writing-anti-ai
Skill35 starsChanged 2 months agoMITView on GitHub
This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to eliminate AI writing patterns from prose. Based on Wikipedia's "Signs of AI writing" guide, detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI vocabulary, negative parallelisms, and excessive conjunctive phrases.
4 other projects use a version of this, 3 of them edited.
Adopted by
Most recently taken up by
- shkodnik1917/claude-brainlabword for word, first seen Nov 8, 2026
- Galaxy-Dawn/claude-scholaredited, first seen Apr 15, 2026
- cnfjlhj/ai-collab-playbookedited, first seen Mar 22, 2026
- Clay-HHK/claude-skillsedited, first seen Mar 5, 2026
Other versions4 projects use a version of this.
Word for word · 1
- shkodnik1917/claude-brainlab★ 35100% same
Edited · 3
- Galaxy-Dawn/claude-scholar★ 5.9k66% same
- cnfjlhj/ai-collab-playbook★ 45665% same
- Clay-HHK/claude-skills★ 170% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository68 other files it gives its agents.
- rules/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- academic-plottingSkill
- agent-identifierSkill
- architecture-designSkill
- astar-paper-reviewSkill
- bug-detectiveSkill
- call-notesSkill
- cavemanSkill
- citation-verificationSkill
- code-ingestSkill
- code-librarySkill
- code-review-excellenceSkill
- command-developmentSkill
- create-projectSkill
- daily-codingSkill
- defuddleSkill
- diagnoseSkill
- doc-coauthoringSkill
- experiment-runsSkill
- frontend-designSkill
- git-guardrails-claude-codeSkill
- git-workflowSkill
- google-workspace-mcpSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- handoff-to-jarvisSkill
- hook-developmentSkill
- improve-codebase-architectureSkill
- json-canvasSkill
- kaggle-learnerSkill
- lab-knowledgeSkill
- latex-conference-template-organizerSkill
- mcp-integrationSkill
- ml-paper-writingSkill
- obsidian-basesSkill
- obsidian-cliSkill
- obsidian-experiment-logSkill
- obsidian-markdownSkill
- operon-obsidian-setupSkill
- paper-ingestSkill
- paper-searchSkill
- paper-to-socialSkill
- paper-venue-formattingSkill
- pdf-readerSkill
- planning-with-filesSkill
- plugin-structureSkill
- presentationSkill
- presenter-modeSkill
- prototypeSkill
- research-cycleSkill
- research-ideationSkill
- restore-sessionSkill
- results-analysisSkill
- results-reportSkill
- reverse-outline-flow-checkSkill
- review-responseSkill
- setup-pre-commitSkill
- skill-developmentSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. 14 are common, 0 are distinctive, and 4 are very specific to this project.
14
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 12
Remove AI-generated writing patterns from text to make it sound natural and human-written.
- Very specific: line 40
No em dashes: Never use ---, --, or — in any form.
- Very specific: line 41
No emphasis markup: Never use \emph{}, \textbf{}, or \textit{} in new text.
- Very specific: line 42
No semicolons: Never use ; to join clauses.
- Common: line 45
Remove throat-clearing openers and emphasis crutches.
- Common: line 53
Avoid binary contrasts, dramatic fragmentation, rhetorical setups.
- Common: line 74
If it sounds like a pull-quote, rewrite it.
- Common: line 110
Every sentence is the same length and structure
- Common: line 111
No opinions, just neutral reporting
- Common: line 112
No acknowledgment of uncertainty or mixed feelings
- Common: line 113
No first-person perspective when appropriate
- Common: line 114
No humor, no edge, no personality
- Common: line 118
Have opinions: Don't just report facts—react to them.
- Common: line 136
Preserve meaning: - Keep core message intact
- Common: line 186
Use progressive disclosure (core rules here, details in references/)
- Common: line 188
Add specific details instead of vague claims
- Very specific: line 189
Use simple constructions (is/are/have) where appropriate
- Common: line 193
Leave stereotypic structures intact
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Writing Anti-AI
Remove AI-generated writing patterns from text to make it sound natural and human-written.
Overview
This skill identifies and eliminates predictable AI writing patterns from prose, based on Wikipedia: Signs of AI writing, maintained by WikiProject AI Cleanup.
Core insight: LLMs use statistical algorithms to predict what should come next. The result tends toward the most statistically likely outcome that applies to the widest variety of cases—creating detectable patterns.
When to Use This Skill
Trigger phrases:
- "Humanize this text"
- "Remove AI writing patterns"
- "Make this sound more natural"
- "This sounds robotic/AI-generated"
- "Fix the AI patterns"
Use cases:
- Editing AI-generated content to sound human
- Reviewing text for AI patterns before publication
- Polishing academic or professional writing
- Removing "slop" from prose
Core Rules
0. Hard Bans for Academic Paper Text (LaTeX)
These three rules are absolute — no exceptions:
- No em dashes: Never use
---,--, or—in any form. Replace with a comma, period, or rewrite the sentence. - No emphasis markup: Never use
\emph{},\textbf{}, or\textit{}in new text. State the point directly without typographic emphasis. - No semicolons: Never use
;to join clauses. Split into two sentences with a period instead.
