Your AI draft sounds like AI. I built a linter that scores how plain it is.

Описание и применение

Линтер plain‑speak оценивает простоту текста, выявляет длинные предложения, «buzzwords» и «hedges», и может использоваться в CI или агентских рабочих потоках для улучшения читаемости.

Задача

AI‑generated text is hard to spot because grammar is correct but the register is overly complex, using buzzwords, hedges, and long sentences.

Результат

The linter scores drafts on plainness, identifies long sentences, buzzwords, and hedge words, and can be integrated into CI or agent workflows to automatically improve readability.

Рабочий процесс

• Clone the repo: git clone https://github.com/hahahahahahahahah6/plain-speak
• Run the linter: python3 plain_speak.py check draft.txt
• Review the output for long sentences, buzzwords, and hedges
• Optionally use the agent skill to rewrite flagged lines
• Re‑run the linter until the plainness score passes the desired threshold

Доказательства

plain-speak is a tiny readability linter that scores text on plainness and flags the offending lines

Источник

Four checks: sentences over 25 words, ~45 built-in AI‑tell buzzwords, a Flesch‑style reading‑ease score folded into the total, and hedge density

Источник

--json and --fail-under 80 make it a CI gate for generated docs

Источник