據 AlphaMoat 統計,截至 2026-10,serper 累計下載 11,600 次、獲 9 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 2,368 位,在「資料分析」分類(915 個)中排名第 227 位。
列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。
| 平台 | 累計下載 | 星標 | 評論 |
|---|---|---|---|
| ClawHub ↗ | 5561 | 7 | - |
| SkillHub ↗ | 1.2萬 | 9 | — |
各平台的計數口徑不同,統計時間不一致。
用 PARA(Projects、Areas、Resources、Archive)整理 Agent 知識。依指南設定 symlink 後,可將語義檢索範圍從 MEMORY.md 擴展到整個知識庫;文件也涵蓋工作階段記錄和 memory flush 做法。請依對應 Agent 環境完成設定。
資料釋出於 2026-10-27
以下是根據技能文件生成的示例,不代表實際執行結果。
2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。
| 月份 | 累計下載 | 環比 | 星標 |
|---|---|---|---|
| 2026-10 | 1.2萬 | — | 9 |
| 2026-09 | 7151 | — | 9 |
| 2026-08 | 6362 | +2.9% | 9 |
| 2026-07 | 6180 | +4.6% | 9 |
| 2026-06 | 5906 | +3.4% | 8 |
| 2026-05 | 5714 | — | 8 |
| 2026-03 | 5075 | — | 7 |
以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。
---
name: serper
description: Google search via Serper API with full page content extraction. Fast API lookup + concurrent page scraping (3s timeout). One well-crafted query returns rich results — avoid multiple calls. Two modes, explicit locale control. API key via .env.
metadata: {"version": "3.0.1", "tags": ["search", "web-search", "serper", "google", "content-extraction"]}
---
# Serper
Google search via Serper API. Fetches results AND reads the actual web pages to extract clean full-text content via trafilatura. Not just snippets — full article text.
### How It Works
1. **Serper API call** — fast Google search, returns result URLs instantly
2. **Concurrent page scraping** — all result pages are fetched and extracted in parallel using trafilatura with a **3-second timeout per page**
3. **Streamed output** — results print one at a time as each page finishes
Each invocation gives you 5 results (default mode) or up to 6 results (current mode), each with full page content. This is already a lot of information.
---
## Query Discipline
**Craft ONE good search query. That is almost always enough.**
Each call returns multiple results with full page text — you get broad coverage from a single query. Do not run multiple searches to "explore" a topic. One well-chosen query with the right mode covers it.
**At most two calls** if the user's request genuinely spans two distinct topics (e.g. "compare X vs Y" where X and Y need separate searches, or one `default` + one `current` call for different aspects). Never more than two.
**Do NOT:**
- Run the same query with different wording to "get more results"
- Run sequential searches to "dig deeper" — the full page content is already deep
- Run one search to find something, then another to follow up — read the content you already have
---
## When to Use This Skill
**Use serper when:**
- Any question that needs current, factual information from the web
- Research topics that need full article content, not just snippets
- News and current events
- Product info, prices, comparisons, reviews
- Technical docs, how-to guides
- Anything where reading the actual page matters
**Do NOT use this skill for:**
- Questions you can answer from your training data
- Pure math, code execution, creative writing
- Greetings, chitchat
**IMPORTANT: This skill already fetches and extracts full page content. Do NOT use web_fetch, WebFetch, or any other URL-fetching tool on the URLs returned by this skill. The content is already included in the output.**
---
## Two Search Modes
There are exactly two modes. Pick the right one based on the query:
### `default` — General search (all-time)
- All-time Google web search, **5 results**, each enriched with full page content
- Use for: general questions, research, how-to, evergreen topics, product info, technical docs, comparisons, tutorials, anything NOT time-sensitive
### `current` — News and recent info
- Past-week Google web search (3 results) + Google News (3 results), each enriched with full page content
- Use for: news, current events, recent developments, breaking news, announcements, anything time-sensitive
