力: 「AIについて」
最適化後: 「AI 人工知能 2026 最新動向」

ユーザー入力: 「Python エラー」
最適化後: 「Python [エラーメッセージ] 解決方法」
```

### ソース優先度
```
技術系:
1. 公式ドキュメント
2. Stack Overflow
3. GitHub Issues
4. 技術ブログ

ニュース系:
1. 大手メディア
2. 専門メディア
3. 公式発表
4. SNS
```

---

## セキュリティ

### 安全な検索
```
チェック:
├── 不審なURLを除外
├── 悪意あるサイトをブロック
├── ファイルダウンロードは確認
└── 個人情報を含む検索に注意
```

### human-security 連携
```
検索結果に含まれる場合:
├── フィッシングサイト → 警告
├── マルウェア配布サイト → 除外
├── 詐欺的なコンテンツ → 注意喚起
└── 信頼性の低いソース → マーク
```

---

## 使用例

### 簡単な検索
```
ユーザー: 「今日の天気を検索して」
MoltBot: 「東京の今日の天気: 晴れ、最高気温18度です。」
```

### 技術的な検索
```
ユーザー: 「React useEffect の使い方を検索して」
MoltBot: 「useEffectの基本的な使い方:
1. コンポーネントマウント時に実行
2. 依存配列で再実行タイミング制御
3. クリーンアップ関数で後処理
[サンプルコード]」
```

### ニュース検索
```
ユーザー: 「最新のAIニュースを検索して」
MoltBot: 「今週のAIニュース:
1. OpenAI GPT-5発表
2. Google Gemini 3.0アップデート
3. AI規制法案の動向」
```

---

## 連携スキル

| スキル | 連携内容 |
|--------|----------|
| deep-research | 深堀り調査 |
| trend-analyzer | トレンド分析 |
| content-ideas | コンテンツネタ |
| fact-checker | ファクトチェック |

Related Skills

amazon-product-search-recommender

16
from diegosouzapw/awesome-omni-skill

When the user wants to search for specific products on Amazon within budget constraints and generate structured recommendations. This skill navigates to Amazon.com, performs targeted searches using specific criteria (price range, material, color), browses search results, extracts product details (title, price, store/brand, URL), and compiles recommendations into a structured JSON format. Triggers include requests for product recommendations, shopping assistance, budget-constrained searches, or when users need to find specific items on Amazon with detailed specifications.

advanced-text-search-matching

16
from diegosouzapw/awesome-omni-skill

Production-grade text search algorithms for finding and matching text in large documents with millisecond performance. Includes Boyer-Moore search, n-gram similarity, fuzzy matching, and intelligent indexing. Use when building search features for large documents, finding quotes with imperfect matches, implementing fuzzy search, or need character-level precision.

jekyll-research-theme

16
from diegosouzapw/awesome-omni-skill

Create production-grade, accessible Jekyll themes for researchers conducting "research in public." Generates complete lab notebook-style themes with Tufte-inspired sidenotes, KaTeX math rendering, and WCAG 2.1 AA compliance. Use when building Jekyll themes for scientific journals, experiment logs, field notes, or research documentation sites. Supports collections for organizing experiments and field notes, responsive sidenote rendering (sidebar on desktop, inline on mobile), and full-width layout options.

hig-components-search

16
from diegosouzapw/awesome-omni-skill

Apple HIG guidance for navigation-related components including search fields, page controls, and path controls.

ai-search-technical-auditor

16
from diegosouzapw/awesome-omni-skill

Audit front-end code for AI search readiness. Use when reviewing HTML structure, meta tags, schema markup, and technical elements that affect how AI crawlers understand and index web pages.

research-documentation

16
from diegosouzapw/awesome-omni-skill

Searches across your Notion workspace, synthesizes findings from multiple pages, and creates comprehensive research documentation saved as new Notion pages. Trigger on "노션 검색", "조사해줘", "리서치 정리". For meeting prep use meeting-intelligence; for saving knowledge use knowledge-capture; for spec breakdown use spec-to-implementation.

documentation-research

16
from diegosouzapw/awesome-omni-skill

Enforces documentation research before implementation. Auto-loads when implementing features to ensure current best practices are followed. Researches official docs first.

CitedResearch

16
from diegosouzapw/awesome-omni-skill

Research output with proper source citations. USE WHEN conducting research, creating sector analyses, or generating investment notes that need verifiable sources.

azure-search-documents-py

16
from diegosouzapw/awesome-omni-skill

Azure AI Search SDK for Python. Use for vector search, hybrid search, semantic ranking, indexing, and skillsets.

azure-search-documents-dotnet

16
from diegosouzapw/awesome-omni-skill

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search.

azure-maps-search-dotnet

16
from diegosouzapw/awesome-omni-skill

Azure Maps SDK for .NET. Location-based services including geocoding, routing, rendering, geolocation, and weather. Use for address search, directions, map tiles, IP geolocation, and weather data.

arxiv-research

16
from diegosouzapw/awesome-omni-skill

Download and analyze academic papers from arXiv. Use when users want to download a specific paper by ID (e.g., "download paper arxiv:1234.5678") or read/analyze papers they've already downloaded.