Sentence Counter

Overview

You pass text (or a file_ref); we count its sentences under a policy you pick — Unicode break rules for real prose, or a plain split on . ! ? and … when you want something blunt and predictable — and hand back the sentences themselves on request. The blunt policy always ships a warning, because abbreviations and decimals fool it.

Sentence boundaries are linguistically complex. We give you two explicit policies with transparent accuracy trade-offs instead of opaque guessing.

When to use it

Scope

Non-goals

• Does not perform NLP sentence parsing
• Does not guarantee accuracy on abbreviation-heavy text under simple_punctuation

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_sentences","input":{"text":"Hello. World!","policy":"unicode_sentence_boundary"}}'

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

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

const { output } = await sq.execute("text.count_sentences", {"policy":"unicode_sentence_boundary","text":"Hello. World!"});

Errors

Other limits

Limitations

• Does not perform NLP sentence parsing
• Does not guarantee accuracy on abbreviation-heavy text under simple_punctuation
• Precise NLP sentence segmentation for legal or clinical text
• Abbreviation-heavy prose when using simple_punctuation without review

How to call

POST /v1/execute (requires authentication)

{
  "skillKey": "text.count_sentences",
  "input": {
    "policy": "unicode_sentence_boundary",
    "text": "Hello. World!"
  }
}

Examples

{
  "policy": "unicode_sentence_boundary",
  "text": "Hello. World!"
}

{
  "count": 2,
  "skill": "text.count_sentences",
  "policy": "unicode_sentence_boundary",
  "locale": "und",
  "warnings": [],
  "unit": "sentence"
}

{
  "policy": "simple_punctuation",
  "text": "Dr. Smith went home. He was tired."
}

{
  "count": 3,
  "skill": "text.count_sentences",
  "policy": "simple_punctuation",
  "locale": "und",
  "warnings": [
    "simple_punctuation is not linguistically reliable and may miscount abbreviations, decimals, initials, and ellipses."
  ],
  "unit": "sentence"
}

Recommended use cases

• Feed readability or speaking-time pipelines with sentence counts
• Measure content structure for articles, reports, or transcripts
• Compare sentence density across documents with a documented policy

Avoid for

• Precise NLP sentence segmentation for legal or clinical text
• Abbreviation-heavy prose when using simple_punctuation without review

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