skills.rest
indranilbanerjee
indranilbanerjeeCOMMUNITY
Explore all skills by this author →
Website𝕏@askneelnowGitHub

search-knowledge

Search brand knowledge across vector, graph, and local memories with filters.

726|123|Updated Feb 11, 2026
Search Tags:#provenance#knowledge-graph#semantic-search#memory-management#vector-database#brand-knowledge
One-click install
npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill search-knowledge-indranilbanerjee
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: search-knowledge
Source: https://github.com/indranilbanerjee/digital-marketing-pro/tree/main/skills/search-knowledge
Command: npx skills add https://github.com/indranilbanerjee/digital-marketing-pro --skill search-knowledge-indranilbanerjee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Semantic search across brand knowledge stores is slow and brittle, making it hard to recall past learnings, voice guidelines, or competitor insights when needed. This skill centralizes retrieval across memory layers to deliver fast, provenance-rich results.

Core Features & Use Cases

  • Semantic search across vector DB, knowledge graph, and local index to surface relevant brand entries.
  • Apply content-type, date-range, tag, and priority filters to refine results.
  • Present results with provenance, entity relationships, and temporal context to support decision making.

Quick Start

Find recent, high-priority brand learnings and guidelines across memory layers.

Frequently Asked Questions about search-knowledge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform semantic search across multiple brand knowledge stores?▼

You can refine semantic search results by applying filters for content type, date range, tags, and priority across connected memory layers to isolate specific brand learnings and guidelines.

How does provenance work when retrieving brand knowledge from a knowledge graph?▼

Provenance is maintained by returning ranked search results with full entity relationships and temporal context from the knowledge graph, ensuring transparent tracking of brand learnings and competitive insights.

Can I retrieve high-priority brand guidelines across different memory layers?▼

Retrieving high-priority brand guidelines across memory layers is supported by applying priority and content-type filters during semantic search to quickly surface critical brand voice and competitor insights.

Why is semantic search for brand knowledge slow and brittle across separate memory stores?▼

Semantic search becomes slow and brittle when memory stores are isolated, making it hard to recall past learnings; centralizing retrieval across vector, graph, and local memories solves this by delivering fast, provenance-rich results.

What is the best way to consolidate competitive insights from a vector database and knowledge graph?▼

The best way to consolidate competitive insights is to run semantic search across both vector database and knowledge graph layers, utilizing date-range and tag filters to return ranked results with full provenance for decision making.

Related Skills

Explore More Data & Analytics Skills→
ajayatwal1105-emersonajayatwal1105-emerson

save-knowledge

Save brand knowledge into semantic memory with deduplication and metadata.

Community
Intermediate
michaelboedingmichaelboeding
24

competitive-intel-agent

Analyze competitors with four agents to generate structured intelligence reports.

Community
Advanced
48Nauts-Operator48Nauts-Operator
3

hybrid-search-implementation

Implement hybrid search combining vector similarity with BM25 ranking.

Community
Advanced
SyntaxAsSpiralSyntaxAsSpiral
5

memory-systems

Persist AI agent context across sessions with vector stores and temporal knowledge graphs.

Community
Advanced