nesdeq

serper

Data Analysisv3.0.2
By nesdeqUpdated 2026-05-113 versions · latest released 2026-01-31@clawhub_nesdeq/serper
Web Scraping

According to AlphaMoat, as of 2026-10, serper has 11,600 downloads and 9 stars — ranked by downloads #2,368 among 10,914 AI skills in this ranking, and #227 of 915 in Data Analysis.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
11.6K
Stars
9
Overall download rank
#2,368
Top 22% overall · Top 25% in Data Analysis
PlatformDownloadsStarsComments
ClawHub ↗5.6K7-
SkillHub ↗11.6K9—

Platforms count differently and update at different times.

What this skill does

It organizes agent knowledge using PARA: Projects, Areas, Resources and Archive. A symlink step expands semantic search beyond MEMORY.md to the wider knowledge base, and the guide also covers session transcripts and memory-flush practices. Follow the setup instructions for the relevant agent environment.

Profile published 2026-10-27

What you can do with it

  • Get result links and full page text from a single query
  • Gather article bodies from several sources for writing or fact-checking

When to use it

  • Search the web and read the returned pages
  • Gather full-page source text after a Serper query

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Use one query to find authoritative sources on this topic and pull the full text of each
I need the full text of these articles, so search first, scrape in parallel, then summarise by theme

Monthly Trend

Downloads11.6K
4.6K8.3K12.1K2026-03 · Downloads 5.1K2026-05 · Downloads 5.7K2026-06 · Downloads 5.9K2026-07 · Downloads 6.2K2026-08 · Downloads 6.4K2026-09 · Downloads 7.2K2026-10 · Downloads 11.6K26-0326-0926-10
Stars9
7892026-03 · Stars 72026-05 · Stars 82026-06 · Stars 82026-07 · Stars 92026-08 · Stars 92026-09 · Stars 92026-10 · Stars 926-0326-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

MonthDownloadsMoMStars
2026-1011.6K—9
2026-097.2K—9
2026-086.4K+2.9%9
2026-076.2K+4.6%9
2026-065.9K+3.4%8
2026-055.7K—8
2026-035.1K—7

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

6.4 KB · ClawHub v3.0.2
---
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.
Show all (162 lines)
### 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`) |

Popular in Data Analysis

全能金融爬虫Data Analysis

中国金融机构数据爬取与分析综合 Skill v12.0.0。2334家/43大类机构名单、60+财经媒体源舆情、 A股报告/公告/研报、60+种查询多源金融数据(自动降级+缓存)、爬取调度与网页操作增强、 实时数据中枢、24 技术指标引擎、多源证据融合、110 MCP 工具 + 10 Resource + 14 Prompt。 🆕 v12.0.0 四条线(信息获取 / 打包下载 / 数据分析 / 登录): 编排:gather_info() 一次跑完"路由→抓取→去占位→质量分→能力边界→回执→打包", 8 类意图各带问法、输入输出、典型耗时与 not_for(说清哪件事做不了)。 诚实:反爬占位条目一律剔除并记账,空结果报 E_SOURCE_EMPTY,不把假数据判成 B 级成功。 交付:包内自带 manifest.json(逐文件 sha256),verify 查得出改动/缺失/多塞, 批量下载单条失败不中断整批,失败清单可直接只重下那几条。 登录:Cookie 由用户导出或扫码接管,档案化 + 健康度四档,对外输出全脱敏(值永不回显)。 何时触发:爬取机构、舆情爬取、东方财富、公告下载、实时行情、技术指标、统一查询、 交付包、批量重下、我已经登录了、登录态还有效吗(完整触发词见下方 auto_trigger)。

↓ 770.1K★ 288user_9d5a2a39
钢联AI - 智能问数Data Analysis

大宗商品价格数据查询技能。用于查询大宗商品期现货价格、宏观经济指标、产业链供需数据、进出口库存数据、金融市场数据等。当用户询问:(1) 期货/现货价格查询,如"螺纹钢价格"、"铜期货收盘价"; (2) 历史行情或趋势分析;(3) 区域或企业价格对比;(4) 宏观经济指标,如GDP、CPI;(5) 产业链上下游数据;(6) 多市场金融数据(期权、股票、债券、外汇);(7) 结算确认单生成时触发此技能。

