1
    🕵️ AI Tell Detector

    🕵️ AI Tell Detector

    by JustHandled Labs

    Scan a draft for the tells that make writing read as AI-generated, so you can revise them before publishing. Flags the delve/tapestry/underscore/harness vocabulary cluster, hedging and filler phrases ("it's worth noting," "in today's digital age"), the "not just X, it's Y" antithesis tic, em-dash overuse, rule-of-three pile-ups, unusually uniform sentence cadence, and generic conclusion openers. It marks locations for you to fix; it does not rewrite.

    Updated Jun 2026
    Security scanned
    Cursor

    $12

    · or 60 credits

    30-day refund guarantee

    Secure checkout via Stripe

    Included in download

    • Audit blog posts for recognizable "AI-isms" before publishing
    • Identify robotic sentence structures and uniform cadence in drafts
    • terminal, file_read automation included
    • Ready for Cursor
    • Instant install

    Sample input

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

    Sample output

    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.

    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.

    Use Cases

    • Audit blog posts for recognizable "AI-isms" before publishing
    • Identify robotic sentence structures and uniform cadence in drafts
    • Receive line-level revision suggestions to humanize technical documentation
    • Scan entire directories of Markdown files for stylistic red flags

    Reviews

    No reviews yet - be the first to share your experience.

    Only users who have downloaded or purchased this skill can leave a review.

    Security Scanned

    Passed automated security review

    Permissions

    Terminal / Shell
    Read Files

    File Scopes

    ai-tell-detector/**
    **/*.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.

    Tags

    writing-assistant
    content-editing
    ai-detection
    editorial-tools
    markdown

    Works with any agent that can read a draft and run a local Python script (Claude Code, Cursor, Codex CLI, and other SKILL.md-compatible agents). Standard library only, no install step. Reads Markdown and text files. Read-only.

    Creator

    JustHandled Labs

    JustHandled Labs creates focused agent skills and workflow packs for Claude, Codex, Cursor, and AI-assisted builders. Each tool is designed around a real repeatable task: cleaner commits, better PRs, stronger handoffs, safer repo hygiene, clearer documentation, and less copy-paste chaos. The goal is not generic AI productivity. The goal is specific workflows that are easier to run, review, and repeat. Maintained by H.J. Westerfield, with a background in communications, editing, project coordination, customer support, and practical AI systems. JustHandled Labs builds tools for people who want useful automation without theatrical complexity.

    Frequently Asked Questions

    Learn More About AI Agent Skills

    More Premium Skills

    inline-comment

    inline-comment

    Best way to steer your agents, effortlessly.

    $9.994 installs

    designing-hybrid-context-layers

    Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.

    $1015 installs

    consumer-motivation-analyzer

    Go beyond surface-level feedback to uncover the psychological drivers and hidden motivations behind buyer behavior.

    $199 installs

    keyword-research

    Transform URLs or product lists into SEO keyword research packs with Google Ads data and intent-based clustering.

    $77 installs

    $12