remove-ai-sloplisted

# Remove AI Slop Identify and remove AI-slop: the filler, hedging, marketing, and jargon phrases that AI text generators lean on, the structural tells they use to manufacture insight, plus em-dash overuse. Output is cleaner prose with the meaning, facts, and technical terms intact. This skill is a reviewer/cleaner, not a writer. It edits what is there; it does not invent content or restructure the document. It covers two kinds of slop: - **Word-level** (words and phrases) — see [references/phrases.md](references/phrases.md). - **Structural** (constructions and rhythm) — see [references/structures.md](references/structures.md). ## Workflow 1. **Identify the setting.** Determine the input: a file on disk to edit in place, or inline prose to return cleaned. If you write to a `.md` file, never wrap the result in a code fence — the file content IS markdown. 2. **Scan the text.** Flag every match of the categories below. Record the exact location (line or sentence), the current phrase, and a proposed replacement. 3. **Report before editing** (unless the user asked for auto-fix). Present findings as a numbered table where each entry gets a number starting at 1: | # | Location | Phrase | Suggested fix | |---|----------|--------|---------------| Let the user accept or reject findings before you apply changes. 4. **Apply the selected fixes.** The user picks which findings to fix by number. Keep the meaning, facts, and technical terms intact. *