Search Strategy
技能 活跃Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.
To efficiently and accurately retrieve information from diverse enterprise data sources by intelligently decomposing and orchestrating search queries.
功能
- Natural language query decomposition
- Multi-source search orchestration
- Source-specific query translation
- Result ranking and synthesis
- Ambiguity handling and fallback strategies
使用场景
- Finding specific decisions or information across chat, documents, and project trackers
- Getting status updates on projects by querying multiple systems simultaneously
- Researching topics by broad searches across all connected knowledge bases
- Clarifying ambiguous information needs by asking targeted follow-up questions
非目标
- Performing actions or making changes in connected systems
- Replacing direct access to individual data sources
- Providing definitive answers without synthesizing results from multiple sources
Trust
- warning:Issues AttentionIn the last 90 days, 29 issues were opened and 4 were closed, indicating a low closure rate and potentially slow maintainer response.
安装
请先添加 Marketplace
/plugin marketplace add anthropics/knowledge-work-plugins/plugin install enterprise-search@knowledge-work-plugins质量评分
类似扩展
External Context
100Invoke parallel document-specialist agents for external web searches and documentation lookup
Web Search
100用于网络搜索。返回带有摘要、URL和缩略图的排名结果。支持新鲜度过滤、SafeSearch、用于自定义排名的Goggles以及分页。主搜索端点。
Agentdb Query
99Query AgentDB through the controller bridge -- semantic routing, hierarchical recall, causal graphs, context synthesis, pattern store/search
Flow Nexus Platform
100Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges
Agent Worker Specialist
100Agent skill for worker-specialist - invoke with $agent-worker-specialist
Do In Parallel
100Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection, quality-focused prompting, and meta-judge → LLM-as-a-judge verification