Generates architectural explanations of codebases using parallel explorer and explainer subagents.
npx skills add https://github.com/edivad1999/stuc-stack --skill how-edivad1999
Please help me install this Agent Skill. Skill: how Source: https://github.com/edivad1999/stuc-stack/tree/main/skills/how Command: npx skills add https://github.com/edivad1999/stuc-stack --skill how-edivad1999
High-intent search queries and answers about installing and using this skill.
Ask a how-does-X-work question and the Skill assesses complexity, then either explains directly or spawns parallel read-only explorer agents. Their findings are synthesized into a structured explanation covering flow, key concepts, and file locations.
Simple questions about a single module or function go to one explainer subagent in a single pass. Complex questions spanning multiple files or services trigger 2-4 parallel explorers whose findings a synthesizer merges into one explanation.
No. All explorer and explainer subagents run with readonly set to true, using only Read, Grep, and Glob. They gather facts and trace code paths without making any changes to the codebase.
Explanations use Overview, Key Concepts, How It Works, Where Things Live, and Gotchas sections, dropping any that do not apply. Diagrams in mermaid or ASCII are included when the flow involves multiple interacting components.
Use this Skill for mechanism questions: how something works, where code should live, and which layer owns logic. For motivation and rationale behind a design decision, the documentation directs you to the separate why skill.
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.
TokenRollAIInvestigate codebase questions using llmdoc documentation and report findings.