#### Mode Selection Guide
| Query signals | Mode |
|---------------|------|
| "how does X work", "what is X", "explain X" | `default` |
| Product research, comparisons, tutorials | `default` |
| Technical documentation, guides | `default` |
| Historical topics, evergreen content | `default` |
| "news", "latest", "today", "this week", "recent" | `current` |
| "what happened", "breaking", "announced", "released" | `current` |
| Current events, politics, sports scores, stock prices | `current` |
---
## Locale (REQUIRED for non-English queries)
**Default is global** — no country filter, English results. This ONLY works for English queries.
**You MUST ALWAYS set `--gl` and `--hl` when ANY of these are true:**
- The user's message is in a non-English language
- The search query you construct is in a non-English language
- The user mentions a specific country, city, or region
- The user asks for local results (prices, news, stores, etc.) in a non-English context
**If the user writes in German, you MUST pass `--gl de --hl de`. No exceptions.**
| Scenario | Flags |
|----------|-------|
| English query, no country target | *(omit --gl and --hl)* |
| German query OR user writes in German OR targeting DE/AT/CH | `--gl de --hl de` |
| French query OR user writes in French OR targeting France | `--gl fr --hl fr` |
| Any other non-English language/country | `--gl XX --hl XX` (ISO codes) |
**Rule of thumb:** If the query string contains non-English words, set `--gl` and `--hl` to match that language.
---
## How to Invoke
```bash
python3 scripts/search.py -q "QUERY" [--mode MODE] [--gl COUNTRY] [--hl LANG]
```
### Examples
```bash
# English, general research
python3 scripts/search.py -q "how does HTTPS work"
# English, time-sensitive
python3 scripts/search.py -q "OpenAI latest announcements" --mode current
# German query — set locale + current mode for news/prices
python3 scripts/search.py -q "aktuelle Preise iPhone" --mode current --gl de --hl de
# German news
python3 scripts/search.py -q "Nachrichten aus Berlin" --mode current --gl de --hl de
# French product research
python3 scripts/search.py -q "meilleur smartphone 2026" --gl fr --hl fr
```
---
## Output Format
The output is a **streamed JSON array** — elements print one at a time as each page is scraped:
```json
[{"query": "...", "mode": "default", "locale": {"gl": "world", "hl": "en"}, "results": [{"title": "...", "url": "...", "source": "web"}, ...]}
,{"title": "...", "url": "...", "source": "web", "content": "Full extracted page text..."}
,{"title": "...", "url": "...", "source": "news", "date": "2 hours ago", "content": "Full article text..."}
]
```
The first element is search metadata. Each following element contains a result with full extracted content.
Result fields:
- `title` — page title
- `url` — source URL
- `source` — `"web"`, `"news"`, or `"knowledge_graph"`
- `content` — full extracted page text (falls back to search snippet if extraction fails)
- `date` — present when available (news results always, web results sometimes)
---
## CLI Reference
| Flag | Description |
|------|-------------|
| `-q, --query` | Search query (required) |
| `-m, --mode` | `default` (all-time, 5 results) or `current` (past week + news, 3 each) |
| `--gl` | Country code (e.g. `de`, `us`, `fr`, `at`, `ch`) |
| `--hl` | Language code (e.g. `en`, `de`, `fr`) |
中國金融機構資料爬取與分析綜合 Skill v12.0.0。2334家/43大類機構名單、60+財經媒體源輿情、 A股報告/公告/研報、60+種查詢多源金融資料(自動降級+快取)、爬取排程與網頁操作增強、 即時資料中樞、24 技術指標引擎、多源證據融合、110 MCP 工具 + 10 Resource + 14 Prompt。 🆕 v12.0.0 四條線(資訊獲取 / 打包下載 / 資料分析 / 登入): 編排:gather_info() 一次跑完"路由→抓取→去佔位→質量分→能力邊界→回執→打包", 8 類意圖各帶問法、輸入輸出、典型耗時與 not_for(說清哪件事做不了)。 誠實:反爬佔位條目一律剔除並記賬,空結果報 E_SOURCE_EMPTY,不把假資料判成 B 級成功。 交付:包內自帶 manifest.json(逐檔案 sha256),verify 查得出改動/缺失/多塞, 批次下載單條失敗不中斷整批,失敗清單可直接只重下那幾條。 登入:Cookie 由使用者匯出或掃碼接管,檔案化 + 健康度四檔,對外輸出全脫敏(值永不回顯)。 何時觸發:爬取機構、輿情爬取、東方財富、公告下載、即時行情、技術指標、統一查詢、 交付包、批次重下、我已經登入了、登入態還有效嗎(完整觸發詞見下方 auto_trigger)。
大宗商品價格資料查詢技能。用於查詢大宗商品期現貨價格、宏觀經濟指標、產業鏈供需資料、進出口庫存資料、金融市場資料等。當用戶詢問:(1) 期貨/現貨價格查詢,如"螺紋鋼價格"、"銅期貨收盤價"; (2) 歷史行情或趨勢分析;(3) 區域或企業價格對比;(4) 宏觀經濟指標,如GDP、CPI;(5) 產業鏈上下游資料;(6) 多市場金融資料(期權、股票、債券、外匯);(7) 結算確認單生成時觸發此技能。
32種圖表,3 個主題,2步生成: 1.上傳資料 — 將 CSV / Excel / JSON 等格式的資料檔案拖入對話方塊; 2.檢視結果 — 互動式圖表(HTML),可儲存圖表為圖片.
