← Back to Skills Marketplace
hgta23

Find Agents Skill

by bittao · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
78
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install find-agents
Description
Performs intelligent web and specialized searches, aggregates multi-source results, and delivers summarized, cited answers with credibility scoring.
README (SKILL.md)

name: find-agents version: 1.0.0 description: "AI-powered find agents that performs intelligent web searches, aggregates results, and provides summarized answers with source citations. Use when: user needs to find current information, research topics, verify facts, or gather data from multiple sources."

Find Agents Skill

An intelligent AI-powered find agents that performs advanced web searches, aggregates results from multiple sources, and provides comprehensive, cited answers to user queries.

Overview

Find Agent is a powerful research tool that combines web search capabilities with AI summarization. It helps users quickly find accurate, up-to-date information from across the internet without manually browsing multiple websites.

Key Features

🔍 Multi-Source Search

  • Web Search: Real-time search across major search engines
  • News Search: Latest news and current events
  • Academic Search: Scholarly articles and research papers
  • Image Search: Visual content discovery
  • Code Search: Programming solutions and documentation

🤖 AI-Powered Analysis

  • Smart Summarization: Condenses multiple sources into coherent answers
  • Fact Verification: Cross-references information across sources
  • Source Credibility: Ranks sources by reliability and authority
  • Context Understanding: Maintains conversation context for follow-up questions

📊 Result Organization

  • Structured Output: Presents information in easy-to-read formats
  • Citation Tracking: Every claim is backed by source links
  • Confidence Scoring: Indicates reliability of information
  • Related Topics: Suggests related queries for deeper exploration

Use Cases

1. Research & Learning

  • Academic Research: Find scholarly articles and citations
  • Topic Exploration: Get comprehensive overviews of complex subjects
  • Fact Checking: Verify claims with multiple authoritative sources
  • Learning New Skills: Find tutorials, documentation, and best practices

2. Professional Work

  • Market Research: Gather industry trends and competitor information
  • Technical Documentation: Find official docs and community solutions
  • News Monitoring: Stay updated on relevant industry news
  • Data Collection: Aggregate statistics and reports

3. Daily Life

  • Product Research: Compare features, prices, and reviews
  • Travel Planning: Find destinations, hotels, and local information
  • Health Information: Access reliable medical and wellness information
  • Current Events: Get summaries of breaking news and developments

Usage Examples

Basic Search

User: "What are the latest developments in quantum computing?"
Search Agent: Performs web search → Aggregates results → Provides summary with citations

Technical Query

User: "How to implement JWT authentication in Node.js?"
Search Agent: Searches code repositories → Finds tutorials → Provides code examples with sources

Fact Verification

User: "Is it true that Python is the most popular programming language in 2024?"
Search Agent: Cross-references multiple sources → Provides verified answer with statistics

News Search

User: "What happened in the tech industry this week?"
Search Agent: Searches recent news → Summarizes key events → Provides timeline

Search Capabilities

Supported Search Types

Type Description Best For
general Broad web search General knowledge, how-to guides
news Recent news articles Current events, trending topics
academic Scholarly sources Research, citations, studies
code Code repositories Programming solutions, libraries
images Visual content Reference images, diagrams

Advanced Search Operators

  • "exact phrase" - Search for exact matches
  • site:example.com - Search within specific domain
  • filetype:pdf - Find specific file types
  • -exclude - Exclude specific terms
  • OR - Search for either term

Output Format

Search Agent provides structured responses:

## Summary
[Concise answer to the query]

## Key Findings
- [Point 1 with citation]
- [Point 2 with citation]
- [Point 3 with citation]

## Sources
1. [Source Title](URL) - [Credibility Score]
2. [Source Title](URL) - [Credibility Score]

## Related Queries
- [Suggested follow-up 1]
- [Suggested follow-up 2]

Technical Architecture

Components

  1. Search Engine Interface: Connects to multiple search APIs
  2. Content Fetcher: Retrieves and parses web pages
  3. AI Analyzer: Processes and summarizes content
  4. Citation Manager: Tracks and formats source references
  5. Response Formatter: Structures output for readability

Data Flow

User Query → Search APIs → Content Extraction → AI Analysis → Citation Mapping → Formatted Response

Configuration

Environment Variables

SEARCH_API_KEY=your_search_api_key
AI_MODEL=gpt-4  # or other supported models
MAX_RESULTS=10  # number of sources to analyze
TIMEOUT=30000   # request timeout in milliseconds

Customization Options

  • Result Count: Adjust number of sources analyzed
  • Source Filters: Whitelist/blacklist specific domains
  • Language Preferences: Prioritize results in specific languages
  • Time Range: Filter results by date (past day, week, month, year)

Best Practices

When to Use Search Agent

✅ Current information not in training data ✅ Verifying facts or claims ✅ Researching new or niche topics ✅ Finding specific technical solutions ✅ Gathering multiple perspectives

When NOT to Use Search Agent

❌ Information already known to be in training data ❌ Personal or private information ❌ Highly sensitive queries ❌ When offline functionality is required