↓ 704.6K★ 6u_9ed3401d
smart-chartsData Analysis

将数据文件(CSV/TSV/TXT/XLSX/XLS/JSON)转化为独立交互式 ECharts HTML 图表——32 类图表、3 套主题,全离线无需 CDN。出图前可先取数据画像(--profile:每列 dtype/基数/缺失/样本/统计、实体粒度、候选洞察信号、疑似非数据行),让 agent 在用户没说想看什么时自己读懂数据并决定出什么图——哪列是 ID、哪列是维度、出什么图,全部由 agent 从画像的客观事实自行判断,技能不代笔;每张图内置事实卡(plot_stats + data_preview),其数值是解读时唯一可引用的数字。本技能负责出图与算事实,不产出书面报告或叙事文档。触发:用户提供或指向表格数据文件并要求出图;提到「画图/出图/可视化/生成图表/generate a chart/make a graph」;想把表格渲染成交互式 HTML 图表。不触发:要的是书面报告、叙事分析或幻灯片;没有数据文件;需要后端的仪表盘;图片/音频/视频等非表格内容。

↓ 604.6K★ 135user_5b28ea14
AdMapixData Analysis

The data layer for AdMapix: turn ad and app queries into API calls that return raw JSON only.

↓ 574.6K★ 304fly0pants
论文配图一键生成Data Analysis

论文配图一键生成:一条命令从 JSON/CSV/Excel 生成顶刊级学术图表,科研绘图 与期刊配图全场景覆盖。40 种图表(森林图/KM 生存曲线(自动风险表)/竞争风险累计发生率/ROC/校准 曲线/决策曲线 DCA/列线图/RCS 非线性剂量反应/亚组分析森林图/RMST 限制平均生存时间/Galbraith 径向图/火山图/雨云图/山脊图/哑铃图/游泳图(逐例时长+里程碑)/ 肿瘤缓解瀑布图/UpSet 交集/PRISMA 流程图/漏斗/BA 一致性/PCA/热图/箱线/小提琴/ 组合图/Cox 多因素回归森林图等),9 套配色(含色盲安全 Okabe-Ito 与期刊色板),9 种期刊投稿预设, YAML 流水线一条命令出全套论文图,一次渲染多格式导出(TIFF/PNG/PDF), PDF 重叠门禁,600dpi。纯本地运行,数据不出机,中文零配置。适用:写论文/ 投稿要配图、把数据变成可投稿图表、批量重出全套图。不适用:文本润色/翻译/ 改写(请用写作类工具);商业报表/仪表盘/海报装饰;无数据支撑的纯示意图。

↓ 421.5K★ 83user_481397b5
smart-chartsData Analysis

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.

↓ 257.5K★ 1user_814dbe54
股票/基金/期货量化分析工具Data Analysis

全球智能投研工具(stock-researcher)v13.0:多源数据 + 概率预测 + 可导出报告。 核心能力: - 多源数据路由:按市场/类别选源,逐级降级;每个结果标注来源与时效等级;源不可用时明确标 unavailable - 全资产量化:股票/ETF/场外基金/指数/期货(期限结构、基差、持仓、折溢价)多因子分析 - 概率预测:1d/5d/1M/3M/6M 经验分布 + 分位数 + 方向概率 + 区间,kNN 邻域收缩融合全局分布; 样本不足自动弃权,可按历史命中样本(同桶)做概率校准 - 证据链简报:每条结论绑定来源、时间与数据质量,冲突信号保留而不抹平 - 报告导出:Word/PPT/PDF/Markdown/JSON/纯文本,纯标准库渲染 + 可选第三方引擎 - MCP Server 24 工具,Claude Code 可直接调用;知识库 12 适配器双向同步 三条铁律: - 数据不装:拿不到就报不可用,不拿 0 价、不拿空表冒充 - 预测不装:概率来自历史相似条件的经验分布,样本不足就说不足,不硬给方向 - 评分≠盈利保证:任何结论都带免责声明

↓ 191.7K★ 147user_9d5a2a39
Tavily SearchData Analysis

Searches the public web through Tavily and returns structured results with links and snippets.

↓ 164.9K★ 286Xiaoran Li

More from nesdeq

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.