Is the AI Tells Review skill free?

Yes. The skill itself is free from NickCrew/Claude-Cortex. SkillProof publishes the install command and an independent test verdict at no cost.

What is the AI Tells Review SkillProof Score?

9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install AI Tells Review?

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 Review 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 Review

Structural AI-prose review: four-family rubric (rhythm, hedging, rhetorical reflexes, performative emphasis) with line-cited fixes.

by NickCrew · NickCrew/Claude-Cortex

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 329399e

Fed a paragraph seeded with real tells ('leverages cutting-edge', 'proves the framework' repeated three times, Furthermore/Additionally/Ultimately openers) through both passes: unguided editing flags the buzzwords informally, while the skill produces a family-tagged report (Contrastive bold, Coined-phrase tic, Manufactured both-sidesing) with a reads-very-AI verdict and a rewrite explicitly gated on user consent.

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 9/10
Docs & honesty 5/5

What AI Tells Review does

Runs a judgment-based pass on public-facing prose that still reads as AI-written after a mechanical scan, citing each tell by family (structural reflexes, tonal hedging, performative emphasis, rhythm patterns), the offending line, and a fix-direction, then offers a gated rewrite that preserves structure and facts. Triggers on phrases like "review for AI tells", "does this read AI", or "strip the AI smell"; explicitly defers the mechanical/vocabulary pass to its companion skill ai-tells-scan.

How to install AI Tells Review

git clone https://github.com/NickCrew/Claude-Cortex
mkdir -p ~/.claude/skills
cp -r Claude-Cortex/skills/ai-tells-review ~/.claude/skills/ai-tells-review

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

Commands — how to trigger AI Tells Review

/ai-tells-review Structural AI-prose review: four-family rubric (rhythm, hedging, rhetorical reflexes, performative emphasis) with line-cited fixes.

It also activates on plain-language prompts like these:

Does this paragraph read like it was written by AI to you?
Review this blog post for AI tells like hedging and rhythm patterns
Strip the AI smell out of this documentation section for me

Frequently asked questions

Is the AI Tells Review skill free?: Yes. The skill itself is free from NickCrew/Claude-Cortex. SkillProof publishes the install command and an independent test verdict at no cost.
Does AI Tells Review work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Fed a paragraph seeded with real tells ('leverages cutting-edge', 'proves the framework' repeated three times, Furthermore/Additionally/Ultimately openers) through both passes: unguided editing flags the buzzwords informally, while the skill produces a family-tagged report (Contrastive bold, Coined-phrase tic, Manufactured both-sidesing) with a reads-very-AI verdict and a rewrite explicitly gated on user consent.
What is the AI Tells Review SkillProof Score?: 9.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install AI Tells Review?: 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 Review 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.