Agentify is a specialized toolset for analyzing, refactoring, and specifying web pages to be perfectly navigable and parseable by AI agents and automation frameworks.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agentify
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 agentify 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 Agentify?
Agentify is designed to bridge the gap between human-centric web design and machine-readable efficiency. By utilizing the Openclaw Skills ecosystem, this tool evaluates HTML, JSX, Vue, and Svelte codebases to improve semantic markup, ARIA accessibility, and structured data. It ensures that websites are not just visually appealing but also optimized for Generative Engine Optimization (GEO), web scrapers, and AI-driven automation tools.
Whether you are preparing a site for complex browser automation or ensuring that AI agents can accurately interpret your content, Agentify provides the technical audit and automated refactoring necessary. It transforms "div soup" into structured, accessible, and high-performance code without breaking existing functionality or visual styles.
Agentify Use Cases
- Performing accessibility (a11y) and machine-readability audits on existing URLs or local codebases.
- Automatically adding stable selectors like data-testid to web templates for Playwright, Puppeteer, or Selenium testing.
- Generating comprehensive agent-friendly design specifications for engineering teams to follow during development.
- Improving SEO and crawler discovery through the automated insertion of JSON-LD and schema.org structured data.
- Enhancing the performance of AI agents interacting with complex web interfaces.
How Agentify Works
- Content Acquisition: The skill retrieves content via URL fetch, local file reads, or direct IDE code selection.
- Technical Analysis: It evaluates the source against a 100-point scoring rubric across nine categories, including Semantic HTML, ARIA patterns, and Selector Stability.
- Scoring & Reporting: A detailed report is generated, providing an A-F grade and a prioritized list of "Quick Wins" for immediate improvement.
- Automated Transformation: If requested, the skill rewrites web templates to inject attributes like data-testid, fix heading hierarchies, and add missing ARIA labels while strictly preserving original logic.
- Spec Generation: It produces a standardized agent-friendly-spec.md file that establishes long-term development standards for the project.
Agentify Setup
To begin using Agentify within the Openclaw Skills framework, ensure your environment has access to the provided reference documents for patterns and scoring.
# Example: Triggering an analysis via a CLI-enabled agent
agentify analyze https://your-website.com
# Example: Rewriting a local React component
agentify rewrite src/components/Header.tsx
Agentify Data Schema & Taxonomy
The skill organizes its output and metadata through the following structures:
| Data Object | Format | Purpose |
|---|---|---|
| Audit Report | Markdown | Detailed scoring (0-100), category breakdown, and before/after code samples. |
| Design Spec | Markdown | A comprehensive file (agent-friendly-spec.md) containing P0-P2 priorities and framework-specific examples. |
| Scoring Rubric | Reference Table | 9 categories weighted by impact, such as Semantic HTML (15pts) and Structured Data (15pts). |
| Transformation Log | Summary | A list of modifications made, attributes added, and items skipped for human review. |
Agentify Advanced Features
- Intelligent framework detection for React (JSX/TSX), Vue, Svelte, and vanilla HTML/CSS.
- Safety-first refactoring engine that ensures zero regressions in component logic, event handlers, or visual styling.
- Automated Generative Engine Optimization (GEO) through structured data and machine-signal enhancement.
- Integration with existing testing suites by mapping data-testid conventions to project-specific requirements.
- Support for multi-agent workflows by standardizing the machine-interface layer of web applications.
SKILL.md
Loading
Related Openclaw Skills
Odontosoft Dental Management
A specialized AI skill for managing dental clinic workflows including doctor availability, patient lookups, and appointment scheduling.
HPC CalculiX
An expert-level AI skill for building, reviewing, and automating CalculiX finite-element analysis workflows through structured input-deck management.
AI Daily News Collector
A sophisticated intelligence agent that filters and summarizes the latest technical breakthroughs in AI within a strict 72-hour window.
Anime Production Update
A professional AI-driven animation production pipeline that transforms scripts into finished anime videos using the Vidu API.
HPC FEniCS
A specialized AI agent skill for building, debugging, and optimizing finite-element workflows using the FEniCS and DOLFINx stacks.
Tianshu Homework Split
A specialized utility that transforms dense academic instructions and syllabus outlines into structured Markdown task lists.
Featured*
