how

Generates architectural explanations of codebases by tracing subsystems with parallel explorer agents.

Updated Sep 23, 2026
One-click install
npx skills add https://github.com/lucasheriques/pstack --skill how-lucasheriques
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: how
Source: https://github.com/lucasheriques/pstack/tree/main/skills/how
Command: npx skills add https://github.com/lucasheriques/pstack --skill how-lucasheriques

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Engineers often need to understand how an unfamiliar subsystem works before changing it, but manually tracing code paths across many files is slow and error-prone. This Skill answers "how does X work" questions by exploring the codebase and producing a senior-engineer-level architectural explanation. ## Core Features & Use Cases - Complexity Assessment: Routes simple questions to a single-pass explainer and complex subsystem questions to parallel explorer agents followed by a synthesis pass. - Structured Explanations: Produces explanations with Overview, Key Concepts, How It Works, Where Things Live, and Gotchas sections, including mermaid or ASCII diagrams when flows involve multiple components. - Placement and Layering Questions: Answers "where should this live", "which package owns this", and "is this the right layer" questions in addition to walkthroughs. - Use Case: Before modifying a sync engine spanning several services, ask how it works and receive a mental model covering entry points, data flow, key abstractions, and non-obvious pitfalls. ## Quick Start Ask how the authentication flow in this repository works from login request to session creation.

Frequently Asked Questions about how

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

FAQPage Schema
How do I get a walkthrough of how a subsystem works in a codebase?▼

Ask a "how does X work" question and the Skill explores the codebase, tracing entry points, call chains, and key abstractions. Complex subsystems are split into exploration angles handled by parallel agents, then synthesized into one structured explanation.

How does the Skill handle simple versus complex code questions?▼

Simple questions about a single module or function are answered by one explainer agent in a single pass. Complex questions spanning multiple files or services spawn 2 to 4 parallel explorer agents whose findings are merged by a synthesizing explainer.

Can it answer where new code should live or which package owns a feature?▼

Yes, placement, ownership, and layering questions are in scope alongside walkthroughs. It explains subsystem architecture and runtime flow so you can decide the right layer or package for a change.

What is the difference between the how and why skills?▼

The how skill explains architecture and runtime flow of existing code, while the why skill investigates motivation behind design decisions using external sources. Use how for mental models and why for rationale.

What format does the architectural explanation output use?▼

Explanations use sections for Overview, Key Concepts, How It Works, Where Things Live, and Gotchas, dropping any that do not apply. Multi-component flows may include mermaid diagrams or ASCII art when they clarify the explanation.