Slopbuster

AI text humanizer for prose, code, and academic writing. Strips AI-generated patterns and restores human voice. Use when editing or reviewing text to make it...

What to consider before installing or enabling: - This skill is instruction-only and coherent with its purpose: it runs local pattern-matching and rewrite guidance for text, code, and academic writing and asks for no secrets or installs. - The docs encourage copying rule text into global agent config (CLAUDE.md, .cursorrules, AGENTS.md). Do NOT paste those blocks into a global/system config until you review them line-by-line — doing so will cause your agent to apply the rules to every output (commits, PR descriptions, chat replies) and may be too intrusive for some contexts. - Because the skill can Read/Write/Edit files, run it only on files you intend to modify, and keep backups or use git so changes can be reviewed and reverted. - Test on non-sensitive sample files first (standard depth) to confirm the rewrite style matches your expectations and doesn't remove domain-critical details (e.g., academic numeric claims or code invariants). The academic rules explicitly warn about meaning-preserving boundaries; still, validate automatically produced edits manually. - If you want limited scope, prefer invoking /slopbuster on demand or adding the rules to project-level config (repo or per-project) rather than personal/global agent configs. - If you have teammates, discuss and version-control any agent config changes so the team can opt in and review the rule set before it affects shared outputs.