AdMapix 的取數層:把廣告與應用相關的查詢轉成介面呼叫,只回原始 JSON。
論文配圖一鍵生成:一條命令從 JSON/CSV/Excel 生成頂刊級學術圖表,科研繪圖 與期刊配圖全場景覆蓋。40 種圖表(森林圖/KM 生存曲線(自動風險表)/競爭風險累計發生率/ROC/校準 曲線/決策曲線 DCA/列線圖/RCS 非線性劑量反應/亞組分析森林圖/RMST 限制平均生存時間/Galbraith 徑向圖/火山圖/雨雲圖/山脊圖/啞鈴圖/游泳圖(逐例時長+里程碑)/ 腫瘤緩解瀑布圖/UpSet 交集/PRISMA 流程圖/漏斗/BA 一致性/PCA/熱圖/箱線/小提琴/ 組合圖/Cox 多因素迴歸森林圖等),9 套配色(含色盲安全 Okabe-Ito 與期刊色板),9 種期刊投稿預設, YAML 流水線一條命令出全套論文圖,一次渲染多格式匯出(TIFF/PNG/PDF), PDF 重疊門禁,600dpi。純本地執行,資料不出機,中文零配置。適用:寫論文/ 投稿要配圖、把資料變成可投稿圖表、批次重出全套圖。不適用:文字潤色/翻譯/ 改寫(請用寫作類工具);商業報表/儀表盤/海報裝飾;無資料支撐的純示意圖。
Intelligent chart generation and data analysis skill. Reads user-supplied data files (CSV/Excel/JSON), analyzes data characteristics with LLM assistance, auto-recommends and generates interactive ECharts visualizations. Use when the user asks to analyze data, generate charts, create visualizations, or work with tabular data files.
全球智慧投研工具(stock-researcher)v13.0:多源資料 + 機率預測 + 可匯出報告。 核心能力: - 多源資料路由:按市場/類別選源,逐級降級;每個結果標註來源與時效等級;源不可用時明確標 unavailable - 全資產量化:股票/ETF/場外基金/指數/期貨(期限結構、基差、持倉、折溢價)多因子分析 - 機率預測:1d/5d/1M/3M/6M 經驗分佈 + 分位數 + 方向機率 + 區間,kNN 鄰域收縮融合全域性分佈; 樣本不足自動棄權,可按歷史命中樣本(同桶)做機率校準 - 證據鏈簡報:每條結論繫結來源、時間與資料質量,衝突訊號保留而不抹平 - 報告匯出:Word/PPT/PDF/Markdown/JSON/純文字,純標準庫渲染 + 可選第三方引擎 - MCP Server 24 工具,Claude Code 可直接呼叫;知識庫 12 介面卡雙向同步 三條鐵律: - 資料不裝:拿不到就報不可用,不拿 0 價、不拿空表冒充 - 預測不裝:機率來自歷史相似條件的經驗分佈,樣本不足就說不足,不硬給方向 - 評分≠盈利保證:任何結論都帶免責宣告
透過 Tavily 搜尋公開網頁,並回傳含連結與摘要的結構化結果。
資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。