explore

Explore codebases read-only to map architecture, dependencies, and knowledge gaps.

36|3|Updated Jan 6, 2026
One-click install
npx skills add https://github.com/2lab-ai/oh-my-claude --skill explore-2lab-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: explore
Source: https://github.com/2lab-ai/oh-my-claude/tree/main/plugins/stv/skills/explore
Command: npx skills add https://github.com/2lab-ai/oh-my-claude --skill explore-2lab-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provide a read-only exploration stance to uncover architecture, assumptions, dependencies, and knowledge gaps so teams can avoid premature design decisions and commit to informed specifications.

Core Features & Use Cases

  • Read-only code investigation: Inspect repository structure, trace call paths, and mine git history without changing files.
  • Visual mapping: Produce ASCII diagrams and dependency maps to reveal boundaries and system interactions.
  • Hypothesis validation & guidance: Form hypotheses grounded in code and evidence, propose artifact saves only with user consent; ideal when requirements are vague, domains are unfamiliar, or legacy code must be understood before spec or implementation.

Quick Start

Explore the authentication module and map its key dependencies, assumptions, and recommended next step.

Frequently Asked Questions about explore

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

FAQPage Schema
How do I analyze repository structure and map dependencies in an unfamiliar codebase?

To analyze repository structure and map dependencies, you can perform read-only codebase exploration to trace call paths, mine git history, and generate ASCII diagrams revealing system boundaries without modifying files.

What is the best way to investigate legacy code before writing implementation specifications?

Investigating legacy code before specification requires a read-only exploration stance to surface architecture, assumptions, and knowledge gaps, ensuring you avoid premature design decisions and commit to informed specs.

Can I generate ASCII diagrams to trace call paths without modifying the repository files?

Yes, you can generate ASCII diagrams to trace call paths and map dependencies while strictly avoiding file modifications or auto-saving artifacts, proposing any artifact saves only with explicit user consent.

How do I validate hypotheses about codebase architecture and uncover hidden assumptions?

You validate hypotheses about codebase architecture by grounding them in code evidence, reviewing git history, and consulting external documentation during read-only investigation to reveal assumptions and knowledge gaps.

Does read-only codebase exploration work for clarifying vague requirements in unfamiliar domains?

Read-only codebase exploration works effectively for clarifying vague requirements in unfamiliar domains by mapping complex legacy systems and surfacing architectural boundaries to inform decisions before implementation.