skilld
All skills
inference-shell avatar

/web-search

@becc256
by inference-shellinference-shell/skills757 stars
104

Web search and content extraction with Tavily and Exa via inference.sh CLI. Apps: Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract. Capabilities: AI-powered search, content extraction, direct answers, research. Use for: research, RAG pipelines, fact-checking, content aggregation, agents. Triggers: web search, tavily, exa, search api, content extraction, research, internet search, ai search, search assistant, web scraping, rag, perplexity alternative

Ask your Agent

Use this Skill: https://skilld.dev/gh/inference-shell/skills/web-search

This session only. Nothing lands on disk.

SKILL.md

≈121 tokens always: the name and description. ≈887 when used: this file.

Install the belt CLI skill: npx skills add belt-sh/cli

Web Search & Extraction

Search the web and extract content via inference.sh CLI.

Web Search & Extraction

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Search the web
belt app run tavily/search-assistant --input '{"query": "latest AI developments 2024"}'

Available Apps

Tavily

App App ID Description
Search Assistant tavily/search-assistant AI-powered search with answers
Extract tavily/extract Extract content from URLs

Exa

App App ID Description
Search exa/search Smart web search with AI
Answer exa/answer Direct factual answers
Extract exa/extract Extract and analyze web content

Examples

Tavily Search

belt app run tavily/search-assistant --input '{
  "query": "What are the best practices for building AI agents?"
}'

Returns AI-generated answers with sources and images.

Tavily Extract

belt app run tavily/extract --input '{
  "urls": ["https://example.com/article1", "https://example.com/article2"]
}'

Extracts clean text and images from multiple URLs.

Exa Search

belt app run exa/search --input '{
  "query": "machine learning frameworks comparison"
}'

Returns highly relevant links with context.

Exa Answer

belt app run exa/answer --input '{
  "question": "What is the population of Tokyo?"
}'

Returns direct factual answers.

Exa Extract

belt app run exa/extract --input '{
  "url": "https://example.com/research-paper"
}'

Extracts and analyzes web page content.

Workflow: Research + LLM

# 1. Search for information
belt app run tavily/search-assistant --input '{
  "query": "latest developments in quantum computing"
}' > search_results.json

# 2. Analyze with Claude
belt app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Based on this research, summarize the key trends: <search-results>"
}'

Workflow: Extract + Summarize

# 1. Extract content from URL
belt app run tavily/extract --input '{
  "urls": ["https://example.com/long-article"]
}' > content.json

# 2. Summarize with LLM
belt app run openrouter/claude-haiku-45 --input '{
  "prompt": "Summarize this article in 3 bullet points: <content>"
}'

Use Cases

  • Research: Gather information on any topic
  • RAG: Retrieval-augmented generation
  • Fact-checking: Verify claims with sources
  • Content aggregation: Collect data from multiple sources
  • Agents: Build research-capable AI agents

Related Skills

# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli

# LLM models (combine with search for RAG)
npx skills add inference-sh/skills@llm-models

# Image generation
npx skills add inference-sh/skills@ai-image-generation

Browse all apps: belt app list

Documentation

Source: SKILL.md on GitHub

Third-party checks

2 warnings16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill facilitates web searching and content extraction through a dedicated CLI tool. It is designed to process external web data, which introduces a risk of indirect prompt injection if the retrieved content contains malicious instructions intended for the processing LLM.

  • Socket16d

    1 alert: gptAnomaly

  • Snyk16d

    Risk: MEDIUM · 1 issue

  • Runlayer6mo

    1/1 file flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at becc256. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last week.

Activeupdated 2 months ago

Capability

What it can do
Runs commands
All 1 allowed tools
Bash(belt *)

Topics

  • web-search
  • tavily
  • exa
  • content-extraction
  • rag
  • research
  • fact-checking
  • inference-sh
  • bash

README badge

README badge for inference-shell/skills/web-search

What it does

Performs web search and content extraction via Tavily and Exa APIs through the inference.sh CLI. Includes AI-powered search with answers, URL extraction, and direct factual lookups—useful for building research agents, RAG pipelines, and fact-checking workflows.

Generated from the current SKILL.md.

Frequently asked

Does this skill work with Claude or other LLMs?
Yes. The skill provides search and extraction apps via the belt CLI that can be chained with LLM models in RAG workflows or agent pipelines. The SKILL.md includes examples of combining Tavily search with Claude models.
What's the difference between Tavily and Exa?
Tavily offers search-assistant (with AI answers) and extract apps. Exa offers search, answer (direct factual responses), and extract apps. Both support content extraction; choose based on whether you need AI-generated summaries (Tavily) or direct factual answers (Exa).
Can I extract content from multiple URLs at once?
Yes. Tavily extract accepts a urls array and returns clean text and images from all provided URLs in one call.
Do I need to install anything before using this skill?
Yes. You must install the belt CLI (`npx skills add belt-sh/cli`) and run `belt login` to authenticate with inference.sh before running any web search or extraction apps.
Can this skill be used for RAG pipelines?
Yes. The skill is explicitly designed for retrieval-augmented generation workflows, allowing you to search the web, extract content, and pass results to LLM models for analysis or summarization.

Generated from the current SKILL.md. These answers refresh after source changes.