Is the AI Tells skill free?

Yes. The skill itself is free from kdgbalmer/ai-tells. SkillProof publishes the install command and an independent test verdict at no cost.

What is the AI Tells SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install AI Tells?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use AI Tells with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

AI Tells

Flags AI writing fingerprints (delve, em dashes, 'not X it's Y') and rewrites clean.

by kdgbalmer · kdgbalmer/ai-tells

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 14, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · b760a65

Ran it on a 134-word tell-stuffed marketing paragraph: it caught all 17 planted tells by exact category (negative parallelism, vague attribution, 'testament'/'paradigm shift', outline-style conclusion) and scored density at ~13/100 words, something my unguided baseline edit did instinctively but couldn't name or quantify.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What AI Tells does

Audits a draft against a catalogue of AI writing tells — vocabulary (delve, leverage, robust), structural (negative parallelism, bullet-everything), tone ('Great question!'), and punctuation (em-dash overuse) — then produces a clean rewrite that keeps the writer's voice. Triggers on 'humanize this', 'does this sound like ChatGPT', 'remove the AI smell', or when a user pastes a draft asking for writing feedback without naming AI.

How to install AI Tells

git clone https://github.com/kdgbalmer/ai-tells
cd ai-tells
mkdir -p ~/.claude/skills
cp -r . ~/.claude/skills/ai-tells

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger AI Tells

/ai-tells Flags AI writing fingerprints (delve, em dashes, 'not X it's Y') and rewrites clean.

It also activates on plain-language prompts like these:

This paragraph sounds AI-written, can you clean it up?
Remove the em dashes and delve-isms from this marketing copy
Check this paragraph for AI writing tells and rewrite it

Frequently asked questions

Is the AI Tells skill free?: Yes. The skill itself is free from kdgbalmer/ai-tells. SkillProof publishes the install command and an independent test verdict at no cost.
Does AI Tells work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 14, 2026. Verdict: Tested · Works. Ran it on a 134-word tell-stuffed marketing paragraph: it caught all 17 planted tells by exact category (negative parallelism, vague attribution, 'testament'/'paradigm shift', outline-style conclusion) and scored density at ~13/100 words, something my unguided baseline edit did instinctively but couldn't name or quantify.
What is the AI Tells SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install AI Tells?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use AI Tells with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.