Corpus Triage

Classify raw project files into organized categories within an inbox directory.

6|3|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/carson-sweet/sweetclaude --skill corpus-triage
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Corpus Triage
Source: https://github.com/carson-sweet/sweetclaude/tree/main/skills/corpus-triage
Command: npx skills add https://github.com/carson-sweet/sweetclaude --skill corpus-triage

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill solves the problem of disorganized project data by providing a structured, batch-oriented workflow to classify raw files into actionable categories like keep, reconcile, discard, or defer.

Core Features & Use Cases

  • Batch Classification: Rapidly process large volumes of files using group-based or individual triage modes.
  • Pipeline Integration: Ensures data integrity by enforcing a strict consolidation-first workflow and maintaining project state.
  • Use Case: Use this when you have imported a large, messy dump of research documents or legacy code and need to systematically clean, archive, or prepare them for reconciliation without manual file-by-file management.

Quick Start

Run the corpus triage skill to begin classifying the files currently sitting in your inbox.

Frequently Asked Questions about Corpus Triage

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

FAQPage Schema
How do I classify and organize a large dump of messy project files?

To classify and organize messy project files, batch processing workflows sort raw data from an inbox directory into actionable categories like keep, reconcile, discard, or defer to streamline data preparation.

What is the best way to automate file triage for legacy code and research documents?

Automated file triage for legacy code and research documents uses group-based or individual modes to systematically clean and archive raw files, preventing manual file-by-file management.

Do I need a pre-initialized project state to batch classify raw data?

Yes, batch classifying raw data requires a pre-initialized project state and strict adherence to a defined pipeline gate to ensure data consistency and enforce a consolidation-first workflow.

Can I process large volumes of files in groups rather than individually?

Yes, you can process large volumes of files using group-based triage modes, enabling rapid batch decision-making for organizing and archiving collections within a defined inbox directory.

When should I not use an automated file triage workflow?

You should avoid automated file triage workflows when your project lacks a pre-initialized state or defined pipeline gate, as skipping the consolidation-first workflow breaks data integrity.