he-research

Run parallel research across documentation, codebase patterns, and external references.

4|1|Updated Feb 14, 2026
One-click install
npx skills add https://github.com/mattjefferson/harness-engineering --skill he-research
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: he-research
Source: https://github.com/mattjefferson/harness-engineering/tree/main/skills/he-research
Command: npx skills add https://github.com/mattjefferson/harness-engineering --skill he-research

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the uncertainty and open questions that arise before detailed planning, ensuring that decisions are based on evidence rather than assumptions.

Core Features & Use Cases

  • Investigates Open Questions: Runs parallel research across documentation, codebase patterns, and external references.
  • Updates Initiative Artifacts: Integrates findings directly into specification documents, providing evidence-backed insights.
  • Use Case: After defining a new feature's high-level requirements, use he-research to investigate potential technical constraints, existing similar solutions, and clarify ambiguous aspects of the requirements before committing to a detailed implementation plan.

Quick Start

Use the he-research skill to investigate open questions for the 'user-authentication' initiative.

Frequently Asked Questions about he-research

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

FAQPage Schema
How do I investigate open questions before planning a software feature?

To investigate open questions before planning, run parallel research across documentation, codebase patterns, and external references to categorize questions, prioritize primary sources, and gather evidence-backed findings that clarify ambiguous requirements.

What is evidence-based requirements gathering for technical specifications?

Evidence-based requirements gathering for technical specifications is the process of distinguishing fact from inference by researching documentation and codebase patterns, ensuring your software scope, requirements, and risks are informed by verified findings rather than assumptions.

How do I research codebase patterns and external references in parallel?

You research codebase patterns and external references in parallel by categorizing open questions and prioritizing primary sources across multiple documentation streams simultaneously, then updating your initiative artifacts with the evidence-backed results.

When do I need to research technical constraints before writing an implementation plan?

You need to research technical constraints before writing an implementation plan when you have high-level feature requirements but face uncertainty, ensuring you uncover existing solutions and clarify ambiguous aspects before committing to a detailed scope.

Does this approach to requirements gathering work without external dependencies?

Yes, this evidence-based research approach operates without external dependencies, allowing you to investigate open questions and update specification documents directly using your existing codebase patterns and internal documentation.

What is the best way to distinguish fact from inference during software investigation?

The best way to distinguish fact from inference during software investigation is to prioritize primary sources across documentation and codebase patterns, categorizing your research findings to ensure specification artifacts contain only evidence-backed insights.