AI Writing Detector
Scan text for AI-generated patterns and identify artificial writing characteristics.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/dbs-ai-check-dontbesilent2025/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Use when you want text checked for AI-generated patterns — scans for the telltale phrasing and structure of machine writing.
What this skill does
This skill scans your text for artificial writing patterns and pinpointed characteristics of machine-generated content. Rather than helping you hide AI traces, it identifies them to help you see your own writing clearly and develop your authentic voice. The tool recognizes that perfect writing—too smooth, too uniform, without hesitation or rough edges—signals inauthenticity, not quality.
What it does
- Scans submitted text against 22 distinct AI writing fingerprints, from over-perfect emotional arcs to repetitive connective phrases
- Generates a detailed detection report that flags each AI pattern with its location in your text, specific explanation, and severity rating (strong signal, medium signal, or weak signal)
- Adapts detection rules by content type—short-form video scripts, long-form social posts, and academic writing are assessed differently
- Offers guided revision conversations that ask you clarifying questions about your intent behind each flagged pattern, rather than rewriting the text for you
- Avoids false positives by excluding techniques that are legitimate in certain genres or writing styles (like consistent closing statements in video scripts)
How to use it
Submit any text you'd like examined. The skill will analyze it and return a structured report showing each AI-pattern match with direct quotes and straightforward explanations. If the scan reveals no significant artificial characteristics, it will say so directly. After receiving results, you can say "I want to revise" to begin a back-and-forth conversation focused on understanding what you meant to express, then finding alternative phrasing that matches your own voice and intent.
Note: this skill's internal instructions are written in Chinese. Claude reads them natively and will work with you in English.
Related skills
Generative Code Art
anthropics
Create algorithmic art with p5.js using randomness and interactive parameters.
PPTX Text Extractor
axoviq-ai
Extract text and speaker notes from PowerPoint presentations.
Directory Submissions Tracker
coreyhaines31
Submit your product to startup and SaaS directories for backlinks and discovery.
Executive Stress-Test Mentor
alirezarezvani
Challenge your business decisions and plans with adversarial questions before they fail.