Agent Skills › rcarmo/piclaw › web-search

web-search

GitHub

提供网页搜索及页面内容抓取功能，支持SearXNG和DuckDuckGo，可将搜索结果或网页转换为Markdown格式。

skel/.pi/skills/web-search/SKILL.md rcarmo/piclaw

Trigger Scenarios

需要获取最新网络信息需要检索特定主题的网页内容

Install

npx skills add rcarmo/piclaw --skill web-search -g -y

More Options

Non-standard path

npx skills add https://github.com/rcarmo/piclaw/tree/main/skel/.pi/skills/web-search -g -y

Use without installing

npx skills use rcarmo/piclaw@web-search

指定 Agent (Claude Code)

npx skills add rcarmo/piclaw --skill web-search -a claude-code -g -y

安装 repo 全部 skill

npx skills add rcarmo/piclaw --all -g -y

预览 repo 内 skill

npx skills add rcarmo/piclaw --list

SKILL.md

Frontmatter

{
    "name": "web-search",
    "description": "Search the web via SearXNG (or DuckDuckGo fallback) and optionally fetch result pages as raw Markdown content.",
    "distribution": "public"
}

Web Search

Use this when you need search results and fetched page content.

If you only need short summaries, use web-search-summary.

Search engine selection

If PICLAW_SEARX_URL is set or --searx-url is passed, the script uses SearXNG.
Otherwise, it falls back to DuckDuckGo HTML search (no API key required).

Examples

Search only:

bun /workspace/.pi/skills/web-search/web-search.ts --query "your query"

Fetch top results and convert them to Markdown:

bun /workspace/.pi/skills/web-search/web-search.ts --query "your query" --fetch true --fetch-limit 2

Output shape

The script prints JSON like:

{
  "query": "...",
  "searxUrl": "http://.../search",
  "limit": 5,
  "fetch": true,
  "results": [
    {
      "title": "...",
      "url": "https://...",
      "content": "snippet or fetched markdown"
    }
  ]
}

Without --fetch, results[].content is the search-result snippet when available.
With --fetch, fetched items replace content with converted Markdown.

Failure behaviour

If the search request fails, the script exits non-zero.
If page fetch fails for an individual result, the search still succeeds and that item gets content: "Failed to fetch: ...".

Options

--query / --q — required search query
--limit — number of search results to return (default 5)
--fetch — fetch and convert result pages (true / 1)
--fetch-limit — how many results to fetch and convert (default 2)
--searx-url — override the SearXNG endpoint (env: PICLAW_SEARX_URL; falls back to DuckDuckGo if unset)
--timeout — fetch timeout in milliseconds (default 15000)