# Search and Extract Web Research

Research assistants need current sources without manual browsing. This skill runs Tavily and Exa apps through belt for search, extraction, and answers.

## Install

```bash
npx skillstore add halt-catch-fire/web-search
```

## Metadata

- Status: approved
- Slug: halt-catch-fire-web-search
- Skillstore revision: r1
- Version status: missing
- Tree hash: 17143ae042234c04605c8067e92c37da6437557c814b95a2651360028235b1af
- Author: halt-catch-fire
- GitHub username: halt-catch-fire
- License: MIT
- Repository: https://github.com/halt-catch-fire/skills/tree/main/tools/llm/web-search/
- Ref: 30c73eac2afe762f6aa9c4553158769369d47351
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, network
- Quality score: 50
- Quality tier: warning
- Public page: https://skillstore.pages.dev/skills/halt-catch-fire-web-search
- Manifest: https://skillstore.pages.dev/api/skills/halt-catch-fire-web-search/manifest

## Capabilities

- Runs Tavily Search Assistant queries through the belt CLI.
- Extracts clean content and images from URLs with Tavily.
- Uses Exa Search to return relevant links with context.
- Uses Exa Answer for direct factual responses.
- Shows workflows that combine search or extraction with OpenRouter Claude models.

## Use Cases

- Prepare Research Briefs: Collect current web sources and extract article text for concise briefing notes.
- Build RAG Context: Gather searchable content from URLs before adding it to retrieval pipelines.
- Track Market Signals: Compare public sources and summarize trends using search plus LLM workflows.

## Prompt Templates

### Basic Web Search

```
Search the web for {topic} with Tavily Search Assistant. Return key sources with short summaries.
```

### Extract Article Content

```
Extract clean text from these URLs: {urls}. Summarize each source and list images when available.
```

### Compare Search Providers

```
Run Tavily Search Assistant and Exa Search for {query}. Compare overlap, unique sources, and source quality.
```

### Build Research Workflow

```
Search for {topic}, extract the strongest sources, then draft a briefing with citations and open questions.
```

## Limitations

- Requires the inference.sh belt CLI and login before use.
- Sends queries, URLs, and content to external services.
- Quality depends on Tavily, Exa, OpenRouter, and source availability.
- Does not verify extracted claims without additional review.

## Best Practices

- Confirm sensitive queries can be shared with Tavily, Exa, inference.sh, and OpenRouter before running commands.
- Use specific questions and known domains when source quality matters.
- Review returned sources before using answers in reports or agents.

## Anti Patterns

- Do not submit secrets, credentials, or private customer data.
- Do not treat AI answers as verified facts without source review.
- Do not run broad extraction jobs without checking target site permissions.

## Security Audit

- Audited at: 2026-07-05T15:19:34.476\+00:00
- Summary: The skill is a legitimate web search and extraction wrapper, but it depends on external CLI execution and third-party services. Most static backtick findings are Markdown false positives, while the real concerns are belt command execution, wildcard belt permissions, remote installs, and disclosure of user queries or extracted content.

## Stats

- Views: 0
- Downloads: 5
- Favorites: 0
- Popularity score: 0