skills.rest
winstonkoh87
winstonkoh87COMMUNITY
Explore all skills by this author →
WebsiteGitHub

semantic-search

Index and retrieve exact Exocortex embeddings from internal libraries via smart_search.py.

558|75|Updated Dec 18, 2025
Search Tags:#embeddings#rag#semantic-search#knowledge-base#internal-library
One-click install
npx skills add https://github.com/winstonkoh87/Athena-Public --skill semantic-search-winstonkoh87
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: semantic-search
Source: https://github.com/winstonkoh87/Athena-Public/tree/main/examples/skills/research/semantic-search
Command: npx skills add https://github.com/winstonkoh87/Athena-Public --skill semantic-search-winstonkoh87

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Exocortex Semantic Engine provides fast, exact lookup of internal embeddings to easily retrieve relevant information from private libraries, enabling precise context for reasoning tasks.

Core Features & Use Cases

  • Exact embeddings lookup for internal libraries.
  • Wraps the smart_search.py wrapper to perform fast local searches.
  • Use Case: retrieve top-matching documents to answer internal queries with high fidelity and speed.

Quick Start

Run a search query to retrieve relevant internal documents and embed results for context.

Frequently Asked Questions about semantic-search

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

FAQPage Schema
How do I retrieve internal knowledge base documents using semantic search?▼

You can retrieve internal knowledge base documents by running a semantic search query to find top-matching embeddings. The Skill wraps the local smart_search.py wrapper to perform exact lookups and returns the top 5 results.

Can I use local embeddings for context augmentation in my reasoning tasks?▼

Yes, local embeddings are explicitly designed for context augmentation. The tool retrieves precise document matches from internal libraries, providing Markdown-ready results suitable for loading context into reasoning tasks.

Do I need external dependencies to perform exact embeddings lookup?▼

No external dependencies are required to perform exact embeddings lookup. The Skill operates entirely on the local smart_search.py wrapper to index and retrieve data from your internal libraries.

How many documents does the semantic search return for context loading?▼

The semantic search returns a maximum of 5 top-matching documents per query. This limit parameter ensures fast, precise context loading from your internal libraries.

What is the best way to search private libraries for precise document retrieval?▼

The best way to search private libraries is using exact embeddings lookup. This approach indexes internal libraries and retrieves Markdown-ready results quickly, enabling high-fidelity document retrieval for internal queries.

Are there limitations to using local semantic search for internal knowledge bases?▼

A limitation of local semantic search is the fixed result limit of 5 documents per query. It relies on the local smart_search.py wrapper, meaning lookups are bound to your existing internal library scope.

Related Skills

Explore More Software Engineering Skills→
shinnytechshinnytech

Remembering Conversations

Index and search historical Claude Code conversations with semantic and exact text matching.

Official
Advanced
mahg-esmahg-es
3

rag-pipeline

Implement end-to-end RAG pipelines with chunking, embeddings, and hybrid search.

Official
Advanced
stephanjstephanj
9

rag-architect

Architect RAG systems integrating vector databases, embedding models, and retrieval pipelines.

Community
Advanced
FalkorDBFalkorDB
22

Create and query vector indexes

Create and query HNSW vector indexes in FalkorDB graph databases.

Official
Intermediate