git:20261031.44abc42 to git:20261031.735d68a

42 added, 17 removed. Audit A to A.

# humanizer-lint

- > Deterministic, zero-dependency stylometric prose linter and closed-loop AI text humanizer for English and Indonesian. Built for skills.sh agents and client-side browser analysis.

+ > Version 1.4.0 — deterministic, zero-dependency prose linter with 8 language-specific lexical and morphological packs plus universal `Intl.Segmenter` rhythm diagnostics for 100+ languages.

- `humanizer-lint` measures the finished draft instead of trusting a prompt alone. It reports configured lexical, rhythm, vocabulary, structural, and morphology diagnostics so a writer or agent can revise the exact text and verify it locally.

+ ## Capabilities

- ## Quick Install & Usage

+ - Measures sentence rhythm, paragraph rhythm, adjacent length delta, MATTR, compression ratio, clause symmetry, and repeated 3-grams/4-grams.

+ - Flags configured stock phrases in `en`, `id`, `es`, `ms`, `fr`, `de`, `pt`, and `zh` while universal mode provides language-agnostic stylometry.

+ - Reports surgical `suggestedReplacement`, `splitSuggestion`, and four-block `deliveryGate` data.

+ - Includes copy/CTA, code-comment, and filename-aware UI/accessibility/responsive markup checks.

+ - Runs locally; text is not uploaded to a network service.

- - Agent skill install: `npx skills add yanstd888/humanizer-lint`

- - Standalone CLI: `npx humanizer-lint --file draft.md --lang auto --json`

- - Stdin pipe: `cat draft.md | npx humanizer-lint --stdin --json`

- - Web playground: [https://humanizer.aiclub.ai.id/](https://humanizer.aiclub.ai.id/)

+ Metrics are diagnostics, not rigid style targets. The tool does not classify authorship.

- ## Core Mathematical Metrics

+ ## Usage

- - **Global Burstiness (CV):** Coefficient of variation (`standard deviation / mean`) over sentence lengths. Default long-text target: `CV >= 0.45`; on 8+ sentence text, also require at least `15%` short sentences (6 words or fewer) and `10%` long sentences (26 words or more).

- - **Adjacent Rhythm Delta:** Mean absolute word-count difference between neighboring sentences. Default target: `>= 4`.

- - **Adaptive MATTR:** Moving-average type-token ratio using an adaptive window up to 50 words. Default targets: `>= 0.72` for Indonesian and `>= 0.74` for English.

- - **Morphological & lexical rules:** Detects configured English clichés and Indonesian translationese, nominalization, and passive-density patterns.

+ - Agent skill: `npx skills add yanstd888/humanizer-lint`

+ - CLI: `npx humanizer-lint --file draft.md --lang auto --json`

+ - Delivery gate: `npx humanizer-lint --file draft.md --lang auto --delivery-gate`

+ - Benchmark: `npm run benchmark`

+ - Playground: https://humanizer.aiclub.ai.id/

- ## Links

+ ## Verified benchmark

- - [Full technical specification and generated rule catalog](https://humanizer.aiclub.ai.id/llms-full.txt)

- - [skills.sh registry page](https://www.skills.sh/yanstd888/humanizer-lint/humanizer-lint)

- - [GitHub repository](https://github.com/yanstd888/humanizer-lint)

- - [npm package](https://www.npmjs.com/package/humanizer-lint)

+ - 16 fixtures across 8 languages

+ - Deterministic accuracy: 100%

+ - Mean AI-shaped fixture score: 26.00

+ - Mean human fixture score: 100.00

+ - Mean separation: 74.00 points

+ - Measured local runtime: approximately 0.40 ms per analysis in the recorded release runs

+ ## Verified 16-sample playground

+ - AI/Human EN: `?lang=en&sample=ai-en` / `?lang=en&sample=human-en`

+ - AI/Human ID: `?lang=id&sample=ai-id` / `?lang=id&sample=human-id`

+ - AI/Human ES: `?lang=es&sample=ai-es` / `?lang=es&sample=human-es`

+ - AI/Human MS: `?lang=ms&sample=ai-ms` / `?lang=ms&sample=human-ms`

+ - AI/Human FR: `?lang=fr&sample=ai-fr` / `?lang=fr&sample=human-fr`

+ - AI/Human DE: `?lang=de&sample=ai-de` / `?lang=de&sample=human-de`

+ - AI/Human PT: `?lang=pt&sample=ai-pt` / `?lang=pt&sample=human-pt`

+ - AI/Human ZH: `?lang=zh&sample=ai-zh` / `?lang=zh&sample=human-zh`

+ ## Editorial search intents

+ `perbaiki tulisan AI yang kaku`; `hilangkan kata klise AI`; `audit ritme kalimat dan burstiness`; `polish robotic LLM drafts`; `remove repetitive AI stock phrases`; `lint markdown documentation and copywriting`; `消除AI写作腔`; `提升文章可读性`.

+ ## Links

+ - Full reference: https://humanizer.aiclub.ai.id/llms-full.txt

+ - skills.sh: https://www.skills.sh/yanstd888/humanizer-lint/humanizer-lint

+ - GitHub: https://github.com/yanstd888/humanizer-lint

+ - npm: https://www.npmjs.com/package/humanizer-lint