Word Opposites Skill

Overview

Word Opposites sends your `word` to a Gemini language model with an instruction to act as a JSON API that returns up to five opposites. The model output is constrained to a schema holding a single array of strings, which becomes `opposites`. `word` echoes your input exactly as sent, without trimming or case changes.

The instruction also tells the model to answer in English regardless of the input language, never to return a string that is not a real English word, and to return an empty array when the input is not a real word or has no meaningful opposite. In practice that means a typo or a term like "table" can legitimately come back with `opposites: []`, which you should treat as "no antonym available" rather than as an error. If the model omits the array, the API still returns `opposites` as an empty array.

The model runs at a low sampling temperature of 0.3, so results for common words are fairly stable, but the list is not drawn from a fixed thesaurus and order or wording can vary between calls. Entries are not deduplicated or ranked by the API. Answers can include both strict antonyms and looser contrasting words, as with "cool" for "hot". Multi-word phrases are accepted as input, but answers are most reliable for single common words.

If the model's safety filter blocks the input, the request fails with a 400 error that carries the block reason. There are no plan-dependent fields.

Live Test Word Opposites Skill Skill →

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as WordOppositesSkill. 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": "WordOppositesSkill",
  "arguments": {
    "word": "hot"
  }
}

You do not name the tool yourself; the model picks it. Asking about hot in the terms this skill covers is enough for it to reach for WordOppositesSkill 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
13
14

{
  "status": "ok",
  "error": null,
  "data": {
    "word": "hot",
    "opposites": [
      "cold",
      "cool",
      "chilly",
      "frozen",
      "frigid"
    ]
  }
}

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

Crossword Clue Generation

Clue authors and puzzle builders retrieve contrasting terms to construct clever definitions and dual-word crossword grids automatically.

Creative Copy Inversion

Generate punchy before-and-after advertising hooks by querying contrasting vocabulary for draft product headlines and promotional slogans.

Sentiment Polarity Testing

To calibrate lexicon-based sentiment models, data teams test opposing word pairs against text classification pipelines.

Digital Workbook Drills

When students complete a reading unit, education software pulls contrasting terms to build antonym matching drills and practice questions.

Other ways to use Word Opposites Skill

Set up Word Opposites 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: