One-click install
npx skills add https://github.com/azigler/dotfiles --skill grok-azigler
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: /grok
Source: https://github.com/azigler/dotfiles/tree/main/agents/skills/grok
Command: npx skills add https://github.com/azigler/dotfiles --skill grok-azigler

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you rapidly understand an unfamiliar part of a codebase through a read-only walkthrough, so you can make informed edits without guessing or repeating earlier discoveries.

Core Features & Use Cases

  • Read-only code investigation: Gathers relevant entry points and walks the most important layers (documentation, entry points, core data model, hot paths, and tests).
  • Question-driven scoping: Turns vague “tell me about this” requests into a narrow, actionable investigation plan.
  • Navigation-ready results: Produces a concise summary with concrete file:line references for quick follow-up.

Quick Start

Use the grok skill to walk the code at the specified path and summarize how it works, focusing on the entry point, core types, hot paths, and relevant tests.

Frequently Asked Questions about /grok

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I understand an unfamiliar codebase before making changes?

To understand an unfamiliar codebase before editing, you can generate a read-only walkthrough that maps entry points, data models, hot paths, and tests. This investigation provides concrete file:line citations for quick navigation without modifying code.

What is the best way to map an authentication flow in a repository?

Mapping an authentication flow requires a question-driven read-only investigation that scopes the request into an actionable plan. The walkthrough identifies high-signal files and provides file:line references to explain the persistence behavior and core logic.

How do I identify data models and persistence behavior in an unfamiliar repo?

Identifying data models and persistence behavior involves reading relevant repository entry documents and selecting high-signal files. The walkthrough focuses on core types and hot paths, optionally persisting findings as a study artifact for future reference.

Can I investigate repository navigation and test organization without modifying files?

Yes, you can perform a read-only code investigation to understand repository navigation and test organization without modifying files. The process gathers entry points and walks important layers to explain why files exist and how tests are structured.

How do I turn a vague code exploration request into an actionable investigation plan?

Turning a vague request into an actionable plan requires question-driven scoping. The investigation narrows the focus to relevant entry documents, core data models, and hot paths, producing a concise summary with file:line references for immediate follow-up.

Do I need to read repository entry documents to understand code structure?

Yes, reading repository entry documents is required to understand code structure effectively. The walkthrough process selects a small set of high-signal files based on these documents to explain core types, hot paths, and test organization.