- Home
- Skills
- Writing & Content
- ai-smell-detector
ai Smell Detector
Identify robotic prose and AI-generated patterns with a 0-5 diagnostic score and structured linguistic analysis.
Free
Works with the AI Agents you already use
ai-smell-detector
Example session with this skill installed
Triage this draft for robotic tone: "The utilization of optimization strategies can enhance efficiency. This will enhance growth. This will enhance results."
- Read your context and instructions
- Compiled the ai-smell-detector
Score: 4/5 (Heavy AI Smell)
Signals
- Symmetrical bullet points (all 3 lines start with 'Enhance...')
- Abstract noun stacking ('utilization of optimization strategies')
- Generic intro/outro
Recommendation: High risk of detection. Full rewrite or pass through humanize-writing skill.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
The AI Smell Detector is a specialized diagnostic utility for developers and content managers who need to objectively evaluate text for "robotic" or machine-generated characteristics. It moves beyond simple binary detection to provide a nuanced 0-5 scoring system, identifying the specific linguistic markers—such as abstract noun stacking, excessive hedging, and symmetrical paragraph structures—that trigger AI detection filters.
Why use this skill
Simply prompting an LLM to "check for AI" often results in hallucinatory false positives or vague feedback. This skill uses a rigorous rubric to separate style issues from meaning issues, providing a technical triage of a draft before you commit resources to a rewrite. It identifies precise "smells" like generic openings and repetitive paraphrasing, allowing for targeted human intervention rather than blind guessing.
Supported workflows
- Pre-publication Triage: Automatically score drafts to decide if they need a manual polish or an automated humanization pass.
- Content Quality Assurance: Audit large batches of copy to ensure a consistent, natural brand voice.
- Source Analysis: Determine if external submissions or research summaries are original or machine-spun.
The output is a structured diagnostic report featuring a severity score, a list of strongest signals, and a strategic recommendation for remediation.
- May struggle with extremely short text snippets (<50 words).
- Cannot detect AI-generated facts or hallucinations, only linguistic patterns.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
69 uses
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 7 months ago
- Free with an Agensi account
Permissions
No special permissions declared or detected