Limitations

  • Search Dependency: Requires internet connectivity
  • API Rate Limits: Subject to search API quotas
  • Source Availability: Limited by indexed web content
  • Real-time Lag: News may have slight delays
  • Language Support: Optimized for major languages

Privacy & Security

  • No Query Logging: User searches are not stored
  • Secure Connections: All API calls use HTTPS
  • Source Verification: Filters known malicious domains
  • Data Minimization: Only fetches necessary content

Integration

With Other Skills

  • findskills: Discover complementary skills
  • code-reviewer: Verify code solutions found
  • translator: Translate search results

API Usage

// Example: Using Search Agent programmatically
const searchAgent = require('search-agent');

const result = await searchAgent.search({
  query: "renewable energy trends 2024",
  type: "news",
  maxResults: 5
});

Version History

  • v1.0.0 (Current)
    • Initial release
    • Multi-source search capability
    • AI-powered summarization
    • Citation tracking

Support & Feedback

For issues, feature requests, or contributions:

  • GitHub Issues: [repository-url]
  • Documentation: [docs-url]
  • Community: [community-url]

License

MIT License - See LICENSE file for details


Keywords: search, research, web search, AI search, information retrieval, fact checking, news aggregation, academic search, code search, intelligent agent, knowledge discovery, source citation, automated research

Usage Guidance
This skill overpromises: its docs claim multi-engine, API-key-backed searches and privacy guarantees, but the code contains only placeholder search endpoints and returns simulated results. Practical steps before installing or using: 1) Treat SEARCH_API_KEY as required only if the implementation actually calls real APIs — ask the author or inspect updated code that replaces the placeholder performSearch with real API calls. 2) Don't provide sensitive API keys or secrets unless you confirm the skill actually needs them and the endpoint is a trusted service. 3) Note the code can fetch arbitrary URLs (axios + cheerio), so run it in a restricted environment if you want to test. 4) Prefer skills with a clear source/homepage and implemented search integrations (not placeholders) and verify privacy claims in code. If the repository later replaces placeholder endpoints with legitimate, documented API integrations and updates the registry metadata to declare required env vars, reassess — that would reduce the concern.
Capability Assessment
Purpose & Capability
The SKILL.md/README claim real-time multi-engine web/news/academic/code search and present SEARCH_API_KEY as required; however, the code's performSearch function uses placeholder endpoints (e.g. https://api.search.com/general) and returns a simulated result array instead of calling real search APIs. The code does perform page fetches (axios + cheerio) for result URLs, which is consistent with scraping, but there is no implemented integration with the multiple search APIs the docs promise. Registry metadata lists no required env vars, while the docs advertise SEARCH_API_KEY as required — an incoherent expectation vs implementation.
Instruction Scope
The runtime instructions (SKILL.md) instruct use of SEARCH_API_KEY and describe connecting to multiple search APIs, but the actual runtime behavior in index.js does not use any external API endpoints for search (it uses a simulated result set) and only fetches individual URLs returned by that placeholder result. The SKILL.md also asserts privacy/security guarantees (e.g., 'No query logging', 'malicious domain filtering') that are not backed by code. Instructions therefore overpromise and grant the agent broad web-fetching capability without clear, implemented boundaries.
Install Mechanism
There is no install spec in the registry (instruction-only), but the skill includes Node.js code and a package.json with dependencies on axios and cheerio. This is not high-risk by itself (dependencies are from npm, no remote arbitrary download URLs), but the presence of runnable code despite an 'instruction-only' install declaration is an inconsistency to be aware of.
Credentials
The SKILL.md and README reference environment variables such as SEARCH_API_KEY, AI_MODEL, SEARCH_MAX_RESULTS, and SEARCH_TIMEOUT. The registry lists no required env vars. The code reads process.env.SEARCH_API_KEY and AI_MODEL into its config, but SEARCH_API_KEY is never actually used to call a real search API in the provided performSearch implementation. Requiring or asking for API keys in docs while not declaring them in metadata is inconsistent and could mislead users into providing secrets unnecessarily.
Persistence & Privilege
The skill does not request permanent presence (always: false) and does not modify other skills or system-wide agent settings. It exports functions and provides CLI behavior, but it does not request elevated platform privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install find-agents
  3. After installation, invoke the skill by name or use /find-agents
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of the Find Agents skill. - Performs intelligent, multi-source web searches with real-time aggregation. - Provides AI-generated summaries with structured output and source citations. - Supports general, news, academic, code, and image search types. - Includes result organization features: confidence scoring, source credibility ranking, and related topics. - Offers customization options for result count, source filters, language, and date range.
Metadata
Slug find-agents
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Find Agents Skill?

Performs intelligent web and specialized searches, aggregates multi-source results, and delivers summarized, cited answers with credibility scoring. It is an AI Agent Skill for Claude Code / OpenClaw, with 78 downloads so far.

How do I install Find Agents Skill?

Run "/install find-agents" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Find Agents Skill free?

Yes, Find Agents Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Find Agents Skill support?

Find Agents Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Find Agents Skill?

It is built and maintained by bittao (@hgta23); the current version is v1.0.0.

💬 Comments