research

Automate feature research and generate hermetic context documents.

4|Updated Mar 23, 2025
One-click install
npx skills add https://github.com/matochu/pythia --skill research-matochu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/matochu/pythia/tree/main/.agents/skills/research
Command: npx skills add https://github.com/matochu/pythia --skill research-matochu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables scalable, hermetic feature research by combining a pre-search across scattered project documents with comprehensive multi-source investigation, then synthesizing the findings into a context document that guides planning and design.

Core Features & Use Cases

  • Pre-search across pythia project documents to ground research and avoid duplication.
  • Multi-source analysis (web, codebase, third-party references) to identify options, best practices, and trade-offs.
  • Produce a hermetic feature context document at feat-XXX/contexts/{topic}.context.md with architectural notes, recommended direction, and an explicit plan for future work.
  • Update Related Contexts to maintain traceability of decisions and dependencies across features.

Quick Start

Invoke the /research command with a topic to generate a feature context document.

Frequently Asked Questions about research

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

FAQPage Schema
How do I automate feature research and generate a context document?

Automated feature research uses pre-search across project documents and multi-source investigation to synthesize a hermetic context document at feat-XXX/contexts/{topic}.context.md. It identifies options, best practices, and trade-offs to guide planning and design.

What is a feature context document and when do I need one?

A feature context document is a hermetic research file containing architectural notes, recommended directions, and third-party findings. You need one when starting feature planning to ground design decisions in comprehensive, traceable research.

How do I avoid duplicating research across scattered project documents?

To avoid duplicating research, run a pre-search across existing project documents before broadening the investigation. This grounds the feature context in current findings and maintains traceability of decisions by updating related contexts.

Can I use feature research for multi-source analysis including web and codebase references?

Feature research supports multi-source analysis across the web, codebase, and third-party references. It synthesizes these sources to identify architectural options, best practices, and trade-offs, producing a comprehensive context document for your workspace.

What's the best way to maintain traceability of decisions across multiple features?

The best way to maintain traceability is to update related contexts after generating each feature context document. This preserves the dependency mapping and decision history across scattered feature research within the workspace.

Does feature research work without external dependencies?

Feature research operates without external dependencies, relying solely on project documents and multi-source investigation. It synthesizes findings into a context file with architectural notes, recommended direction, and an explicit plan for future work.