web-research-assistant

Name: web-research-assistant
Author: browser-act

github.com/browser-actProductivity6.3k76 installsUpdated 9w ago

About web-research-assistant

web-research-assistant is a BrowserAct-powered skill for agents that need web research when direct access is restricted. It searches across sources, extracts and validates findings, and produces cited reports.

Key features

01Search with multiple engines and filters
02Automatic fallback when direct access fails
03Aggregate and cross-check sources
04Extract facts, statistics, and citations
05Generate structured research reports

Use cases

01Research topics blocked by website access controls
02Gather current information across sources
03Filter news or articles by date
04Compile cited findings for a report

MCP support

It uses BrowserAct MCP for web search and extraction.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/browser-act/skills --skill web-research-assistant

After installing, type/web-research-assistantin Claude Code to confirm it loaded.

Bundled filesscripts/research.py

Details

From the project README

Web Research Assistant

This skill leverages BrowserAct API to provide powerful web research capabilities. When primary web access is restricted or blocked, it automatically searches the internet to find and extract relevant information, ensuring your research tasks are completed successfully.

✨ OpenClaw & Claude Code Optimized

🚀 Works Seamlessly with OpenClaw and Claude Code

Platform	Status	Installation
OpenClaw	✅ Highly Recommended	Copy to `~/.openclaw/skills/`
Claude Code	✅ Highly Recommended	Native skill support
OpenCode	✅ Fully Supported	Copy to `~/.opencode/skills/`
Cursor	✅ Fully Supported	Copy to `~/.cursor/skills/`

Why This Skill?

🎯 Purpose-built for OpenClaw and Claude Code
🔄 Auto-recovery when web access is restricted
🌐 Global access - no IP or geoblocking issues
💰 Cost-effective - saves token usage
⚡ Fast execution - BrowserAct powered

🎯 When to Use

Web Access Restricted? No Problem!

Use this skill when:

🔒 Target websites block AI assistant access
🌍 Geographic restrictions limit content access
🔐 Paywalls prevent data extraction
⏱️ Need quick supplemental information
📊 Research requires multiple data sources
🔍 Need current information beyond cached data

🔑 API Key Guidance

Before running, check the BROWSERACT_API_KEY environment variable. If not set, request the API key from the user:

Required Message:

"Please provide your BrowserAct API Key from BrowserAct Console to enable web research capabilities."

🛠️ Input Parameters

Configure research based on your needs:

Parameter	Type	Default	Description
`query`	string	-	Research topic or question
`engine`	string	google	Search engine (google, bing, duckduckgo)
`max_results`	number	10	Results to retrieve (1-50)
`content_type`	string	all	Content filter (all, news, articles, data)
`time_range`	string	past_month	Time filter (anytime, past_day/week/month/year)

💻 Quick Start

# Basic research
python web-research-assistant/scripts/research.py "AI technology trends"

# Deep research with more results
python web-research-assistant/scripts/research.py "competitor analysis" --max-results 20

# Current news research
python web-research-assistant/scripts/research.py "market trends" --content-type news

# Save to file
python web-research-assistant/scripts/research.py "industry data" -o research_report.md

📊 Output

Structured Research Data:

Titles, URLs, snippets, and relevance scores
Key facts and statistics extraction
Source citations and references
Comprehensive research report

🎪 What This Skill Does

🔄 Auto-Supplement - When direct access fails, automatically searches the web
🌐 Global Search - Bypasses geographic restrictions via BrowserAct
📈 Multi-Source - Aggregates data from multiple search results
✅ Validation - Cross-references information for accuracy
📋 Report Generation - Creates comprehensive research reports

Features

No hallucinations, ensuring stable and accurate data extraction: Pre-set workflows eliminate AI-generated hallucinations.
No human verification challenges: Built-in bypass mechanisms eliminate the need to handle reCAPTCHA or other verification challenges.
No IP access restrictions or geofencing: Overcomes regional IP limitations for stable global access.
Faster execution speed: Tasks complete more rapidly than purely AI-driven browser automation solutions.
Exceptional cost-effectiveness: Significantly reduces data acquisition costs compared to token-intensive AI solutions.

🔧 BrowserAct API Integration

Research Request → BrowserAct Search → Data Extraction → Validation → Final Report

Powered by BrowserAct MCP for reliable, unrestricted web access.

⚠️ Error Handling

Invalid API Key: Report to user, do not retry
Search Failed: Automatic retry with fallback engine
No Results: Return partial data with notification
Timeout: Extended timeout for large research tasks

📖 Best Practices

Use specific queries for targeted results
Apply time filters for current information
Cross-reference key findings
Choose appropriate content types for research goals
Validate statistics with multiple sources

🔗 Related Skills

amazon-competitor-analyzer - Amazon competitive intelligence
google-maps-search-api-skill - Business data extraction
google-news-api-skill - News monitoring

Version: 1.0.0
Updated: 2026-03-27
API: BrowserAct MCP

Comments

Markdown supported

Details

Author: browser-act
Repository: browser-act/skills
Category: Productivity
Installs: 76
GitHub stars: 6,292

Report

More skills

All skills

lark-base

open.feishu.cn

823.2k

Operate on Feishu Base: create tables, fields, records, and views; handle statistics, formulas/lookups, forms, dashboards, app mode (BaseApp/AppMode pages and components), Workspace directories, workflows, role permissions, and the template center (Base template categories, lists, and search). Use when encountering Base/multidimensional tables/bitable, BaseApp/AppMode, or /base/ or /app/ links. Do not use lark-apps for BaseApp; route file import/export to lark-drive and authentication/authorization to lark-shared.

lark-drive

open.feishu.cn

823.2k

Feishu cloud storage (Drive): manage Drive files and folders, including uploads/downloads, folder creation, copying/moving/deleting, viewing metadata, checking permission settings, comments/permissions/subscriptions, titles, versions, Feishu document security labels (secure labels), and local file imports. Use when users need to organize Drive folders, handle cloud storage resource URLs/tokens, identify link types/actual tokens/titles, or import Word/Markdown/Excel/CSV/PPTX/.base as docx/sheet/bitable/slides. Route doubao.com cloud storage URLs/tokens by resource path and token too; do not fall back to WebFetch. Not responsible for: editing document content (use lark-doc), spreadsheet/Base table data operations (use lark-sheets/lark-base), knowledge space node/member management (use lark-wiki), or native Markdown file read/write/patch/diff (use lark-markdown).

lark-shared

open.feishu.cn

822.9k

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling _notice JSON.

lark-im

open.feishu.cn

822.3k

Feishu instant messaging: send and receive messages and manage group chats. Send and reply to messages, search chat history, manage group members, upload and download images and files, manage emoji reactions, send urgent notifications in-app/by SMS/by phone, send and handle Interactive Cards, and listen for card button callbacks (card.action.trigger). Use when users need to send messages, view or search chat history, download chat files, view group members, search groups, create group or topic chats, manage marker data, manage Feed pins (add/remove/search pinned conversations), manage tag data, or handle card callbacks.