Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From writing
Avoids AI writing tropes like em dashes, delve, and promotional language when writing or editing PR descriptions, commit messages, documentation, Slack, or de-AI'ing text.
npx claudepluginhub bendrucker/claude --plugin writingHow this skill is triggered — by the user, by Claude, or both
Slash command
/writing:writingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Never use spaced em dashes (` — `). This is the most recognizable AI writing tell.
Humanizes AI-generated text in project files, READMEs, docs, and blogs by detecting and fixing 24 documented AI writing patterns. Interactive workflow with input selection, content type, and intensity options.
Humanizes AI-generated developer docs and code comments by auto-applying safe fixes from review-ai-writing results. Includes git stash safety, dry-run preview, full scans, and category filtering.
Removes signs of AI-generated writing from text to make it sound more natural and human. Detects and fixes patterns like inflated symbolism, promotional language, passive voice, and filler phrases.
Share bugs, ideas, or general feedback.
Never use spaced em dashes (—). This is the most recognizable AI writing tell.
word—wordThese words are strongly associated with AI-generated text. Do not use them:
Do not replace "is" or "are" with fancier constructions:
Avoid marketing-style adjectives and verbs:
Avoid the "not just X, but also Y" construction. Simplify.
Semicolons are not wrong but AI overuses them. Prefer shorter sentences or commas. If you find yourself using more than one semicolon in a paragraph, rewrite.
Write in a direct, conversational tone. Every line should teach the reader something new. Remove words that state the obvious or pad length.
Scan the target text for the patterns above. Replace each instance with natural alternatives. Prefer the simplest rewrite that preserves meaning.