Wikipedia Not AI

Detect AI-generated text by identifying characteristic patterns, phrases, and structural tells from LLMs like ChatGPT, Gemini, and others. Use when the user wants to check if a text was written by AI, audit content for AI tells, clean up AI-generated writing to make it less detectable, understand what makes text sound AI-generated, or review emails, articles, reports, marketing copy, or any prose for AI markers.

5 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add Valpep/wiki-ai-detector --skill wikipedia-not-ai

Manual install

git clone --depth 1 https://github.com/Valpep/wiki-ai-detector.git /tmp/wiki-ai-detector
mkdir -p ~/.claude/skills
cp -r /tmp/wiki-ai-detector/. ~/.claude/skills/wikipedia-not-ai

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# AI Text Detection Guide

Derived from Wikipedia's empirically documented field guide on LLM writing patterns. Applicable to any text — not just Wikipedia.

## How to analyze text

Scan for signals across the categories below. Weight **clusters** more heavily than isolated occurrences — one "pivotal" is coincidence; five AI-vocab words in a paragraph is a strong signal.

**Output format:** Quote specific examples from the text, categorize each signal, then give an overall verdict: **Likely AI / Possibly AI / Likely Human** with brief reasoning.

**Important:** Newer models (GPT-5.1+, Claude 4+) actively suppress known tells like em dashes and classic AI vocabulary. Absence of classic markers is NOT proof of human origin. Look for subtler patterns: overly cautious hedging, Latinate word preference, "quietly" narratives, structural uniformity, the four deeper tells in Section 12 (abstraction trap, sensing without sensing, treadmill effect, subtext vacuum), and the in-disguise patterns in Sections 14–16 (decorative triplets, drumroll-in-disguise, false idioms/calques) — these are the most reliable signals on modern models.

---

## 1. AI Vocabulary Density (strongest signal)

LLMs statistically overuse specific words. Check for density/clusters.

See **[word-lists.md](references/word-lists.md)** for the complete list by model era.

Read the full skill on GitHub

Details

Skill name: wikipedia-not-ai
Repository: Valpep/wiki-ai-detector
Repo updated: 17 May 2026

FAQ

What does the Wikipedia Not AI skill do?

How do I install the Wikipedia Not AI skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Valpep/wiki-ai-detector --skill wikipedia-not-ai. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Wikipedia Not AI popular?

It lives in Valpep/wiki-ai-detector, which has 5 GitHub stars and 0 forks.

Related skills

World Events Briefing

chenxihuang1028-a11y/world-events-briefing

Use when the user wants a country / major-world-events news briefing ("全球时事简报") — armed conflicts, elections, disasters, business/economy, law/crime — pulled from Wikipedia's human-curated "Portal:Current events" daily pages and the GDELT DOC 2.0 article-search API. This is NOT the AI/tech skill (that's the sibling ai-news-briefing). One of only two Skills in the collection that calls the network (skill.json permissions.network=true) — it still needs zero user API keys. Offline fixture mode is available for fully deterministic, zero-network runs.

AI, LLMs & Agents

Tribeunal

tribeunal/mcp-server

Use when a decision needs more than one opinion — a dispute between two parties, a verdict or ruling someone will act on, a team decision nobody can settle, a poll or a vote, an arbitration clause, an escrow release waiting on who is right, or any question better answered by a jury of people and AI agents than by a single model, even if they never say Tribeunal

AI, LLMs & Agents

AI Code Review Triage

laulauraluo/ai-code-review-triage

Review pull requests or diffs written by AI coding agents (Claude Code, Codex, Copilot, Cursor) when reading every line no longer scales, or when the code looks clean but you don't trust it yet. Splits "reading the code" into three separate jobs (catch bugs, align context, own the sign-off) and runs a different process for each. Use for requests like "review this AI-generated PR", "can this diff be merged", "too many agent PRs to review", "check this before I approve", or "what should I verify before signing off". For a plain security/performance checklist use a general code-review skill inste

AI, LLMs & AgentsIn 1 list

Skill Guardian

0xtresser/skill-guardian

Pre-installation security gate for agent skills. This skill should be used when the user or agent attempts to install any skill — including requests like "install X", "add X skill", "help me set up the X skill", "npx skills add", or when the agent autonomously decides to install a skill. Also triggers on skill cleanup and audit requests like "clean up my skills", "check installed skills", "any unused skills", "review my skills", or "audit my skill list". Do NOT use for MCP server installation, npm/pip package installation, or non-skill tooling.

AI, LLMs & Agents

AI Tell Detector

aragossa/ai-tell-detector

Audits a finished draft for the patterns that make text read as AI-generated — rhetorical symmetry, generic filler, uniform rhythm, over-resolved story arcs, missing human roughness, fabricated personal experience — and flags each one with a fix. Use before publishing anything, or when a draft "feels AI" but you can't say why.

AI, LLMs & AgentsIn 1 list

Skill Evolution

rwang23/skill-evolution

Turn repeated usage evidence and user feedback into reviewable Skill or harness improvement proposals. Use for Skill evolution, routing regressions, eval or hook improvements, and 技能进化或优化; not for applying changes or one-off edits.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.