Spelling Correction Skill

Overview

Did You Mean sends your `query` to a Gemini language model with an instruction to act as a JSON API that returns three "did you mean" alternatives in the style of a search engine, with spellings corrected and without shortening the query. The model is constrained to a JSON schema containing a single array of strings, and that array is returned as `didYouMean`. `query` echoes your input unchanged.

The model runs with a sampling temperature of 0.7, so repeated calls with the same query can produce different wording or ordering. Three suggestions are requested, but the count is not enforced in code; treat `didYouMean` as a list of zero or more strings rather than a fixed-length array. If the model returns nothing, `didYouMean` is an empty array. Suggestions are always written in English, even when the query is in another language, so this endpoint suits English search interfaces best.

If the model's safety filter blocks the query, the request fails with a 400 error and the block reason instead of returning an empty list. There is no dictionary lookup or edit-distance step: the output depends entirely on the model, so it can rephrase a correctly spelled query as well as fix a misspelled one. Use it as a suggestion source to show the user, not as an automatic correction. There are no plan-dependent fields.

Live Test Spelling Correction Skill Skill →

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as SpellingCorrectionSkill. 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.

{
  "name": "SpellingCorrectionSkill",
  "arguments": {
    "query": "what weather today is"
  }
}

You do not name the tool yourself; the model picks it. Asking about what weather today is in the terms this skill covers is enough for it to reach for SpellingCorrectionSkill 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"
    }
  }
}

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.

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.

1
2
3
4
5
6
7
8
9
10
11
12

{
  "status": "ok",
  "error": null,
  "data": {
    "query": "what weather today is",
    "didYouMean": [
      "what is the weather today",
      "what's the weather like today",
      "what will be the weather today"
    ]
  }
}

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.

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.

A call costs 20 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Use cases

E-Commerce Search Suggestions

When shoppers mistype product names in a store search bar, display alternate spelling recommendations so they still find inventory.

Help Desk Query Fallback

To prevent dead ends in customer support portals, offer corrected search terms whenever a knowledge base query returns zero articles.

User Form Normalization

Clean user-submitted tags and profile fields during registration by matching misspellings against recommended corrections before saving entries to the database.

Chatbot Typo Recovery

Chatbots can parse incoming user messages with spelling mistakes and prompt users with suggested corrections before triggering fallback handlers.

Other ways to use Spelling Correction Skill

Set up Spelling Correction Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.

Related

More in Text Processing: