skills.rest
chenchunrun
chenchunrunCOMMUNITY
Explore all skills by this author →
GitHub

rga-knowledge-search

Query the ripgrep-all cache to locate relevant information across local documents.

1|1|Updated Apr 25, 2026
Search Tags:#documents#citations#cache#local-docs#text-extraction#knowledge-search#rga
One-click install
npx skills add https://github.com/chenchunrun/onyx-soc --skill rga-knowledge-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rga-knowledge-search
Source: https://github.com/chenchunrun/onyx-soc/tree/main/skills/rga-knowledge-search
Command: npx skills add https://github.com/chenchunrun/onyx-soc --skill rga-knowledge-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires zstandard, pdfplumber, python-docx, openpyxl, python-pptx, ebooklib, chardet.

What problem does it solve?

Locating precise information across scattered local documents can be time-consuming and error-prone. This Skill uses the ripgrep-all cache to search text quickly across PDFs, Word, EPUB, and archive formats, providing fast, source-backed results.

Core Features & Use Cases

  • Local knowledge search: query across PDFs, Office documents, ebooks, and archives using cached text.
  • Source-backed results: each fact references specific file paths and line ranges to ensure traceability.
  • Fallback to live view: if the cache is missing, it can fall back to on-demand document viewing for deeper inspection.
  • Typical use: summarize internal reports or archival materials by extracting precise passages around a query.

Quick Start

Ask it to search the local knowledge base for a topic and return the most relevant passages with citations.

Frequently Asked Questions about rga-knowledge-search

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

FAQPage Schema
How do I search text across multiple local PDFs and Office documents?▼

You can search local documents by querying the ripgrep-all cache to locate matching text across PDFs, Office formats, and ebooks, receiving results with specific file paths and line ranges for traceability.

What is the best way to find specific passages in archived historical documents?▼

Finding specific passages in archived historical documents is handled by searching the cached text and extracting contextual slices around your keywords, with page- and line-based navigation for precise retrieval.

Can I search inside local EPUB and Office files without extracting text manually?▼

Yes, you can search inside local EPUB and Office files without manual text extraction because the Skill reads directly from the ripgrep-all cache to provide fast, source-backed results across supported formats.

How does cached document search handle files that are missing from the cache?▼

Cached document search handles missing cache entries by falling back to on-demand live document viewing, allowing deeper inspection of the original file when cached text is unavailable.

What do I need to set up before querying my local knowledge base for internal reports?▼

Before querying your local knowledge base for internal reports, you need local documents in formats like PDF, Office, or EPUB, and a generated ripgrep-all cache so the Skill can search and return cited passages.

Related Skills

Explore More Education & Research Skills→
rickyanandarickyananda
1

ocr-and-documents

Extract text from PDFs, scans, and office documents into markdown.

Community
Advanced
Fancu1Fancu1

notion-research-documentation

Synthesize Notion pages into structured documents with citations.

Community
Intermediate
quiznatquiznat

ocr-and-documents

Extract text from PDFs and scanned documents using pymupdf and marker-pdf.

Community
Intermediate
cdeistopenedcdeistopened
2

local-markdown-search

Index and search local Markdown collections with BM25 and vector embeddings.

Community
Intermediate