Explains codebase architecture and subsystem flow through parallel explorer agents.
npx skills add https://github.com/gmackie/agent-skills --skill how-gmackie
Please help me install this Agent Skill. Skill: how Source: https://github.com/gmackie/agent-skills/tree/main/skills/how Command: npx skills add https://github.com/gmackie/agent-skills --skill how-gmackie
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, traces the call chain from entry point to output, and returns a structured explanation covering key concepts, flow, file locations, and gotchas.
Request a critique of a subsystem and the skill first explains the architecture, then spawns multiple independent model critics that evaluate it against a rubric covering abstraction fit, data model, boundaries, and evolution readiness.
No. All explorer, explainer, and critic subagents run in read-only mode, using Glob, Grep, and Read to inspect code without writing or changing any files.
Use explain mode for understanding questions like how a feature flows or where code lives. Use critique mode only when you explicitly want architectural problems, risks, or improvement opportunities identified.
Explorers may fail to trace dynamic or indirect connections, and the skill instructs them to report open questions honestly rather than guess. Very broad questions are decomposed into at most four exploration angles.
remorsesFetches and caches dependency source code from npm, PyPI, and crates.io for agent inspection.
karrioapiWrite Product Requirements Documents with ASCII diagrams before implementing features.
charly-vibesGenerate pull request descriptions from code diffs and commit history.
tanqiminInvestigates questions against primary sources and writes cited findings to Markdown files.
