More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    🕵️ AI Tell Detector

    1

    Identify and Humanize AI-Generated Prose Modern LLMs have specific stylistic signatures—often called "AI slop"—that make content feel robotic, overly formal, or repetitive.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    🕵️ AI Tell Detector

    🕵️ AI Tell Detector

    Example session with this skill installed

    Scan 'blog-draft.md' for AI signals and suggest how to fix the cadence.

    • Read your context and instructions
    • Compiled the ai tell detector

    AI Tell Audit: blog-draft.md

    • Line 12 (Vocabulary): Used "delve deep into." Suggestion: Use "explore" or "analyze."

    Lines 15-20 (Cadence): 4 consecutive sentences of 12-14 words. Suggestion: Break up the flow with a short sentence.

    • Line 34 (Punctuation): Excessive em-dash use detected.
    blog-draft.md

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Identify and Humanize AI-Generated Prose

    Modern LLMs have specific stylistic signatures—often called "AI slop"—that make content feel robotic, overly formal, or repetitive. The AI Tell Detector is a specialized diagnostic tool designed for developers, editors, and technical writers who need to audit drafts for these recognizable patterns before publication.

    What it does

    Using a combination of pattern-matching scripts and cadence analysis, the skill scans your Markdown or text files to identify specific linguistic "tells." It doesn't just give a generic "AI score"; it provides a line-level audit of structural and vocabulary issues that trigger human suspicion.

    • Vocabulary Auditing: Flags overused AI-isms like "delve," "tapestry," "testament," and "comprehensive."
    • Structural Analysis: Identifies uniform sentence lengths and repetitive antithesis constructions (e.g., "Not only X, but also Y").
    • Punctuation & Syntax: Detects em-dash overuse and excessive hedging phrases that dilute your message.
    • Actionable Feedback: Every finding includes a specific suggestion for how to revise the text for a more natural, human flow.

    Why use this skill?

    While standard AI detectors provide a "pass/fail" percentage, this skill acts as a mechanical editor. It shows you exactly why a piece of writing feels "off," allowing you to maintain your voice while removing the artifacts of LLM generation. It supports any text or Markdown-based workflow and is optimized for technical documentation and blog drafts.

    Heuristic detector. The signals it reports are a probabilistic style read, not proof of authorship, and a strong human writer can legitimately trip some of them. Treat findings as places to look, not verdicts. It surfaces tells; revising them is your call.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 5 months ago

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    **/*.md
    **/*.txt

    Read-only. Computes its cadence and density signals with the standard library and prints findings with rule id, severity, file, and line. It reads no environment variables and writes nothing.

    Listed5 months ago

    What's inside

    Frequently Asked Questions

    Unlike standard detectors that give a vague percentage score, this skill provides a line-level audit identifying specific 'tells' like repetitive sentence structures and overused vocabulary, acting as a diagnostic editor rather than a simple gatekeeper.

    The AI Tell Detector identifies and flags problematic patterns for you to address; it does not automatically rewrite your content, ensuring you maintain full creative control and the final human touch.

    This skill is designed to process Markdown and plain text files, making it a perfect fit for technical documentation, blog drafts, and developer-focused editorial workflows.

    The skill analyzes your text for several specific patterns: the 'delve/tapestry' vocabulary cluster, 'Not only X, but Y' sentence constructions, em-dash overuse, and uniform sentence cadence.

    Your purchase includes the core detection engine and any subsequent logic updates that expand the database of flagged AI-isms as LLM linguistic patterns evolve.

    Once added to your workspace, simply provide the draft you want to audit; the skill will scan the text and return a detailed list of flagged locations along with specific suggestions for manual revision.

    New in Writing & Content