9routerx-web-search — Claude Code skill: web search and setup
The 9routerx-web-search Claude Code skill searches the web and public X posts through 9RouterX. It runs when an agent is asked to find articles, information, or posts on X.
MIT ★ 259 updated 2026-11-16
npx skills add yanstd888/9routerx --skill 9routerx-web-search -a claude-codeWhat 9routerx-web-search does
The skill sends search requests to POST $9ROUTERX_URL/v1/search and returns results with titles, links, and text snippets. Requests can target web pages, news, or X; country, language, date-range, and domain options depend on the selected provider.
Available search models can be fetched from /v1/models/web. Models marked combo chain providers and switch to a fallback if one fails. A running 9RouterX instance and the 9ROUTERX_URL variable are required; set 9ROUTERX_KEY when authentication is enabled. X searches through Xquik also need its API key in 9RouterX provider settings. Xquik charges 1 credit per returned post.
What it helps with
- find web articles on a topic
- retrieve recent news results
- search public X posts for a query
- limit web results to selected domains
Example prompts for the agent
- Find articles about running language models locally.
- Search for recent TypeScript news in English.
- Find public X posts from
githubabout releases.
How to install 9routerx-web-search
1Skills CLI (Vercel)
npx skills add yanstd888/9routerx --skill 9routerx-web-search -a claude-code2Manually: put the files in place
~/.claude/skills/9routerx-web-search/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/9routerx-web-search/
1Skills CLI (Vercel)
npx skills add yanstd888/9routerx --skill 9routerx-web-search -a codex2Manually: put the files in place
.agents/skills/9routerx-web-search/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add yanstd888/9routerx --skill 9routerx-web-search -a cursor2Manually: put the files in place
.cursor/skills/9routerx-web-search/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install yanstd888/9routerx skills/9routerx-web-search2Manually: put the files in place
.github/skills/9routerx-web-search/SKILL.md1Skills CLI (Vercel)
npx skills add yanstd888/9routerx --skill 9routerx-web-search -a gemini-cli2Platform CLI
gemini skills install https://github.com/yanstd888/9routerx --path skills/9routerx-web-searchManually: put the files in place
.devin/skills/9routerx-web-search/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about 9routerx-web-search
How do I install 9routerx-web-search in Claude Code?
Run npx skills add yanstd888/9routerx --skill 9routerx-web-search -a claude-code. The skill file is placed at ~/.claude/skills/9routerx-web-search/SKILL.md.
What does 9routerx-web-search do?
It sends web, news, or public X search requests to 9RouterX and returns the results. Requests go through the selected search provider.
What does 9routerx-web-search require?
A running 9RouterX instance and the 9ROUTERX_URL variable are required; authentication also requires 9ROUTERX_KEY. X searches through Xquik need its API key in the provider settings.
Source text
SKILL.md · MIT
---
name: 9routerx-web-search
description: Web and X search via 9RouterX /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the web, find articles, or search public X posts.
---
# 9RouterX — Web Search
Requires `9ROUTERX_URL` (and `9ROUTERX_KEY` if auth enabled). See https://raw.githubusercontent.com/yanstd888/9routerx/refs/heads/main/skills/9routerx/SKILL.md for setup.
## Discover
```bash
curl $9ROUTERX_URL/v1/models/web | jq '.data[] | select(.kind=="webSearch") | .id'
# Per-provider params (searchTypes, maxResults, required options like cx for google-pse)
curl "$9ROUTERX_URL/v1/models/info?id=tavily/search"
```
IDs end in `/search` (e.g. `tavily/search`). Combos (`owned_by:"combo"`) chain providers with auto-fallback.
## Endpoint
`POST $9ROUTERX_URL/v1/search`
| Field | Required | Notes |
|---|---|---|
| `model` (or `provider`) | yes | from `/v1/models/web` (e.g. `tavily` or `brave`) |
| `query` | yes | search query |
| `max_results` | no | default 5 |
| `search_type` | no | `web` (default) / `news` / `x` for Xquik |
| `country`, `language`, `time_range`, `domain_filter` | no | provider-dependent |
## Examples
```bash
curl -X POST $9ROUTERX_URL/v1/search \
-H "Authorization: Bearer $9ROUTERX_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tavily","query":"9RouterX open source","max_results":5}'
```
JS:
```js
const r = await fetch(`${process.env.9ROUTERX_URL}/v1/search`, {
method: "POST",
headers: { "Authorization": `Bearer ${process.env.9ROUTERX_KEY}`, "Content-Type": "application/json" },
body: JSON.stringify({ model: "search-combo", query: "latest LLM benchmarks", max_results: 10 }),
});
console.log(await r.json());
```
X search with Xquik:
```bash
curl -X POST $9ROUTERX_URL/v1/search \
-H "Authorization: Bearer $9ROUTERX_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"xquik","query":"from:github release","max_results":10,"provider_options":{"queryType":"Latest"}}'
```
Add the Xquik API key in 9RouterX's provider settings. Xquik charges 1 credit per returned post. Continue a search by passing `pagination.next_cursor` as `provider_options.cursor`.
Xquik responses include provider pagination and credit usage:
```json
{
"pagination": { "has_more": true, "next_cursor": "cursor-2" },
"usage": { "queries_used": 1, "search_cost_usd": null, "provider_credits_used": 10 }
}
```
## Response shape
```json
{
"provider": "tavily",
"query": "9RouterX open source",
"results": [
{
"title": "...", "url": "https://...", "display_url": "github.com/...",
"snippet": "...", "position": 1, "score": 0.92,
"published_at": null, "favicon_url": null, "content": null,
"metadata": { "author": null, "language": null, "source_type": null, "image_url": null },
"citation": { "provider": "tavily", "retrieved_at": "2026-...", "rank": 1 }
}
],
"answer": null,
"usage": { "queries_used": 1, "search_cost_usd": 0.008 },
"metrics": { "response_time_ms": 850, "upstream_latency_ms": 700, "total_results_available": 12 },
"errors": []
}
```
## Provider quirks
All accept `query` + `max_results`. Optional fields vary:
| Provider | Supports | Required extras |
|---|---|---|
| `tavily` | country, domain_filter, news topic | — |
| `exa` | domain_filter (incl/excl), news category | — |
| `brave-search` | country, language | — |
| `serper` | country, language, news endpoint | — |
| `perplexity` | country, language, domain_filter | — |
| `linkup` | domain_filter, time_range | `depth: fast/standard/deep` (option) |
| `google-pse` | country, language, time_range, offset | **`cx` required** (providerOptions) |
| `searchapi` | country, language, pagination | — |
| `youcom` | country, language, time_range, domain_filter, full_page | — |
| `searxng` | language, time_range | Self-hosted, **noAuth** |
| `xquik` | X/Twitter search operators, language, cursor pagination | `queryType: Latest/Top`, `cursor` (options) |
Provider IS the model — `"provider":"tavily" ≡ "model":"tavily"`.
© yanstd888 · MIT · yanstd888/9routerx