Generates architectural explanations of codebases by orchestrating parallel explorer and explainer subagents.
npx skills add https://github.com/Shtian/AuthentiClash --skill how-shtian
Please help me install this Agent Skill. Skill: how Source: https://github.com/Shtian/AuthentiClash/tree/main/.claude/skills/how Command: npx skills add https://github.com/Shtian/AuthentiClash --skill how-shtian
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. It returns a structured explanation with an overview, flow walkthrough, file map, and gotchas referencing exact files and functions.
Simple questions about a single module or function are explored and explained in one pass by a single subagent. Complex questions spanning multiple files are decomposed into 2-4 angles investigated by parallel explorer subagents, then synthesized into one explanation.
Yes, the skill covers placement, ownership, and layering questions such as "where should this live" or "which package owns this". It explains subsystem architecture and boundaries so you can judge the right layer for new logic.
No, all explorer and explainer subagents are explicitly instructed not to modify files. They use read-only operations like Read, Grep, and Glob to trace code paths and gather findings.
Explorers report gaps explicitly in an Open Questions section rather than guessing. The explainer acknowledges these unresolved areas in the final explanation instead of hiding them.
InverterNetworkIndex source code into a knowledge graph for visual exploration.
rogerzntsExplains codebase architecture and critiques subsystem design using parallel explorer agents.
tvishwanadhaCentralize Architecture Decision Records with superseding and amending workflows.
eatbreadsGenerate layered PlainUML sequence diagrams and key-function tables for IDE-based source reading.
