| name | enterprise-search |
| description | Search and query enterprise JSON data to find specific information like employee IDs, document references, URLs, and insights. Use this skill when you need to locate answers to business questions such as finding authors of reports, team members with specific insights, or shared URLs. Handles multi-step queries, filtering, and deduplication of results. |
Enterprise Data Search Strategies
Finding Document Authors and Reviewers
Pattern: Search for document name + extract userId from messages mentioning it
grep -i "market research report\|market research" /root/DATA/products/ContentForce.json
grep -i "market research" /root/DATA/products/ContentForce.json | grep -o '"userId":"[^"]*"' | cut -d'"' -f4
Finding Team Members with Specific Insights
Pattern: Search for keywords related to competitor products or strengths/weaknesses
grep -i "competitor\|strengths\|weaknesses\|advantages\|disadvantages" /root/DATA/products/ContentForce.json
grep -i "competitor\|strengths\|weaknesses" /root/DATA/products/ContentForce.json | grep -o '"userId":"[^"]*"' | cut -d'"' -f4
Finding Shared URLs/Demo URLs
Pattern: Search for URLs, links, and demo references
grep -o 'https*://[^" |<]*' /root/DATA/products/ContentForce.json | sort -u
grep -i "demo\|url\|link" /root/DATA/products/ContentForce.json | grep -o 'https*://[^" |<]*'
Deduplication and Formatting
grep -o 'eid_[a-f0-9]*' file.json | sort -u
grep -o 'eid_[a-f0-9]*' file.json | sort -u | wc -l
Question Answering Workflow
- Parse the question - Identify key terms (report names, keywords, types)
- Search the product JSON - Use grep to find relevant messages
- Extract entities - Get userIds, URLs, or other requested information
- Deduplicate - Ensure unique results using
sort -u
- Format - Convert to the required output format (list of IDs/URLs)
Product Files Location
- Main data:
/root/DATA/products/
- Each product has a
.json file (e.g., ContentForce.json)
- Look for both primary product and competitor product files