
Web Search
- 562 installs
- modelscope.cn
This is a copy of web-search by halt-catch-fire - installs and ranking accrue to the original listing.
web-search is an agent skill that performs real-time internet searches and returns current web content to AI coding agents.
About
web-search is an agent skill that lets AI coding agents perform real-time internet searches and retrieve fresh web content during development sessions. Solo builders and indie hackers use it when their agents need current data, API documentation, competitor analysis, technology trends, or answers to fast-changing technical questions. It removes the limitation of static training data so agents can reason with today's information. The skill is especially valuable for research-heavy tasks where outdated knowledge would lead to incorrect suggestions or missed opportunities. Because it can be invoked at any point in the solo-builder journey, it becomes a foundational capability that improves every phase from initial discovery through ongoing product iteration.
- Enables live web search directly from agent workflows
- Returns current information beyond training cutoffs
- Supports research across any builder activity
- Integrates with Claude Code, Cursor and similar agents
- 471 developers have installed this skill
Web Search by the numbers
- 562 all-time installs (skills.sh)
- +7 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/modelscope.cn --skill web-searchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 562 |
|---|---|
| Repository | modelscope.cn ↗ |
What it does
Give their coding agents real-time web access for up-to-date information, competitor data, and technical research.
Who is it for?
Best when your agents need fresh information for research, competitor analysis, technology decisions, or documentation lookup.
Skip if: Projects that must run entirely offline or where web access is restricted by security policy.
When should I use this skill?
When the agent needs up-to-date information from the internet that is beyond its training data.
What you get
The agent receives accurate, up-to-date search results that improve its reasoning and recommendations, which can then be used by next skills such as research synthesis or implementation planning.
- Search result data returned to the calling agent
By the numbers
- 471 installs
Files
Web Search & Extraction
Search the web and extract content via inference.sh CLI.

Quick Start
Requires inference.sh CLI (infsh). Get installation instructions:npx skills add inference-sh/skills@agent-tools
infsh login
# Search the web
infsh 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
infsh 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
infsh app run tavily/extract --input '{
"urls": ["https://example.com/article1", "https://example.com/article2"]
}'Extracts clean text and images from multiple URLs.
Exa Search
infsh app run exa/search --input '{
"query": "machine learning frameworks comparison"
}'Returns highly relevant links with context.
Exa Answer
infsh app run exa/answer --input '{
"question": "What is the population of Tokyo?"
}'Returns direct factual answers.
Exa Extract
infsh app run exa/extract --input '{
"url": "https://example.com/research-paper"
}'Extracts and analyzes web page content.
Workflow: Research + LLM
# 1. Search for information
infsh app run tavily/search-assistant --input '{
"query": "latest developments in quantum computing"
}' > search_results.json
# 2. Analyze with Claude
infsh 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
infsh app run tavily/extract --input '{
"urls": ["https://example.com/long-article"]
}' > content.json
# 2. Summarize with LLM
infsh 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 150+ apps)
npx skills add inference-sh/skills@agent-tools
# 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-generationBrowse all apps: infsh app list
Documentation
- Adding Tools to Agents - Equip agents with search
- Building a Research Agent - LLM + search integration guide
- Tool Integration Tax - Why pre-built tools matter
Related skills
How it compares
Use instead of static knowledge prompts when you need live data from the current web.
FAQ
Who is web-search for?
web-search is for developers and developers who use Claude Code, Cursor, or similar agents and need their AI tools to access current information from the internet.
When should I use web-search?
Use it when your agent needs current API references, technology comparisons, competitor product details, latest framework updates, market research, or any information that changes frequently. It is valuable before making technical decisions, validating assumptions, exploring new
Is web-search safe to install?
Users should review the Security Audits panel on this page before installing. Like any tool with network access, it is important to understand the permission model and data handling.