agentleFS
NexaiGuyNexaiGuy/nex-ai-skills/skills/agent-ready-website-converter/SKILL.md

agent-ready-website-converter

Skill1 starsChanged 16 days agoMITView on GitHub

Convert websites into agent-consumable formats with JSON-LD, product feeds, and .well-known discovery files. Use when: Generate valid JSON-LD for Organization and Product schemas; Create a .well-known/agent.json file for AI agent discovery; Audit a website''s readiness for AI shopping and browsing agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create a .well-known/agent.json file for AI agent discovery

    line 42
  2. Distinctive:

    Does not automatically deploy files to web servers.

    line 50
  3. Distinctive:

    No deep programming knowledge is required.

    line 85

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Agent Ready Website Converter

Free skill by Nex AI. This file is the public guide from Agensi. Scripts, extension source, and templates from the original package are not in this folder.

Turn Your Website into an Agent-Ready Storefront

As AI agents like Claude, ChatGPT, and shopping bots begin to navigate the web autonomously, traditional HTML isn't enough. This skill provides a specialized developer pipeline to convert any website—live or local—into an agent-consumable format that AI can discover, crawl, and transact with.

What it does

The skill executes a multi-stage pipeline using Python-based extraction and generation scripts:

  • Extraction: Scrapes HTML using Microdata and heuristic fallbacks to normalize products, pricing, and business identity.
  • Generation: Produces standards-compliant json-ld.json, a product-feed.json, and the emerging .well-known/agent.json discovery file.
  • Formatting: Creates an llms.txt policy file to define crawl rules for LLM-based agents.
  • Readiness Scoring: Generates a technical report scoring your site on structured data, machine-readable pricing, and checkout discoverability.

Why use this skill?

Standard prompts often struggle to generate perfectly valid JSON-LD or manage complex URL-to-JSON extractions. This skill uses a hardened Python pipeline with SSRF protection and deterministic schema generation. It ensures your site doesn't just "look" good to humans, but scores 100/100 for AI agent readiness.

Deliverables

The output is a ready-to-deploy agent-ready/ directory containing all necessary metadata files and a comprehensive readiness report with specific optimization recommendations.

Built by Nex AI. More skills and info at nex-ai.be and slopsome.com.

When to use

  • Generate valid JSON-LD for Organization and Product schemas
  • Create a .well-known/agent.json file for AI agent discovery
  • Audit a website's readiness for AI shopping and browsing agents
  • Extract structured product data from unstructured HTML folders
  • Generate llms.txt crawl policy files for AI bots

Known limitations

  • Requires Python 3.11+ environment.
  • Does not automatically deploy files to web servers.
  • Heuristic extraction may require manual JSON cleanup for non-standard HTML.

Example

Request

Analyze my local website in the ./dist folder and make it ready for AI shopping agents.

Result

Pipeline complete. Created directory /agent-ready/ containing:

  • jsonld.json (Organization & Product schemas)
  • .well-known/agent.json (Discovery)
  • llms.txt (Crawl policy)

Readiness Score: 85/100. Recommendation: Add explicit 'availability' signals to Product offers to reach 100.

Questions

How does this skill help my website interact with AI agents?

This skill transforms your existing website into a machine-readable format using structured data like JSON-LD and .well-known files. This ensures AI agents can accurately fetch your products, prices, and business details without getting confused by traditional HTML layouts.

Which AI agents and bots will be able to read my website after using this?

The skill is designed for cross-platform compatibility, supporting major AI ecosystems including ChatGPT, Claude, and specialized shopping bots. By generating standardized formats like llms.txt and agent.json, your site becomes discoverable by any agent following emerging web standards.

What specific files are included in the final delivery?

You will receive a downloadable 'agent-ready/' directory containing your custom JSON-LD schemas, product feeds, and discovery files. Additionally, it includes a technical readiness report that scores your site and provides actionable optimization tips.

Do I need advanced technical skills to implement the output?

No deep programming knowledge is required; you simply need to be able to upload the generated files to your website's root directory. The tool handles the complex Python extraction and schema generation logic for you.

Can I use this on a local staging site or only on live websites?

Yes, the skill utilizes a Python-based pipeline that can crawl both live URLs and local development environments. This allows you to audit and prepare your site for AI agents before you even push your latest updates live.

How does this handle websites that have poor existing SEO or missing metadata?

The skill uses deterministic schema generation and heuristic fallbacks to ensure that even if your HTML is messy, the output remains valid and structured. It also includes SSRF protection to ensure the extraction process is secure and reliable.


Built by Nex AI. More skills, including the paid catalog: https://www.agensi.io/creators/ch1n4-g3nd4x

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.