Generates architectural explanations of codebases by orchestrating parallel read-only explorer and explainer subagents.
npx skills add https://github.com/imjasonh/playground --skill how-imjasonh
Please help me install this Agent Skill. Skill: how Source: https://github.com/imjasonh/playground/tree/main/.cursor/skills/how Command: npx skills add https://github.com/imjasonh/playground --skill how-imjasonh
High-intent search queries and answers about installing and using this skill.
Ask a how-does-X-work question and the Skill explores the code, tracing entry points, call chains, and key abstractions. It returns a structured explanation with an overview, flow walkthrough, file map, and gotchas.
Simple questions about a single module or function go to one explainer subagent in a single pass. Complex questions spanning multiple files or services are decomposed into 2-4 angles explored by parallel subagents, then synthesized.
No. All explorer and explainer subagents run with read-only access, using Read, Grep, and Glob to inspect the codebase. They gather facts and write explanations without changing any files.
Explanations use sections for Overview, Key Concepts, How It Works, Where Things Live, and Gotchas, dropping any that do not apply. Diagrams in mermaid or ASCII are included when they clarify multi-component flows.
Use it when you need a working mental model of a subsystem before changing code, or when deciding where new logic should live. It is not a substitute for reading exact implementations when making precise edits.
agentpatternsCoordinate parallel codebase exploration and web research into a compact artifact.
rogerzntsExplains codebase architecture and critiques subsystem design using parallel explorer agents.
mmdmcyInvestigate design rationale behind code by querying seven evidence sources in parallel.
vickysrawatAnswers codebase questions from architecture docs and the knowledge graph without scanning source.
