← スキル一覧に戻る

deal-hunt
by tavily-ai
Official Tavily plugin for Claude Code
⭐ 2🍴 0📅 2026年1月22日
SKILL.md
name: deal-hunt description: "Find the best current deals/coupons for a specific product. Searches web for deals and returns raw results for analysis."
Deal Hunt
Search for deals on any product. Returns raw Tavily search results - Claude analyzes them to find the best prices.
Prerequisites
Tavily API Key Required - Get your key at https://tavily.com
Add to ~/.claude/settings.json:
{
"env": {
"TAVILY_API_KEY": "tvly-your-api-key-here"
}
}
Usage
# Search entire web (default - no domain filter)
python scripts/deal_hunt.py "Dyson V15"
# Multi-query search (max 3, runs in parallel, deduplicates results)
python scripts/deal_hunt.py "AirPods Pro" --queries "AirPods Pro deal,AirPods Pro coupon,AirPods Pro discount"
# Limit to specific sites
python scripts/deal_hunt.py "MacBook Air" --domains amazon.com,walmart.com,bestbuy.com
# Custom single query
python scripts/deal_hunt.py "Nintendo Switch" --query "Nintendo Switch OLED bundle deal"
# Fresh deals only
python scripts/deal_hunt.py "PS5" --time-range day
CLI Parameters
| Option | Short | Default | Description |
|---|---|---|---|
product | - | Required | Product name |
--query | -q | {product} deal price | Single custom search query |
--queries | None | Comma-separated queries (max 3), runs in parallel with dedup | |
--domains | -d | None (search all) | Optionally limit to specific domains |
--max-results | -n | 10 | Number of results per query |
--time-range | -t | week | day, week, month, year, none |
--search-depth | -s | advanced | basic, advanced, fast, ultrafast |
Output
Returns JSON with results:
{
"meta": {
"product": "AirPods Pro",
"queries": ["AirPods Pro deal", "AirPods Pro coupon"],
"domains": null,
"time_range": "week",
"search_time": "2026-01-13T...",
"total_results": 15
},
"results": [
{
"title": "...",
"url": "https://...",
"content": "...",
"score": 0.95
}
]
}
When using --queries, results are deduplicated by URL (highest score kept, content merged).
Output Schema for Analysis
After running the search, Claude should analyze results and structure findings as:
{
"product": "Sony WH-1000XM5",
"best_deal": {
"price": 279.99,
"original_price": 399.99,
"discount": "30% off",
"retailer": "Amazon",
"url": "https://amazon.com/...",
"condition": "new",
"in_stock": true
},
"all_deals": [
{
"price": 279.99,
"retailer": "Amazon",
"url": "https://...",
"notes": "Prime shipping"
},
{
"price": 169.99,
"retailer": "eBay via Slickdeals",
"url": "https://...",
"notes": "Refurbished"
}
],
"coupons": [
{
"code": "AUDIO10",
"discount": "10% off",
"retailer": "Best Buy",
"expires": "2026-01-31"
}
],
"summary": "Best new price is $279.99 at Amazon (30% off). Refurbished available for $169.99."
}
Claude extracts prices from content, compares deals, and presents the best options with purchase links.
スコア
総合スコア
60/100
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
+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