1. Cut Filler Phrases
Remove throat-clearing openers and emphasis crutches.
Examples:
- "In order to achieve this goal" → "To achieve this"
- "Due to the fact that" → "Because"
- "It is important to note that" → (delete)
2. Break Formulaic Structures
Avoid binary contrasts, dramatic fragmentation, rhetorical setups.
Patterns to avoid:
- Negative parallelisms: "It's not just X, it's Y"
- Rule of three: "A, B, and C" (prefer two or four items)
- Em-dash reveals: "X—Y" (just use commas — or better, rewrite)
3. Vary Rhythm
Mix sentence lengths. End paragraphs differently.
Check:
- Three consecutive sentences same length? Break one.
- Paragraph ends with punchy one-liner? Vary it.
4. Trust Readers
State facts directly. Skip softening, justification, hand-holding.
Bad: "It could potentially be argued that the policy might have some effect." Good: "The policy may affect outcomes."
5. Cut Quotables
If it sounds like a pull-quote, rewrite it.
Bad: "This represents a major step in the right direction." Good: "The company plans to open two more locations."
Common AI Patterns
Content Patterns
| Pattern | Description |
| Undue emphasis | "stands as a testament", "crucial role" |
| Promotional language | "vibrant", "rich heritage", "breathtaking" |
| Vague attributions | "Experts believe", "Observers note" |
| Superficial -ing analyses | "highlighting the importance", "ensuring that" |
| Formulaic "challenges" sections | "Despite X, faces challenges" |
Language Patterns
| Pattern | Description |
| AI vocabulary | Additionally, crucial, delve, enhance, landscape |
| Copula avoidance | "serves as", "stands for", "represents" |
| Em dash overuse | Using — more than humans |
| Rule of three | Forcing ideas into groups of three |
| Elegant variation | Excessive synonym substitution |
For comprehensive pattern lists, see:
references/patterns-english.md- Complete English pattern referencereferences/patterns-chinese.md- Complete Chinese pattern reference
Personality and Soul
Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious.
Signs of soulless writing:
- Every sentence is the same length and structure
- No opinions, just neutral reporting
- No acknowledgment of uncertainty or mixed feelings
- No first-person perspective when appropriate
- No humor, no edge, no personality
How to add voice:
Have opinions. Don't just report facts—react to them.
"I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
Vary your rhythm. Short punchy sentences. Then longer ones that take their time.
Acknowledge complexity. Real humans have mixed feelings.
"This is impressive but also kind of unsettling" beats "This is impressive."
Use "I" when it fits. First person isn't unprofessional—it's honest.
"I keep coming back to..." signals a real person thinking.
Workflow
- Identify patterns - Scan for AI patterns listed above
- Rewrite sections - Replace AI-isms with natural alternatives
- Preserve meaning - Keep core message intact
- Maintain voice - Match intended tone (formal, casual, technical)
- Add soul - Inject personality and opinions
Quick Scoring
Rate the text 1-10 on each dimension (max 50):
| Dimension | Question | Score |
| Directness | Direct statements or announcements? | /10 |
| Rhythm | Varied or metronomic? | /10 |
| Trust | Respects reader intelligence? | /10 |
| Authenticity | Sounds human? | /10 |
| Density | Anything cuttable? | /10 |
Standard:
- 45-50: Excellent, AI patterns removed
- 35-44: Good, room for improvement
- Below 35: Needs revision
Examples
See examples/ for before/after transformations:
examples/english.md- English text examples
Quick Reference
Common Fixes:
| Before | After |
| "serves as a testament to" | "shows" |
| "Moreover, it provides" | "It adds" |
| "It's not just X, it's Y" | "X does Y" |
| "Industry experts believe" | "According to [specific source]" |
Additional Resources
Reference Files
references/patterns-english.md- Complete English pattern referencereferences/phrases-to-cut.md- Filler phrases to removereferences/wikipedia-source.md- Original Wikipedia source material
Example Files
examples/english.md- English before/after examples
Best Practices
✅ DO:
- Combine pattern detection with soul injection
- Use progressive disclosure (core rules here, details in references/)
- Vary sentence structure and rhythm
- Add specific details instead of vague claims
- Use simple constructions (is/are/have) where appropriate
❌ DON'T:
- Just remove patterns without adding voice
- Leave stereotypic structures intact
- Over-correct and lose the original meaning
- Ignore language-specific patterns
- Make all sentences the same length
License
MIT
Attribution
Based on Wikipedia: Signs of AI writing, maintained by WikiProject AI Cleanup. Merges content from humanizer, humanizer-zh, and stop-slop skills.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

