Detect Ai

Name: Detect Ai
Author: humanizerai

humanizerai/agent-skills

776 installs
38 repo stars
Updated February 5, 2026
humanizerai/agent-skills

detect-ai is a Claude Code skill that calls the HumanizerAI API to score text from 0-100 with detailed AI-detection metrics for developers who must vet content before publishing or submitting.

About

detect-ai is a user-invocable HumanizerAI agent skill that analyzes text via POST https://humanizerai.com/api/v1/detect with a Bearer HUMANIZERAI_API_KEY. It returns a 0-100 AI-likelihood score plus detailed metrics in an actionable report when users run /detect-ai with text arguments. The skill allows WebFetch for API calls and fits pre-publish checks for blogs, docs, or submissions that must meet human-writing policies. Developers reach for detect-ai when they need a quick automated screen rather than manual guesswork about AI-generated tone or structure.

Returns overall AI score 0-100
Provides perplexity, burstiness, readability metrics
Supports pre-publish checks

Detect Ai by the numbers

776 all-time installs (skills.sh)
+27 installs in the week ending Aug 2, 2026 (Skillselion tracking)
Ranked #1,341 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 3, 2026 (Skillselion catalog sync)

npx skills add https://github.com/humanizerai/agent-skills --skill detect-ai

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/humanizerai/agent-skills/detect-ai.svg)](https://skillselion.com/skills/humanizerai/agent-skills/detect-ai)

Installs	776
repo stars	★ 38
Last updated	February 5, 2026
Repository	humanizerai/agent-skills ↗

How do you detect AI-generated text before publishing?

Analyze text to detect AI-generated content and receive a score with metrics before publishing.

Who is it for?

Developers or editors running pre-publish checks on articles, README drafts, or submissions that require AI-detection scoring.

Skip if: Teams without a HumanizerAI API key, legal plagiarism analysis, or rewriting text to sound human—that needs a separate humanizer workflow.

When should I use this skill?

User runs /detect-ai or asks to check if text was AI-written before publishing or submitting.

What you get

AI detection score from 0-100, detailed metric breakdown, and a formatted review summary for the submitted text.

AI likelihood score
detection metric report

By the numbers

Returns AI detection score on a 0-100 scale

Files

SKILL.mdMarkdownGitHub ↗

Detect AI Content

Analyze text to determine if it was written by AI using the HumanizerAI API.

How It Works

When the user invokes /detect-ai, you should:

1. Extract the text from $ARGUMENTS 2. Call the HumanizerAI API to analyze the text 3. Present the results in a clear, actionable format

API Call

Make a POST request to https://humanizerai.com/api/v1/detect:

Authorization: Bearer $HUMANIZERAI_API_KEY
Content-Type: application/json

{
  "text": "<user's text>"
}

API Response Format

The API returns JSON like this:

{
  "score": {
    "overall": 82,
    "perplexity": 96,
    "burstiness": 15,
    "readability": 23,
    "satPercent": 3,
    "simplicity": 35,
    "ngramScore": 8,
    "averageSentenceLength": 21
  },
  "wordCount": 82,
  "sentenceCount": 4,
  "verdict": "ai"
}

IMPORTANT: The main AI score is score.overall (not score directly). This is the score to display to the user.

Present Results Like This

## AI Detection Results

**Score:** [score.overall]/100 ([verdict])
**Words Analyzed:** [wordCount]

### Metrics
- Perplexity: [score.perplexity]
- Burstiness: [score.burstiness]
- Readability: [score.readability]
- N-gram Score: [score.ngramScore]

### Recommendation
[Based on score.overall, suggest whether to humanize]

Score Interpretation (use score.overall)

0-20: Human-written content
21-40: Likely human, minor AI patterns
41-60: Mixed signals, could be either
61-80: Likely AI-generated
81-100: Highly likely AI-generated

Error Handling

If the API call fails: 1. Check if HUMANIZERAI_API_KEY is set 2. Suggest the user get an API key at https://humanizerai.com 3. Provide the error message for debugging

Related skills

Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k

Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k

CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k

Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k

Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72

Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10

FAQ

What API does detect-ai call?

detect-ai sends a POST request to https://humanizerai.com/api/v1/detect with Authorization Bearer HUMANIZERAI_API_KEY and returns a 0-100 score plus detailed AI-detection metrics.

How do you invoke detect-ai in Claude Code?

Run the user-invocable /detect-ai command with the text to analyze in arguments; the skill extracts input, calls HumanizerAI, and formats the score and metrics for review.

AI & Agent Buildingseocontent