Website Readability Skill

Overview

Website Readability works by fetching the page, extracting its readable text and scoring it across standard readability indices (Flesch, Gunning Fog, SMOG, Coleman-Liau, ARI, Dale-Chall). It also reports the word and sentence counts, an estimated reading time, an averaged grade level and the target reader audience so you can judge a page's accessibility at a glance.

Live Test Website Readability Skill Skill →

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as WebsiteReadabilitySkill. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.

Tool call

{
  "name": "WebsiteReadabilitySkill",
  "arguments": {
    "url": "https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/concepts"
  }
}

You do not name the tool yourself; the model picks it. Asking about https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/concepts in the terms this skill covers is enough for it to reach for WebsiteReadabilitySkill on its own — naming it explicitly also works, and is the way to force the call.

Connecting

One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.

{
  "mcpServers": {
    "vervekit": {
      "url": "https://api.vervekit.com/v1/mcp"
    }
  }
}

Per-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.

Argument	Type	Description
`url`Required	string	The URL of the web page to analyze url

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.

Result

{
  "status": "ok",
  "error": null,
  "data": {
    "fleschReadingEase": 24.34,
    "fleschReadingEaseText": "Very Confusing",
    "fleschKincaidGrade": 19.3,
    "gunningFog": 19.62,
    "colemanLiauIndex": 13.12,
    "smogIndex": 14.37,
    "automatedReadabilityIndex": 22.6,
    "daleChallReadabilityScore": 17,
    "daleChallReadabilityScoreText": "average 13th to 15th-grade (college) student",
    "wordCount": 634,
    "sentenceCount": 29,
    "readingTimeMinutes": 3,
    "averageGradeLevel": 17.8,
    "targetAudience": "post-graduate",
    "url": "https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/concepts"
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Field	Type	Example	Description
`fleschReadingEase`	number	`24.34`	Flesch Reading Ease score (0-100, higher is easier)
`fleschReadingEaseText`	string	`Very Confusing`	Descriptive text interpretation of Flesch Reading Ease
`fleschKincaidGrade`	number	`19.3`	Flesch-Kincaid Grade Level (US school grade equivalency)
`gunningFog`Premium	number	`19.62`	Gunning Fog Index (years of education needed to understand)
`colemanLiauIndex`Premium	number	`13.12`	Coleman-Liau Index (US grade level based on character count)
`smogIndex`Premium	number	`14.37`	SMOG Index (years of education to understand text)
`automatedReadabilityIndex`Premium	number	`22.6`	Automated Readability Index (US grade level estimate)
`daleChallReadabilityScore`Premium	number	`17`	Dale-Chall Readability Score (educational level)
`daleChallReadabilityScoreText`Premium	string	`average 13th to 15th-grade (college) student`	Descriptive interpretation of Dale-Chall Readability Score
`wordCount`	number	`634`	Number of words in the page's readable text
`sentenceCount`	number	`29`	Number of sentences in the page's readable text
`readingTimeMinutes`	number	`3`	Estimated reading time in minutes at an average adult reading speed of 238 words per minute
`averageGradeLevel`Premium	number	`17.8`	Single averaged US school grade level digested from the grade-based indices (Flesch-Kincaid, Gunning Fog, Coleman-Liau, SMOG, ARI) — the one number that summarizes how much education a reader needs
`targetAudience`Premium	string	`post-graduate`	Reader band mapped from the average grade level: elementary, middle school, high school, college, post-graduate or general public
`url`	string	`https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/concepts`	The analyzed URL from the request

Failure modes

Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.

Status	What it means
`400` / `422`	The arguments did not validate. The message names the offending one.
`401`	The OAuth session is invalid or expired — reconnect the server.
`403`	Blocked by a key restriction or an IP allow-list. Never a bad identity.
`404`	This skill is not part of VerveKit. Check the catalog.
`429`	Out of credits, or a brief rate limit. The message tells them apart.

A call costs 10 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Use cases

Content Management Audits: CMS plugins check published articles against Flesch-Kincaid grade scores to keep drafts within target reading levels before publication.
Public Notice Compliance: When updating government web portals, compliance teams verify that policy notices maintain high Flesch Reading Ease scores for clear public comprehension.
EdTech Article Recommendation: Educational platforms inspect external articles by URL to pair students with texts matching their current reading grade and estimated reading time.
Search Content Optimization: Flag overly dense blog posts during site audits by tracking reading ease scores and sentence counts against top-ranking search competitors.