Convert website to markdown for rag
Skill iterationlayer/skills/skills/convert-website-to-markdown-for-rag
Extract clean title, summary, markdown sections, and source metadata from a public documentation page for RAG ingestion.From its SKILL.md
npx -y skills add iterationlayer/skills --skill convert-website-to-markdown-for-ragAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
10.5 KB, as published. Nobody here has run it
Convert Website to Markdown for RAG
AI teams use this recipe to prepare public documentation pages for RAG ingestion. Extract a clean title, summary, markdown sections, canonical URL, and update metadata before indexing.
APIs Used
Website Extraction (1 credit per website extraction)
Prerequisites
You need an Iteration Layer API key. Get one at platform.iterationlayer.com during the 7-day trial.
For full integration guidance (SDKs, auth, MCP, error handling), see the Iteration Layer Integration Guide.
Implementation
curl -X POST https://api.iterationlayer.com/website-extraction/v1/extract \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"file": {
"type": "url",
"url": "https://example.com/docs/api-reference"
},
"schema": {
"fields": [
{
"name": "page_title",
"type": "TEXT",
"description": "Documentation page title"
},
{
"name": "canonical_url",
"type": "TEXT",
"description": "Canonical URL for the page"
},
{
"name": "summary",
"type": "TEXTAREA",
"description": "Short page summary"
},
{
"name": "sections",
"type": "ARRAY",
"description": "Clean markdown sections from the page",
"fields": [
{
"name": "heading",
"type": "TEXT",
"description": "Section heading"
},
{
"name": "markdown",
"type": "TEXTAREA",
"description": "Section content as markdown"
}
]
},
{
"name": "last_updated",
"type": "DATE",
"description": "Last updated date if shown"
}
]
}
}'
import { IterationLayer } from "iterationlayer";
const client = new IterationLayer({ apiKey: "YOUR_API_KEY" });
const result = await client.extractWebsite({
file: {
type: "url",
url: "https://example.com/docs/api-reference",
},
schema: {
"fields": [
{
"name": "page_title",
"type": "TEXT",
"description": "Documentation page title"
},
{
"name": "canonical_url",
"type": "TEXT",
"description": "Canonical URL for the page"
},
{
"name": "summary",
"type": "TEXTAREA",
"description": "Short page summary"
},
{
"name": "sections",
"type": "ARRAY",
"description": "Clean markdown sections from the page",
"fields": [
{
"name": "heading",
"type": "TEXT",
"description": "Section heading"
},
{
"name": "markdown",
"type": "TEXTAREA",
"description": "Section content as markdown"
}
]
},
{
"name": "last_updated",
"type": "DATE",
"description": "Last updated date if shown"
}
]
},
});
from iterationlayer import IterationLayer
client = IterationLayer(api_key="YOUR_API_KEY")
result = client.extract_website(
file={
"type": "url",
"url": "https://example.com/docs/api-reference",
},
schema={
"fields": [
{
"name": "page_title",
"type": "TEXT",
"description": "Documentation page title"
},
{
"name": "canonical_url",
"type": "TEXT",
"description": "Canonical URL for the page"
},
{
"name": "summary",
"type": "TEXTAREA",
"description": "Short page summary"
},
{
"name": "sections",
"type": "ARRAY",
"description": "Clean markdown sections from the page",
"fields": [
{
"name": "heading",
"type": "TEXT",
"description": "Section heading"
},
{
"name": "markdown",
"type": "TEXTAREA",
"description": "Section content as markdown"
}
]
},
{
"name": "last_updated",
"type": "DATE",
"description": "Last updated date if shown"
}
]
},
)
package main
import il "github.com/iterationlayer/sdk-go"
func main() {
client := il.NewClient("YOUR_API_KEY")
result, err := client.ExtractWebsite(il.ExtractWebsiteRequest{
File: il.UrlFileInput{
Type: "url",
Url: "https://example.com/docs/api-reference",
},
Schema: il.ExtractionSchema{
Fields: []any{
il.TextFieldConfig{
Name: "page_title",
Type: "TEXT",
Description: "Documentation page title",
},
il.TextFieldConfig{
Name: "canonical_url",
Type: "TEXT",
Description: "Canonical URL for the page",
},
il.TextareaFieldConfig{
