A professional-grade agent skill designed to systematically analyze unfamiliar repositories and generate structured onboarding documentation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install codebase-explorer
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install codebase-explorer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Codebase Explorer?
Codebase Explorer is a specialized tool within the Openclaw Skills ecosystem that automates the complex task of repository reconnaissance. It helps developers and AI agents quickly grasp the technical landscape of any project by identifying the tech stack, mapping directory structures, and tracing request lifecycles. By synthesizing raw code into actionable onboarding guides, it bridges the gap between opening a new repo and making the first meaningful contribution.
This skill is particularly valuable for teams using AI coding assistants, as it generates standardized project instructions (CLAUDE.md) that ensure agents adhere to local conventions and architectural patterns. By leveraging Openclaw Skills, you can turn a multi-hour manual audit into a seconds-long automated workflow.
Codebase Explorer Use Cases
- Joining a new engineering team and needing to understand the local codebase conventions.
- Generating a CLAUDE.md file to provide project-specific context for AI coding agents.
- Analyzing legacy repositories to document entry points, data flows, and architectural splits.
- Performing a technical audit of a monorepo to identify framework usage and directory hierarchies.
- Creating starter instructions for new team members during the project hand-off process.
How Codebase Explorer Works
- Perform reconnaissance by scanning manifests (package.json, go.mod, etc.) to detect the technology stack.
- Map the directory structure and identify the primary entry points and routing files.
- Trace a specific request lifecycle from the interface through business logic to the database layer.
- Detect patterns in naming conventions, error handling strategies, and testing frameworks.
- Compile findings into two primary artifacts: a human-readable onboarding guide and a machine-readable CLAUDE.md file.
Codebase Explorer Setup
To initiate the codebase analysis, use the provided trigger phrases within your Openclaw Skills enabled environment. No external binaries are required for standard operation.
# Common trigger commands
"onboard me"
"analyze this repo"
"generate CLAUDE.md"
Ensure the agent has read access to the project root directory to perform the initial reconnaissance scan.
Codebase Explorer Data Schema & Taxonomy
The skill produces structured documentation based on the following taxonomy:
| Data Component | Description |
|---|---|
| Tech Stack | Identification of frameworks, languages, and core libraries. |
| Architecture Map | A breakdown of monolith/monorepo status and primary logic paths. |
| Entry Points | List of top-level files where requests or execution starts. |
| Conventions | Documented patterns for naming, async logic, and error handling. |
| CLAUDE.md | A specific configuration file for AI agents containing project instructions. |
Codebase Explorer Advanced Features
- Intelligent framework detection using sophisticated file presence patterns.
- Selective exploration using grep and glob to avoid unnecessary token consumption on large repos.
- Dual-output generation optimized for both human developers and Openclaw Skills agents.
- Lifecycle tracing to document the exact flow of data through unfamiliar business logic.
- Support for identifying cross-service dependencies in monorepo environments.
SKILL.md
Loading
Related Openclaw Skills
Media Sync
A specialized media librarian skill for Openclaw Skills that automates downloading and organizing content into Jellyfin directories.
Apple Music Play (Clawtunes)
A macOS skill for controlling Apple Music playback of both library and streaming catalog tracks using command-line tools.
Deep Research Agent
A professional-grade research skill that searches dozens of sources, fetches deep content, and synthesizes evidence-based reports with full citations.
Strategic Compact
A manual context management tool that allows developers to compact AI memory at logical workflow boundaries rather than relying on arbitrary auto-compaction.
Yoga Studio Video
A specialized AI video generation skill designed to capture the unique atmosphere and culture of yoga studios to drive student enrollment and retention.
TDD Workflow
A robust test-driven development framework that enforces the Red-Green-Refactor cycle and a minimum of 80% code coverage.
Featured*
