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.

3 starsAI, LLMs & Agents

Install

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

npx skills add aragossa/ai-tell-detector --skill ai-tell-detector

Manual install

git clone --depth 1 https://github.com/aragossa/ai-tell-detector.git /tmp/ai-tell-detector
mkdir -p ~/.claude/skills
cp -r /tmp/ai-tell-detector/en/ai-tell-detector ~/.claude/skills/ai-tell-detector

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 Tell Detector

Human AI-detectors (Grammarly, Gemini, GPTZero and similar) and human readers catch the
same handful of patterns. This skill runs that same audit before you publish, so you
catch it instead of your reader.

## Input

The finished draft (post, comment, email, DM). No other iteration needed — feed it the
final text, not a topic.

## What it checks

1. **Rhetorical symmetry.** "It's not X — it's Y", "not just A, but B", triads ("faster,
   better, stronger"). Flag every instance with the line it's on.
2. **Filler transitions and hedges.** "In today's world", "It's worth noting",
   "Let's be honest", "At the end of the day", "Spoiler:". These add length, not meaning.
3. **Uniform rhythm and structure.** If every sentence is roughly the same length and
   every paragraph the same shape, call it out. Also check the beat-by-beat shape of
   the whole piece: situation → contrast → lesson → plug → question is a template, not
   a style — flag it even if no single sentence is the problem. Concrete variance check:
   real human prose mixes a long run-on sentence full of asides with a fragment right
   after it; paragraphs of 2-4 sentences of near-identical length, kept up through the
   whole piece, are a flag on their own.
4. **Generic abstraction over specifics.** Claims with no number, name, date, or quote
   behind them ("many companies struggle with...", "in my experience..." with nothing
   concrete after it).

Read the full skill on GitHub

Details

Skill name: ai-tell-detector
Repository: aragossa/ai-tell-detector
Path: en/ai-tell-detector/SKILL.md
License: MIT
Repo updated: 4 September 2026
Listed in: karanb192/awesome-claude-skills

FAQ

What does the AI Tell Detector skill do?

How do I install the AI Tell Detector skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add aragossa/ai-tell-detector --skill ai-tell-detector. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is AI Tell Detector popular?

It lives in aragossa/ai-tell-detector, which has 3 GitHub stars and 0 forks, and is included in 1 curated skill list.

Related skills

Privacyscrubber Guard

moxno/privacyscrubber-mcp

Pre-ingestion zero-trust PII, secret, and regulated data sanitization skill for AI coding agents (Claude Code, Cursor, Codex, Gemini CLI, Windsurf) via @privacyscrubber/mcp-server. Intercepts files, shell commands, and prompts in local RAM with 30 specialized industry profiles and SHA-256 compliance receipts.

AI, LLMs & AgentsIn 1 list

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

Benchmark Yylo

yylo-dev/yylo-skills

Prepare reviewed cases and frozen checklists, compare models and harnesses, and independently evaluate retained outputs with YYLO Benchmark's thin trusted-host runner.

AI, LLMs & AgentsIn 1 list

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

Cohesivity

cohesivity-org/cohesivity-plugin

Backend and infra for a project via Cohesivity (cohesivity.ai). Provisions Postgres, hosting and deploys, auth and social login, realtime websockets, an agent-native email inbox, object and vector storage, Redis, cron, and AI model APIs (OpenAI, Anthropic, Deepgram, Exa) through one HTTP API. Use when a valid .cohesivity file exists, a Cohesivity MCP is available, the user names Cohesivity, or the project needs a backend or any of these services and no competing provider was chosen.

AI, LLMs & AgentsIn 1 list

Wikipedia Not AI

Valpep/wiki-ai-detector

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.

AI, LLMs & Agents

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