A professional AI diagnostic tool for auditing frontend project architecture, tech stack health, and engineering configurations.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install eno
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install eno using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Frontend Architecture Analyzer is a high-level diagnostic tool designed for senior developers and architects. As a key part of the Openclaw Skills library, it provides an automated yet deep-dive review of frontend project structures across various frameworks including Vue, React, Angular, and specialized environments like OpenHarmony or VSCode extensions. It evaluates the technical truth of a project, identifying technical debt and providing a quantitative health score.
By leveraging this skill, development teams can ensure their projects adhere to modern best practices. The analyzer scrutinizes everything from dependency management and TypeScript strictness to complex design patterns and build system efficiency. It is an essential companion for maintaining long-term code quality and streamlining the refactoring process in complex web ecosystems.
To use this tool, ensure your AI agent is configured to access the Openclaw Skills repository. You can trigger the analysis by providing project context via natural language.
# Example usage within an AI coding agent
Analyze the architecture of this React project and review my component design patterns.
Simply provide the directory structure or relevant configuration files (package.json, tsconfig.json, build configs) to initiate the audit.
The skill organizes its findings into a structured multidimensional schema:
| Dimension | Evaluation Criteria | Metrics |
|---|---|---|
| Tech Stack Health | Framework versions, dependency locking | 0-50 Points |
| Design Patterns | Component granularity, state management | 0-35 Points |
| Engineering | Build configs, CI/CD, linting, test coverage | 0-20 Points |
| Performance | Split-chunking, lazy loading, tree-shaking | Qualitative Review |
| Overall Grade | Weighted average of all dimensions | Grade A to E |
Loading
An intelligent recommendation engine that maps specific emotional tones and scenarios to the ideal SenseAudio voice IDs.

A command-line interface for querying public Weibo data, including trending topics and user profiles, without requiring an API key.

A specialized automation recipe designed to seamlessly transfer and archive Gmail message content directly into Google Docs for permanent reference.

A powerful GIS automation skill that leverages the qgis_process CLI to perform repeatable vector and raster data transformations.

An expert AI news analyst that explains, interprets, and provides witty commentary on trending global events.

A sophisticated tool designed to translate human cognitive styles and work preferences into structured, machine-readable Markdown profiles for AI agents.








