Name: "summary",
Type: "TEXTAREA",
Description: "Short page summary",
},
il.ArrayFieldConfig{
Name: "sections",
Type: "ARRAY",
Description: "Clean markdown sections from the page",
Fields: []any{
il.TextFieldConfig{
Name: "heading",
Type: "TEXT",
Description: "Section heading",
},
il.TextareaFieldConfig{
Name: "markdown",
Type: "TEXTAREA",
Description: "Section content as markdown",
},
},
},
il.DateFieldConfig{
Name: "last_updated",
Type: "DATE",
Description: "Last updated date if shown",
},
},
},
})
if err != nil {
panic(err)
}
_ = result
}
{
"name": "Convert Website to Markdown for RAG",
"nodes": [
{
"parameters": {
"content": "## Convert Website to Markdown for RAG\n\nAI teams use this recipe to prepare public documentation pages for RAG ingestion. Extract a clean title, summary, markdown sections, canonical URL, and update metadata before indexing.\n\n**Note:** This workflow uses the Iteration Layer community node (`n8n-nodes-iterationlayer`). Install it via Settings > Community Nodes before importing. Self-hosted n8n only.",
"height": 280,
"width": 500,
"color": 2
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
200,
40
],
"id": "8489dbea-5cb7-5f09-9b79-e6a44f53269d",
"name": "Overview"
},
{
"parameters": {
"content": "### Step 1: Extract Website Data\nResource: **Website Extraction**\n\nConfigure the public website URL and schema below, then connect your credentials.",
"height": 160,
"width": 320,
"color": 6
},
"type": "n8n-nodes-base.stickyNote",
"typeVersion": 1,
"position": [
475,
100
],
"id": "3cc8b04a-f31d-5e80-8e40-21caf2d0d2e7",
"name": "Step 1 Note"
},
{
"parameters": {},
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
250,
300
],
"id": "06fbaa26-af7e-5549-a5a1-cbf38e0ad77e",
"name": "Manual Trigger"
},
{
"parameters": {
"resource": "websiteExtraction",
"fileUrl": "https://example.com/docs/api-reference",
"schemaInputMode": "rawJson",
"schemaJson": "{\"fields\":[{\"name\":\"page_title\",\"type\":\"TEXT\",\"description\":\"Documentation page title\"},{\"name\":\"canonical_url\",\"type\":\"TEXT\",\"description\":\"Canonical URL for the page\"},{\"name\":\"summary\",\"type\":\"TEXTAREA\",\"description\":\"Short page summary\"},{\"name\":\"sections\",\"type\":\"ARRAY\",\"description\":\"Clean markdown sections from the page\",\"fields\":[{\"name\":\"heading\",\"type\":\"TEXT\",\"description\":\"Section heading\"},{\"name\":\"markdown\",\"type\":\"TEXTAREA\",\"description\":\"Section content as markdown\"}]},{\"name\":\"last_updated\",\"type\":\"DATE\",\"description\":\"Last updated date if shown\"}]}"
},
"type": "n8n-nodes-iterationlayer.iterationLayer",
"typeVersion": 1,
"position": [
520,
300
],
"id": "18411b48-26e9-52ec-a857-abe04c01b0ea",
"name": "Extract Website Data",
"credentials": {
"iterationLayerApi": {
"id": "1",
"name": "Iteration Layer API"
}
}
}
],
"connections": {
"Manual Trigger": {
"main": [
[
{
"node": "Extract Website Data",
"type": "main",
"index": 0
}
]
]
}
},
"settings": {
"executionOrder": "v1"
}
}
Extract structured data from the public website page at [website URL]. Use the extract_website tool with this schema:
- page_title (TEXT): Documentation page title
- canonical_url (TEXT): Canonical URL for the page
- summary (TEXTAREA): Short page summary
- sections (ARRAY): Clean markdown sections from the page. Each item has heading (TEXT), markdown (TEXTAREA)
- last_updated (DATE): Last updated date if shown
Response
{
"success": true,
"data": {
"page_title": {
"type": "TEXT",
"value": "API Reference",
"confidence": 0.98,
"citations": [
"API Reference"
],
"source": "website.html"
},
"summary": {
"type": "TEXTAREA",
"value": "Reference documentation for authentication, requests, responses, and errors.",
"confidence": 0.91,
"citations": [
"Authentication, requests, responses, and errors"
],
"source": "website.html"
},
"sections": {
"type": "ARRAY",
"value": [
{
"heading": "Authentication",
"markdown": "Use a bearer token in the Authorization header."
}
],
"confidence": 0.88,
"citations": [
"## Authentication"
],
"source": "website.html"
}
}
}