# brightdata-local-search

Spins up a local search pipeline on Bright Data's SERP API: query expansion, SERP retrieval, RRF reranking.

- skill · `type=skill` · Claude Code · 625 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/development/brightdata-local-search
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/brightdata-local-search

## What it does

This skill runs the `unfancy-search` pipeline on your own machine. It expands a query, pulls SERP results from several engines, reranks them with RRF, drops duplicates and clusters hits by domain.

Setup takes three moves: clone the `unfancy-search` repo, fill in `.env`, start the server. Docker is the recommended route; Node.js 18+ with pnpm works too. The server listens on `http://localhost:3000`. A search is a `POST /api/search` call that returns a `jobId`, and you poll `/api/search-status/{jobId}` every 3 seconds until `status` reads `done`.

You need a Bright Data account with SERP API access and a token in `BRIGHT_DATA_API_TOKEN`. The Anthropic key in `ANTHROPIC_API_KEY` is optional, and without it query expansion stays off. Research mode fires 12 sub-queries, expand mode fires 3 — both bill tokens, so turn them off when one query is enough.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --skill development/brightdata-local-search
```

2. **Skills CLI (Vercel)**
```bash
npx skills add davila7/claude-code-templates --skill brightdata-local-search -a claude-code
```

3. **Manually: put the files in place**
- File: `~/.claude/skills/brightdata-local-search/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/brightdata-local-search/

### Codex

**Manually: put the files in place**
- File: `.agents/skills/brightdata-local-search/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

**Manually: put the files in place**
- File: `.cursor/skills/brightdata-local-search/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davila7/claude-code-templates brightdata-local-search
```

2. **Manually: put the files in place**
- File: `.github/skills/brightdata-local-search/SKILL.md`

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/development/brightdata-local-search
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/brightdata-local-search/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/development/brightdata-local-search

## When to use it
- run web search locally instead of through a hosted endpoint
- widen a single query into several sub-queries
- strip duplicates and group results by domain
- keep unwanted domains out of the results
- ground an agent's answers in fresh web data

## Example prompts
- Run a local search for kubernetes scaling strategies in research mode
- Find articles on API rate limiting, but exclude pinterest.com and quora.com
- Start the unfancy-search server and show me the ranked results with RRF scores

## Similar
- [search](https://affpapa.org/en/nevibecode/skills/brightdata-search.md) — skill · 7500 installs
- [brightdata-mcp](https://affpapa.org/en/nevibecode/mcp/brightdata-mcp.md) — MCP server · ★ 2687
- [local-place-search](https://affpapa.org/en/nevibecode/skills/local-place-search.md) — skill · 395 installs
- [searxng-search](https://affpapa.org/en/nevibecode/skills/searxng-search.md) — skill · 828 installs
- [postgres-hybrid-text-search](https://affpapa.org/en/nevibecode/skills/postgres-hybrid-text-search.md) — skill · 372 installs
- [scraping-google-search-results](https://affpapa.org/en/nevibecode/skills/scraping-google-search-results.md) — skill · 759 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 361 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md