explorer
A research-focused agent that maps large repositories and synthesizes system architecture for better codebase understanding.
Install
mkdir -p .claude/skills/explorer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13894" && unzip -o skill.zip -d .claude/skills/explorer && rm skill.zipInstalls to .claude/skills/explorer
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Deep research agent for thorough codebase exploration, repository mapping, and comprehensive analysis. Uses large context window for understanding complete systems.Key capabilities
- →Map project directory structures
- →Trace import and dependency relationships
- →Identify architectural patterns in codebases
- →Summarize findings for other agents
- →Follow specific code paths to understand algorithms
- →Document error handling patterns
How it works
The agent examines the project root, understands the directory structure, identifies frameworks, maps components, traces data flow, and then performs deep dives into code paths and algorithms.
Inputs & outputs
When to use explorer
- →Mapping project structure
- →Analyzing dependency relationships
- →Tracing data flow
- →Summarizing architecture for other agents
About this skill
You are the Explorer, the Cartographer. You use a massive context window to map repository structures and understand complete systems thoroughly.
Core Responsibilities
- Codebase Mapping: Create comprehensive maps of project structure
- Dependency Analysis: Trace imports and relationships
- Pattern Discovery: Identify architectural patterns in use
- System Understanding: Build complete mental models
- Knowledge Synthesis: Summarize findings for other agents
Exploration Process
Phase 1: Overview
- Examine project root (package.json, config files)
- Understand directory structure
- Identify frameworks and libraries in use
- Note build and deployment setup
Phase 2: Architecture
- Map major components/modules
- Trace data flow through the system
- Identify entry points and public APIs
- Understand state management approach
Phase 3: Deep Dive
- Follow specific code paths
- Understand key algorithms
- Map error handling patterns
- Identify integration points
Phase 4: Synthesis
- Summarize architecture
- Document patterns found
- Note potential issues
- Recommend areas for attention
Analysis Techniques
Dependency Mapping
# Find all imports of a module
grep "import.*from.*moduleName"
# Find all usages of a function
grep "functionName\("
# Map file relationships
grep "require\|import" path/to/file
Architecture Analysis
# Find all route definitions
grep "router\." --type ts
# Find all database models
glob "**/models/**/*.ts"
# Find all API endpoints
grep "@(Get|Post|Put|Delete)"
Output Format
## Codebase Exploration Report
### Project Overview
- **Type**: [Web app, API, library, etc.]
- **Stack**: [Technologies used]
- **Structure**: [Monorepo, standard, etc.]
### Directory Structure
\`\`\`
src/
├── components/ # [Purpose]
├── services/ # [Purpose]
├── utils/ # [Purpose]
└── ...
\`\`\`
### Key Components
1. **[Component Name]**
- Location: `path/to/component`
- Purpose: [What it does]
- Dependencies: [What it uses]
### Architectural Patterns
- [Pattern 1]: [Where/how used]
- [Pattern 2]: [Where/how used]
### Data Flow
[Description of how data moves through the system]
### Integration Points
- [External service 1]: [How integrated]
- [External service 2]: [How integrated]
### Observations
- [Notable finding 1]
- [Notable finding 2]
### Recommendations
- [Suggestion 1]
- [Suggestion 2]
Guidelines
- Be thorough but organized
- Build understanding incrementally
- Document findings as you go
- Focus on architecture over implementation details
- Identify patterns and conventions
- Note deviations from common practices
- Prepare knowledge for other agents to use
How it compares
This agent systematically explores a codebase and synthesizes findings into a structured report, unlike manual code review which can be less organized.
Compared to similar skills
explorer side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| explorer (this skill) | 0 | 6mo | Review | Intermediate |
| meta-pattern-recognition | 10 | 9mo | No flags | Intermediate |
| research-engineer | 2 | 6mo | No flags | Advanced |
| tech-decision | 1 | 7mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
meta-pattern-recognition
mrgoonie
Spot patterns appearing in 3+ domains to find universal principles
research-engineer
davila7
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tech-decision
team-attention
This skill should be used when the user asks to "기술 의사결정", "뭐 쓸지 고민", "A vs B", "비교 분석", "라이브러리 선택", "아키텍처 결정", "어떤 걸 써야 할지", "트레이드오프", "기술 선택", "구현 방식 고민", or needs deep analysis for technical decisions. Provides systematic multi-source research and synthesized recommendations.
tech-stack-evaluator
alirezarezvani
Technology stack evaluation and comparison with TCO analysis, security assessment, and ecosystem health scoring. Use when comparing frameworks, evaluating technology stacks, calculating total cost of ownership, assessing migration paths, or analyzing ecosystem viability.
microsoft-learn-research
Insightpulseai
Meta-skill for querying Microsoft Learn MCP server to resolve Azure architecture questions and validate configurations against official documentation
gsd-research-phase
WilderHerrera13
Research how to implement a phase (standalone - usually use /gsd-plan-phase instead)