Generates architectural explanations of how codebases work using parallel explorer subagents.
npx skills add https://github.com/rockcookies/skills --skill how-rockcookies
Please help me install this Agent Skill. Skill: how Source: https://github.com/rockcookies/skills/tree/main/skills/cursor-plugins/how Command: npx skills add https://github.com/rockcookies/skills --skill how-rockcookies
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, tracing entry points, call chains, and key abstractions. Complex questions spawn parallel explorer agents whose findings are synthesized into one structured explanation.
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 trigger 2 to 4 parallel explorers, then a synthesis step that reconciles their findings.
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 flows involve multiple interacting components.
No. All explorer and explainer subagents run in read-only mode using Read, Grep, and Glob. They gather facts and write explanations without changing any files.
Use it when onboarding onto an unfamiliar subsystem, before changing code you do not own, or when deciding where new logic should live. It is less useful for single-line questions answerable by reading one function directly.
agentpatternsCoordinate parallel codebase exploration and web research into a compact artifact.
monktuiRoute multi-agent git-review tasks through role and model tier pipelines.
eugenelimReconstruct past decision rationale from time-ordered artifacts.
leynosLocate symbol definitions, references, and call relationships using LSP-powered analysis.
