Explains codebase architecture and subsystem flows through parallel explorer agents and optional multi-model critique.
npx skills add https://github.com/jnyross/pstack-muse --skill how-jnyross
Please help me install this Agent Skill. Skill: how Source: https://github.com/jnyross/pstack-muse/tree/main/skills/how Command: npx skills add https://github.com/jnyross/pstack-muse --skill how-jnyross
High-intent search queries and answers about installing and using this skill.
Ask a "how does X work" question and the skill explores the codebase, traces the flow from entry point to output, and returns a structured explanation covering key concepts, step-by-step flow, file locations, and gotchas.
Simple questions about a single module are answered by one agent that explores and explains in a single pass. Complex subsystem questions are split into 2-4 parallel explorer agents whose findings a separate explainer synthesizes.
Yes. Critique mode first produces the full explanation, then spawns one critic per configured model that reviews the actual code against a rubric covering abstraction fit, data model, boundaries, and evolution readiness.
It targets how and where questions about architecture and runtime flow, not motivation. For why a decision was made, the documentation directs you to the separate why skill instead.
No. All explorer, explainer, and critic subagents run in read-only mode. They use Glob, Grep, and Read to inspect the code and return findings without making any changes.
linkerdogGenerate a subsystem-aligned repository map with file-by-file reading paths.
tktafAnalyzes and explains code execution paths and data flow in a software project.
mmdmcyInvestigate design rationale behind code by querying seven evidence sources in parallel.
JylhisQuery Emacs help, Info manuals, and source via batch evaluation.
