Word Counter (Policy-Driven)

Overview

You pass text (or a file_ref) and choose how a word is defined — Unicode word boundaries or visible written words; we return the count, the words themselves on request, any judgement calls we had to make, and the rule set we used so the number is defensible. Leave the policy out and we count with Unicode boundaries. A word count is only accurate when the counting rule is stated, so we always state it.

Word counts vary by algorithm. We force you to pick an explicit policy so your counts are reproducible and defensible.

When to use it

Scope

Non-goals

• Does not guess which policy fits your use case
• Does not perform NLP or grammatical word analysis

Properties

Capabilities

Cost & billing

Flat rate per invocation

File handling

File limits

Constraints this skill applies to your input and generated files. The “Limited by” column shows the static source of each cap; none of these can be raised by upgrading your plan.

How we handle your data

Input schema

Output schema

API contract

curl -sS -X POST "$BASE/v1/execute" -H "Authorization: Bearer $KEY" -H 'Content-Type: application/json' -d '{"skillKey":"text.count_words","input":{"text":"Hello world","policy":"unicode_default"}}'

import { Squillify } from "@squillify/sdk";

const sq = new Squillify({ apiKey: process.env.SQUILLIFY_API_KEY });

const { output } = await sq.execute("text.count_words", {"policy":"unicode_default","text":"Hello world"});

Errors

Other limits

Limitations

• Does not guess which policy fits your use case
• Does not perform NLP or grammatical word analysis
• LLM token budgeting (use text.count_tokens)
• Quick approximate length when methodology does not matter
• Character or byte counting (use text.count_characters or text.count_bytes)

How to call

POST /v1/execute (requires authentication)

{
  "skillKey": "text.count_words",
  "input": {
    "policy": "unicode_default",
    "text": "Hello world"
  }
}

Examples

{
  "policy": "unicode_default",
  "text": "Hello world"
}

{
  "warnings": [
    {
      "message": "This count follows Unicode word boundary rules, not grammatical word analysis.",
      "code": "UNICODE_NOT_GRAMMATICAL"
    }
  ],
  "unit": "word",
  "policy": "unicode_default",
  "count": 2,
  "metadata": {
    "skill_version": "1.0.0",
    "skill": "text.count_words",
    "deterministic": true,
    "policy_version": "unicode-uax29-jdk21",
    "policy": "unicode_default",
    "reliability_mode": "STRICT"
  }
}

{
  "policy": "orthographic",
  "text": "Hello world"
}

{
  "warnings": [],
  "unit": "word",
  "policy": "orthographic",
  "count": 2,
  "metadata": {
    "skill_version": "1.0.0",
    "skill": "text.count_words",
    "deterministic": true,
    "policy_version": "orthographic-v1",
    "policy": "orthographic",
    "reliability_mode": "STRICT"
  }
}

Recommended use cases

• Document word counts for billing, contracts, or editorial guidelines
• Validate content length before publishing or submission
• Compare counts across documents with a documented methodology

Avoid for

• LLM token budgeting (use text.count_tokens)
• Quick approximate length when methodology does not matter
• Character or byte counting (use text.count_characters or text.count_bytes)

Related skills

Composable with

Safety & privacy

• Runs without calling any external service.
• Your payloads are never stored permanently.
• Telemetry captures metadata only — never your payload contents.
• We never train models on your payloads.
• No human reviews your payloads.

Tags