skills.rest
winsorllc
winsorllcCOMMUNITY
Explore all skills by this author →
GitHub

document-indexer

Index text documents into a JSONL file with full-text search and keyword extraction.

1|Updated Feb 25, 2026
Search Tags:#indexing#information retrieval#search#text processing#document management#keyword extraction
One-click install
npx skills add https://github.com/winsorllc/upgraded-carnival --skill document-indexer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: document-indexer
Source: https://github.com/winsorllc/upgraded-carnival/tree/main/.pi/skills/document-indexer
Command: npx skills add https://github.com/winsorllc/upgraded-carnival --skill document-indexer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of efficiently organizing, searching, and retrieving information from a collection of documents, making it difficult to find specific content quickly.

Core Features & Use Cases

  • Document Indexing: Ingests text files and documents, creating a searchable index.
  • Full-Text Search: Enables powerful searching across the content of indexed documents.
  • Keyword Extraction & Categorization: Automatically identifies key terms and assigns categories for better organization.
  • Use Case: Quickly find all documents related to "project alpha" that were categorized as "technical specifications" by searching for the keywords.

Quick Start

Use the document-indexer skill to add the file '/path/to/report.txt' to the index under the 'reports' category.

Frequently Asked Questions about document-indexer

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

FAQPage Schema
How do I index text documents for full-text search and keyword extraction?▼

Full-text search works by scanning a JSONL-based index built from your ingested text files, matching your query against stored content, and returning documents categorized by extracted keywords.

How does full-text search work across indexed text files?▼

Full-text search works by scanning a JSONL-based index built from your ingested text files, matching your query against stored content, and returning documents categorized by extracted keywords.

Can I categorize and search text documents using a JSONL index?▼

Yes, you can categorize and search text documents using a JSONL index by adding files under specific categories, enabling filtered full-text search across your organized document collection.

What is the best way to manage and retrieve keywords from a collection of text files?▼

The best way to manage and retrieve keywords is to add text files to a centralized index, which utilizes basic text processing to generate searchable keywords and assign document categories.

How do I add, list, and remove documents from a JSONL document index?▼

You add, list, and remove documents from a JSONL document index by using supported index management commands, utilizing MD5 hashing to uniquely identify and manage each text document.

Related Skills

Explore More Software Engineering Skills→
esopianesopian
2

learn

Review, search, prune, and export stored project learnings from JSONL files.

Community
Basic
hairihouhairihou

extract-pdf-text

Extract text from PDF files via pdfplumber with optional page selection.

Community
Intermediate
dkyazzentwatwadkyazzentwatwa
86

topic-modeler

Extract latent topics from text collections using Latent Dirichlet Allocation.

Community
Intermediate
sorodriguezzsorodriguezz

Using Document Database (DocDB)

Create, manage, and query JSON documents in InterSystems IRIS DocDB.

Community
Intermediate