mupeng-web-claudeUnified web search skill. Fallback order ā web_search(Brave) ā duckduckgo ā claude.ai. Auto-cache search results (saved to memory/research/)
Install via ClawdBot CLI:
clawdbot install mupengi-bot/mupeng-web-claudeReliable web search via 3-tier fallback strategy: Brave API ā DuckDuckGo ā claude.ai browser
Use OpenClaw built-in web_search tool.
web_search(query="search query", count=5, freshness="pw")Pros:
Cons:
missing_brave_api_key error without keyUse DuckDuckGo API when Brave fails.
python -c "
from duckduckgo_search import DDGS
with DDGS() as ddgs:
results = list(ddgs.text('query', region='wt-wt', max_results=5))
for r in results:
print(f\"{r['title']}: {r['href']}\")
"Pros:
Cons:
Trigger web search in claude.ai browser tab.
1. browser navigate ā https://claude.ai/new
2. browser act type ā "search question"
3. browser act press ā Enter
4. sleep 15-30s
5. browser snapshot ā extract responsePros:
Cons:
if web_search available:
try web_search(query)
if success: return results
if web_search failed or unavailable:
try duckduckgo-search
if success: return results
if both failed:
fallback to web-claude browser methodAll search results automatically saved to memory/research/ folder:
Filename Convention:
memory/research/search-YYYY-MM-DD-HH-MM-[keyword].mdSaved Content:
Example:
# Web Search: AI Agent Market Size
- **Search Time:** 2026-02-14 07:56 KST
- **Search Method:** web_search (Brave API)
- **Query:** "AI agent market size 2026"
## Results
1. **AI Agent Market to Reach $47B by 2030** - TechCrunch
https://techcrunch.com/...
- CAGR 43.2% growth forecast
- Enterprise agents account for 60%
2. **Korean AI Market Exceeds 1 Trillion KRW** - Chosun Ilbo
https://chosun.com/...
- Q1 2026 basis
- Led by generative AI
...
## Insights
- AI agent market growing rapidly
- Enterprise automation is core driver
- Korean market also active"Search for latest AI agent trends"
"Find 2026 Korean SaaS investment status"ā Auto-attempts Tier 1 Brave ā Tier 2 DDG ā Tier 3 claude.ai
# Brave only
"Search with web_search: AI market size"
# DuckDuckGo only
"Search with duckduckgo: privacy-focused"
# claude.ai browser only
"Analyze with web-claude: complex market research"# Last 24 hours news
web_search(..., freshness="pd")
# Last week
web_search(..., freshness="pw")
# Last month
web_search(..., freshness="pm")web_search(query="query", search_lang="ko", country="KR")1. browser navigate ā https://claude.ai/new (or existing tab)
2. browser snapshot ā save targetId
3. Find input field (contenteditable div or textarea)
4. browser act type ā enter question
5. browser act press ā Enter
6. sleep 15-30s (wait for response)
7. browser snapshot ā extract response text
8. Return result to caller + save to memory/research/Use this unified search skill when monitoring competitors:
Use search results for card news research:
Search for related info after YouTube summary:
| Situation | Recommended Method |
|-----------|-------------------|
| Need fast search | web_search (Brave) |
| No Brave key | duckduckgo-search |
| Privacy important | duckduckgo-search |
| Need analysis+summary | web-claude |
| Complex research | web-claude |
| Image/video search | duckduckgo-search |
| Latest news (24h) | web_search (freshness="pd") |
memory/research/ folder auto-createdš§ Built by ė¬“ķģ“ ā Mupengism ecosystem skill
Generated Feb 25, 2026
Startups can use the skill to quickly gather market data on competitors, such as funding rounds or product launches, using the fast web_search for real-time info and duckduckgo for privacy-sensitive searches. The auto-cache feature saves results to memory/research/ for ongoing analysis and reporting.
Consultants can leverage the fallback strategy to research industry trends, with web_search for recent data using freshness parameters and web-claude for complex analysis like summarizing market reports. This ensures reliable data collection even if one method fails, supporting client deliverables.
Content creators can use the skill to research topics for articles or videos, starting with duckduckgo for broad searches and falling back to web-claude for in-depth insights. The integration with cardnews and yt-digest skills helps turn search results into structured content plans.
Researchers can employ the skill to gather sources for papers, using web_search with search_lang parameters for localized data and web-claude for analyzing complex studies. The auto-cache in memory/research/ organizes findings for citation and further review.
Analysts can utilize the skill to track financial news and company data, prioritizing web_search for fast updates on market size and duckduckgo for privacy-focused searches. The tiered approach ensures data availability for making informed investment decisions.
Offer the skill as part of a subscription service for businesses needing reliable web search, with tiers based on API usage (e.g., Brave API access) and priority support. Revenue comes from monthly fees, leveraging the auto-fallback to ensure uptime and customer satisfaction.
Provide a free version with basic duckduckgo searches and limited cache, while charging for premium features like Brave API integration, advanced freshness controls, and enhanced web-claude automation. This model attracts users with no-cost access and upsells power users.
License the skill to large organizations for internal use, such as integrating with competitor-watch or cardnews skills for automated research workflows. Revenue is generated through one-time licensing fees or annual contracts, with customization options for specific industries.
š¬ Integration Tip
Integrate this skill with competitor-watch for automated monitoring and cardnews for content generation, using the auto-cache to streamline data flow between skills.
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations.
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.