Help us improve
Share bugs, ideas, or general feedback.
From skills
Removes AI-generated slop from prose (filler phrases, passive constructions) and code diffs (over-explained comments). Rewrites to sound natural and human.
npx claudepluginhub kriscard/skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/skills:deslopifyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Strip the patterns that mark text as AI-generated. Preserve all factual
Removes AI artifacts (tool names, boilerplate, over-structuring) from documents. Processes single files, directories, or git diffs.
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 text by removing patterns like inflated symbolism, promotional language, em dash overuse, and rule of three per Wikipedia guide. Use for editing drafts and reviewing content.
Share bugs, ideas, or general feedback.
Strip the patterns that mark text as AI-generated. Preserve all factual content and the author's intended tone — change the delivery, not the message.
Scan for these before rewriting. The more you find, the more aggressive the edit.
Opening filler (cut 80% of the time — start with the actual point):
Hollow transitions:
Emphasis inflation:
AI vocabulary (replace with the plain word):
Excessive hedging:
Nominalization (convert to verb):
Bullet lists where prose would be clearer: not every list needs to be a list. Three related sentences often read better as a paragraph.
En-dash used as em-dash: – should be — (or just a comma)
When the input is a diff (or the user asks to remove AI comments from code):
What to remove:
// increment counter above counter++)// TODO: implement, // Handle error)What to keep:
Hard constraint: DO NOT modify any code. Only remove comments. No refactoring, no style changes, no removing try/catch or null checks. If you spot code slop, note it in the summary but leave it.
Output: report 1–3 sentences on what was removed and any code issues noticed but left unchanged.