gptzero
Integrate GPTZero API for AI content detection — text scanning, file upload, batch processing, per-sentence probability scores. Use when: programmatic AI content scanning, academic integrity tools, content moderation pipelines.
What this skill does
# GPTZero API Integration
## Overview
GPTZero is a specialized AI content detection service providing per-document and per-sentence AI probability scores. It detects output from GPT-family, Claude, Gemini, and other LLMs.
- **API base URL:** `https://api.gptzero.me/v2`
- **Auth:** `x-api-key` header
- **Docs:** https://gptzero.me/docs
## Instructions
### Authentication
Set `GPTZERO_API_KEY` in your environment, then use it in the `x-api-key` header for all requests.
### Single Text Analysis — POST `/v2/predict/text`
Send `{ "document": "<text>" }` as JSON. Returns a response with:
- `completely_generated_prob` (0-1) — probability the entire document is AI-generated
- `average_generated_prob` (0-1) — average AI probability across sentences
- `overall_burstiness` — burstiness score (low = more AI-like)
- `sentences[]` — per-sentence objects with `generated_prob`, `perplexity`, and `highlight_sentence_for_ai`
### Score Interpretation
| `completely_generated_prob` | Meaning |
|-----------------------------|--------------------------|
| > 0.80 | Very likely AI-generated |
| 0.50 - 0.80 | Mixed / uncertain |
| < 0.50 | Likely human-written |
### File Upload — POST `/v2/predict/files`
Upload PDF, DOCX, or TXT files using multipart form data. Returns the same document structure as text analysis.
### Batch Processing
GPTZero free tier allows ~10 req/min. For bulk scanning, process in batches with concurrency control (e.g., 3 concurrent requests with 300ms delay between batches).
### Flagged Sentences
Filter `sentences` where `highlight_sentence_for_ai === true` to extract the specific sentences GPTZero considers AI-generated.
## Examples
### Example 1: Scanning a student essay
A university teaching assistant checks a submitted essay using the GPTZero API:
```
POST https://api.gptzero.me/v2/predict/text
Headers: { "x-api-key": "gz-abc123...", "Content-Type": "application/json" }
Body: { "document": "The Industrial Revolution fundamentally transformed Western society in numerous ways. It is worth noting that the shift from agrarian economies to industrial manufacturing created unprecedented urbanization. Furthermore, the development of steam power and mechanized production significantly altered labor dynamics and social structures across Europe and North America." }
Response:
{
"documents": [{
"completely_generated_prob": 0.89,
"average_generated_prob": 0.85,
"overall_burstiness": 0.12,
"sentences": [
{ "sentence": "The Industrial Revolution fundamentally transformed Western society in numerous ways.", "generated_prob": 0.78, "highlight_sentence_for_ai": true },
{ "sentence": "It is worth noting that the shift from agrarian economies...", "generated_prob": 0.95, "highlight_sentence_for_ai": true },
{ "sentence": "Furthermore, the development of steam power...", "generated_prob": 0.91, "highlight_sentence_for_ai": true }
]
}]
}
Verdict: AI-generated (89% probability). All 3 sentences flagged.
```
### Example 2: Verifying a journalist's draft
An editor checks a news article draft before publication:
```
POST https://api.gptzero.me/v2/predict/text
Body: { "document": "At 3:47 AM on Tuesday, a pipe burst in the basement of Mel's Diner on Crenshaw Blvd, flooding the kitchen where owner Melinda Torres had just finished prepping 40 pounds of brisket for the lunch rush. 'I heard it pop and I just stood there watching the water come up,' Torres said. 'Twenty-two years in this spot and nothing like this has happened.' The city's Department of Water and Power dispatched a crew by 5 AM." }
Response:
{
"documents": [{
"completely_generated_prob": 0.08,
"average_generated_prob": 0.11,
"overall_burstiness": 0.67,
"sentences": [
{ "sentence": "At 3:47 AM on Tuesday, a pipe burst...", "generated_prob": 0.05, "highlight_sentence_for_ai": false },
{ "sentence": "'I heard it pop and I just stood there...'", "generated_prob": 0.03, "highlight_sentence_for_ai": false },
{ "sentence": "The city's Department of Water and Power...", "generated_prob": 0.12, "highlight_sentence_for_ai": false }
]
}]
}
Verdict: Human-written (8% probability). No sentences flagged.
```
## Guidelines
- Minimum text length: ~250 characters for reliable results
- Best accuracy on English text; other languages are supported but less reliable
- Paraphrased or lightly edited AI text may score lower than raw AI output
- Does not detect AI-generated images or code
- Free tier: ~10,000 words/month, ~10 req/min; check https://gptzero.me/pricing for paid plans
- Handle HTTP 429 (rate limit) by waiting 60s and HTTP 402 (quota exceeded) by checking your plan
- Always route flagged content to human review — no detector is 100% accurate
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.