Explore

A meta-skill that chains together different exploration workflows depending on how deep you need to go. Quick mode runs tldr commands for a one-minute overview, deep mode adds onboarding and research agents for comprehensive analysis, and architecture mode focuses on layers and call graphs. The question flow is well-designed, walking you through depth selection, scope, and output format if you just type /explore without arguments. It's strictly read-only, which is the right call for exploration. The handoff output option is smart for passing context to implementation agents. Most useful when you're new to a codebase or planning refactoring work where you need to understand boundaries and dependencies first.

skills.sh installs: 580
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill explore --agent claude-code

Installs into .claude/skills of the current project.

Files

Explore - Internal Codebase Exploration

Meta-skill for exploring an internal codebase at varying depths. READ-ONLY workflow - no code changes.

Usage

/explore <depth> [options]

Question Flow (No Arguments)

If the user types just /explore with no or partial arguments, guide them through this question flow. Use AskUserQuestion for each phase.

Phase 0: Workflow Selection

question: "How would you like to explore?"
header: "Explore"
options:
  - label: "Help me choose (Recommended)"
    description: "I'll ask questions to pick the right exploration depth"
  - label: "Quick - fast overview"
    description: "Chain: tldr tree → tldr structure (~1 min)"
  - label: "Deep - comprehensive analysis"
    description: "Chain: onboard → tldr → research → document (~5 min)"
  - label: "Architecture - layers & dependencies"
    description: "Chain: tldr arch → call graph → layer mapping (~3 min)"

Mapping: