| name | web-search-summary |
| description | Search via SearXNG (or DuckDuckGo fallback), fetch top results, and return sentence-level summaries plus optional converted page content. |
| distribution | public |
Web Search Summary
Use this when you need short summaries of the top pages, not full page content.
If you need fetched Markdown as the main artifact, use web-search.
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
Run a summarised search:
bun /workspace/.pi/skills/web-search-summary/web-search-summary.ts --query "your query"
Adjust fetch depth or summary length:
bun /workspace/.pi/skills/web-search-summary/web-search-summary.ts --query "your query" --fetch-limit 3 --max-sentences 4 --max-chars 800
Output shape
The script prints JSON like:
{
"query": "...",
"searxUrl": "http://.../search",
"limit": 5,
"fetch": true,
"maxSentences": 3,
"maxChars": 600,
"results": [
{
"title": "...",
"url": "https://...",
"content": "fetched markdown or original snippet",
"summary": "short sentence-level digest"
}
]
}
summary is only added for fetched items.content contains converted Markdown when fetch succeeds.
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
summary: "Failed to fetch: ..." while other results continue.
- Set
--fetch false to skip page retrieval entirely.
Options
--query / --q — required search query--limit — number of search results to return (default 5)--fetch — set to false to skip page fetches (default true)--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)--max-sentences — summary sentence limit (default 3)--max-chars — summary character limit (default 600)
Notes
- Summaries are heuristic first-sentence digests and may need human refinement.
- HTML conversion uses
turndown + linkedom and prefers <article>, <main>, or [role='main'].
