how

Generates architectural explanations of codebases by orchestrating parallel explorer and explainer subagents.

1|Updated Sep 13, 2026
One-click install
npx skills add https://github.com/silentFellow/public-dotfiles --skill how-silentfellow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: how
Source: https://github.com/silentFellow/public-dotfiles/tree/main/agents/skills/how
Command: npx skills add https://github.com/silentFellow/public-dotfiles --skill how-silentfellow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Understanding how an unfamiliar subsystem works requires tracing code paths across many files, which is slow and error-prone when done manually. This Skill answers "how does X work" questions by exploring the codebase and producing a senior-engineer-level architectural explanation. ## Core Features & Use Cases - Adaptive Exploration Strategy: Routes simple questions to a single explainer pass and complex subsystem questions to 2-4 parallel read-only explorer agents followed by a synthesis step. - Structured Explanations: Produces consistent output sections (Overview, Key Concepts, How It Works, Where Things Live, Gotchas) with optional mermaid or ASCII diagrams. - Placement and Ownership Guidance: Answers layering questions like "where should this live" and "which package owns this" alongside runtime flow walkthroughs. - Use Case: Before modifying a payment processing pipeline, ask how it works and receive a mental model covering entry points, data flow, key abstractions, and non-obvious pitfalls. ## Quick Start Ask the agent to explain how a specific subsystem or feature in this repository works before making changes to it.

Frequently Asked Questions about how

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

FAQPage Schema
How do I get an explanation of how a codebase subsystem works?▼

Ask a "how does X work" question and the Skill explores the codebase, then returns a structured explanation with Overview, Key Concepts, How It Works, Where Things Live, and Gotchas sections. Complex questions trigger parallel explorer agents whose findings are synthesized.

How does the Skill decide between simple and complex exploration?▼

Simple questions about a single module or narrow function go to one explainer agent in a single pass. Complex questions spanning multiple files or services spawn 2 to 4 parallel explorer agents first, then a synthesizer merges their findings.

Can it answer where new code should live in a project?▼

Yes, it handles placement, ownership, and layering questions such as "where should this live" or "which package owns this" by mapping subsystem boundaries and explaining the existing architecture before you add to it.

Does the exploration modify any files in the repository?▼

No, all explorer and explainer subagents run in read-only mode using Read, Grep, and Glob. The Skill only reads code to build the explanation and never writes or changes files.

What are the limitations of automated codebase exploration?▼

Explorers may fail to trace dynamic or indirect connections, and the Skill instructs them to state gaps explicitly as open questions rather than guess. Explanations reflect the code as written, not intended design or runtime-only behavior.