skills.rest
jamieadams-nerd
jamieadams-nerdCOMMUNITY
Explore all skills by this author →
GitHub

rag-query

Perform semantic search over the UMRS reference library with JSON output.

Updated Dec 4, 2025
Search Tags:#python#rag#search#grounding#collections#semantic-search#reference-library
One-click install
npx skills add https://github.com/jamieadams-nerd/umrs-project --skill rag-query-jamieadams-nerd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-query
Source: https://github.com/jamieadams-nerd/umrs-project/tree/main/.claude/skills/rag-query
Command: npx skills add https://github.com/jamieadams-nerd/umrs-project --skill rag-query-jamieadams-nerd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Searches the UMRS reference library using semantic search. Trigger this skill whenever any agent — rust-developer, security-engineer, tech-writer, security-auditor, or others — is working on topics related to SELinux, MLS policy, Linux kernel internals, filesystem standards, IMA, dm-crypt, Linux capabilities, extended attributes, CUI handling, or any topic likely covered by the reference library. Also trigger when the user asks to "search the references", "look up X in the RAG", or when answering a technical question would benefit from grounding in authoritative source material.

Core Features & Use Cases

  • Semantic search over the UMRS reference library via the query.py script.
  • Supports searching across all collections, a specific collection, or multiple collections.
  • Control the number of results and output format (including JSON) for programmatic processing.

Quick Start

Run a query with python .claude/rag/query.py "your query" to retrieve semantically relevant results from the UMRS reference library.

Frequently Asked Questions about rag-query

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

FAQPage Schema
How do I search a reference library for grounded information on SELinux and Linux kernel internals?▼

Semantic search over a reference library surfaces grounded information on SELinux, Linux kernel internals, and filesystem standards by running a Python query script. You retrieve semantically relevant results from authoritative source material without manual browsing.

Can I target specific collections when doing a semantic search?▼

Semantic search supports targeting all collections, a specific collection, or multiple collections simultaneously. You execute a Python query with optional collection parameters to narrow results to relevant reference library sections.

How do I control the number of search results and get JSON output for programmatic processing?▼

The Python query interface provides top-k control to limit returned results and offers JSON output format. You configure these parameters when running the query script to obtain structured data for downstream programmatic processing.

What technical topics are covered by the UMRS reference library for semantic search?▼

The reference library covers SELinux, MLS policy, Linux kernel internals, filesystem standards, IMA, dm-crypt, Linux capabilities, extended attributes, and CUI handling. Semantic search retrieves authoritative results across these security and system-level topics.

Does the semantic search query tool require any external dependencies?▼

The Python-based semantic search query tool operates with no external dependencies. You run the standalone query script directly against the reference library without installing additional packages or frameworks.

When should I trigger a reference library search instead of answering from general knowledge?▼

Trigger a reference library search when answering technical questions about SELinux, dm-crypt, IMA, or CUI handling that benefit from grounding in authoritative source material. Use it when users ask to search references or look up information in the RAG system.

Related Skills

Explore More Data & Analytics Skills→
patricio0312revpatricio0312rev
5

vector-db-setup

Configure Pinecone, Chroma, pgvector, and Qdrant vector databases for semantic search.

Community
Advanced
InternScienceInternScience
52

gjf-to-xyz

Parse Gaussian gjf input files and convert them to XYZ format.

Official
Intermediate
lorenzogmlorenzogm
15

bmad-agent-tech-writer

Generate technical documentation, Mermaid diagrams, and explanations of complex concepts.

Community
Advanced
overviewlabsoverviewlabs

qmd

Search local Markdown collections with hybrid keyword and vector retrieval.

Community
Advanced