This repository has no description
1.1 kB
46 lines
1---
2name: websearch
3description: Search the web using Kagi and fetch page contents. Use when you need current information, documentation, or to look up APIs/libraries.
4---
5
6# Web Search Skill
7
8Search the web using Kagi and fetch/extract page contents.
9
10## Search
11
12```bash
13kagi-search "your query"
14```
15
16Returns search results with titles, URLs, and snippets.
17
18### JSON output with quick answer
19
20```bash
21kagi-search --json "your query"
22```
23
24Returns JSON with:
25- `quick_answer.markdown` — AI-generated summary
26- `results[].title`, `results[].url`, `results[].snippet`
27
28### Get more results
29
30```bash
31kagi-search --json --links 10 "your query"
32```
33
34## Fetch a page
35
36```bash
37curl -sL "https://example.com" | head -500
38```
39
40For cleaner extraction from HTML, pipe through a text extractor or use `curl` with appropriate flags.
41
42## Typical workflow
43
441. Search: `kagi-search --json "nix flake lock update single input"` — get overview + links
452. Fetch: `curl -sL "<url>"` — get full page content from a promising result
463. Use the information to answer the question or solve the task