Document Corpus

Consolidate, clean, and index project documentation into a searchable canonical corpus.

6|3|Updated Apr 12, 2026

Search Tags:#documentation #indexing #knowledge management #rag #search #pipeline

Ready to run

npx skills add https://github.com/carson-sweet/sweetclaude --skill document-corpus

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Document Corpus
Source: https://github.com/carson-sweet/sweetclaude/tree/main/skills/document-corpus
Command: npx skills add https://github.com/carson-sweet/sweetclaude --skill document-corpus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of fragmented, unorganized project documentation by providing a structured pipeline to consolidate, triage, and index files into a reliable, searchable canonical corpus.

Core Features & Use Cases

Pipeline Management: Orchestrates the full lifecycle of documentation from raw inbox files to indexed canonical records.
Semantic Search (RAG) Integration: Automatically builds and maintains a vector index for intelligent project-wide search.
Use Case: Use this to turn a chaotic folder of meeting notes, design drafts, and research PDFs into a single, authoritative source of truth that the AI can query to answer complex project questions.

Quick Start

Run the document corpus skill to initialize the project structure and begin importing your documents.

Frequently Asked Questions about Document Corpus

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

FAQPage Schema

How do I consolidate fragmented project documentation into a searchable knowledge base?▼

To consolidate fragmented project documentation into a searchable knowledge base, this skill provides a structured pipeline to triage, reconcile, and index raw files into a unified canonical corpus. It manages the end-to-end lifecycle from inbox files to canonical records.

How does RAG indexing work for unorganized project files?▼

RAG indexing for unorganized project files works by automatically building and maintaining a semantic vector index from the reconciled canonical corpus. This allows the AI to intelligently query project-wide documentation to answer complex questions.

What is the best way to manage the lifecycle of raw documentation files?▼

The best way to manage the lifecycle of raw documentation files is through an orchestrated pipeline that tracks state from initial triage through semantic indexing. This ensures document integrity and search accuracy throughout the transformation.

Do I need a structured directory environment to index project documentation?▼

Yes, you need a structured directory environment and state tracking to index project documentation effectively. These prerequisites are required to ensure proper file triage, document reconciliation, and accurate semantic search results.

Can I turn a chaotic folder of meeting notes and research PDFs into a single source of truth?▼

Yes, you can turn a chaotic folder of meeting notes and research PDFs into a single source of truth by running the document corpus skill. It consolidates and cleans raw files into an authoritative canonical corpus for AI queries.