Detects and removes AI writing patterns from text. Use when polishing drafts, cleaning AI-generated content, or ensuring writing sounds authentically human. Invoke with "run through slop detector", "clean this up", or "remove AI fingerprints".
npx skills add https://github.com/nicepkg/ai-workflow --skill ai-slop-detector
Takes any text and rewrites it to remove common AI writing patterns, making it sound authentically human. Returns only the cleaned final version.
Execute these steps NOW on the text provided:
The input text is everything that preceded this skill's invocation. Process it now.
This skill is often invoked at the end of other skills (magic-model-review, bb-coaching-response, newsletter-coach, etc.).
When invoked mid-workflow:
Remove these entirely or replace with specific facts:
Fix: Use specific, factual descriptions
Remove these - present facts directly:
Fix: Just state the thing
Replace excessive use of:
Fix: Use varied, natural transitions or combine sentences
End paragraphs with forward-looking statements or the most important point.
Pattern to replace: "In summary," "In conclusion," "Overall" followed by restatement
Use sentence case instead:
Use bold sparingly - only for true emphasis or introducing technical terms for the first time.
Write in flowing paragraphs instead of numbered/bulleted lists:
Replace with varied punctuation (commas, parentheses, colons, or sentence breaks):
Replace analytical -ing phrases with specific outcomes.
Pattern to replace: Vague present participle comments (highlighting, demonstrating, showcasing)
Attribute claims to specific sources with dates or numbers.
Pattern to replace: "Industry experts," "many believe," "studies show" without citation
Use specific lists instead of artificial "from X to Y" constructions.
Pattern to replace: "from...to..." when not describing actual ranges
These patterns scream AI:
Fix: Replace with direct positive assertions
Exception: Contrast is acceptable ONLY if spaced out with substantial content between negative and positive (2-3+ sentences of expansion).
These opening gambits announce "AI wrote this":
Fix: Start with the actual point
AI loves these dramatic punctuation patterns:
Fix: Let the content carry the weight
AI overuses these for false drama:
Fix: Vary paragraph length naturally. Reserve one-liners for genuine impact.
| AVOID | USE INSTEAD |
|-------|-------------|
| "leverages" | "uses" |
| "encompasses" | "includes" |
| "facilitates" | "enables" or "allows" |
| "utilized" | "used" |
| "commenced" | "began" or "started" |
| "subsequent to" | "after" |
| "prior to" | "before" |
| "in order to" | "to" |
| "serves to" | "helps" or omit entirely |
| "delve" | "explore" or "examine" |
| "navigate" | "work through" or "handle" |
| "unpack" | "explain" or "break down" |
| "tapestry" | "mix" or "combination" |
| "realm" | "area" or "field" |
| "embark" | "start" or "begin" |
| "harness" | "use" or "apply" |
| "illuminate" | "show" or "reveal" |
| "pivotal" | "important" or "key" |
| "robust" | "strong" or "solid" |
Use inverted pyramid structure (important info first) or natural conversational flow.
Pattern to replace: Five-paragraph essay structure with thesis statements and formal conclusions
Vary list lengths and replace generic adjectives with specific details.
Pattern to replace: Constant groupings of three generic qualities
Remove AI hedging phrases entirely - state facts directly.
Patterns to remove: "as of [date]," "based on available information," "while specific details are limited"
Use direct assertions backed by specific data.
Pattern to replace: Excessive qualifiers (appears to, tends to, seems to, might)
Before returning cleaned text, verify:
10. No direct contrast formulations ("This isn't X—it's Y")
11. No throat-clearing openers ("Here's the thing", "Let me be clear")
12. No emphasis crutches ("That's it. That's the [noun].")
13. Varied paragraph lengths (not all one-sentence or all same length)
Return only the cleaned text. No preamble, no explanation of changes, no "Here's the cleaned version:" - just the polished content ready to use.
| Version | Date | Changes |
|---------|------|---------|
| 1.2.0 | 2026-01-17 | Added throat-clearing, emphasis crutches, dramatic fragmentation; expanded word substitutions (+10 words); 13-point checklist |
| 1.1.0 | 2026-01-15 | Directive instructions for immediate execution, positive framing, skill chaining section |
| 1.0.0 | 2026-01-01 | Initial creation from Write with AI prompt |
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementing any feature or bugfix, before writing implementation code
Use when you have a spec or requirements for a multi-step task, before touching code
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Use when writing or improving README files. Not all READMEs are the same — provides templates and guidance matched to your audience and project type.
| Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2 features. Best for production Opentrons protocols, official API compatibility. For multi-vendor automation or broader equipment control use pylabrobot.
Take nicepkg/ai-slop-detector from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.