Not in the top 1,000 by GitHub stars

lynote-ai/ai-text-detector

A cautious, explainable AI text detector for local workflows and coding agents. Need production detection in your app? Try the Lynote AI Detector API → lynote.ai/ai-detector-api

Claude Code Codex Engineering Writing

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

ae52c665b903 → ae52c665b903

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → ae52c665b903

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit ae52c665b9030cddc7292196c8d6ec249153f617

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/lynote-ai/ai-text-detector.git .hotskills/lynote-ai-ai-text-detector && git -C .hotskills/lynote-ai-ai-text-detector checkout --detach ae52c665b9030cddc7292196c8d6ec249153f617
# Copy each selected skill directory from .hotskills/lynote-ai-ai-text-detector into .claude/skills/<skill-name>/

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/lynote-ai/ai-text-detector.git .hotskills/lynote-ai-ai-text-detector && git -C .hotskills/lynote-ai-ai-text-detector checkout --detach ae52c665b9030cddc7292196c8d6ec249153f617
# Copy each selected skill directory from .hotskills/lynote-ai-ai-text-detector into .agents/skills/<skill-name>/

657GitHub stars

1star in 7 days

1skill in this repository

4commits in 30 days

Heat

2.8

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

ai-text-detector-github /

How it works

ai-text-detector-github

When your agent uses it

Detect whether a passage shows AI-like writing signals and return an explainable risk estimate with confidence, caveats, and next steps.

What it loads into context

Frontmatter

37 tokens

Always available to the agent

SKILL.md

628 tokens

When the skill is activated

Reference documents

31,925 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Overview
Trigger Conditions
Required Behavior
Execution Flow
Output Guidance
Repository Layout
Development Notes

Scripts executed separately

Makefile
detection-model-pipeline/Makefile
detection-model-pipeline/code/harness/validate_demo_data.py
detection-model-pipeline/code/harness/validate_docs.py
detection-model-pipeline/code/harness/validate_manifest.py
detection-model-pipeline/code/i_prepare_hier_dataset.py
detection-model-pipeline/code/j_train_hier_model.py
detection-model-pipeline/code/k_calibrate_hier_model.py
detection-model-pipeline/code/l_eval_hier_model.py
detection-model-pipeline/code/m_serve_hier_api.py
detection-model-pipeline/code/sentence_splitter.py
detection-model-pipeline/model_entity/hier_aidetect_model.py
detection-model-pipeline/model_entity/hier_model_factory.py
detection-model-pipeline/model_entity/hier_xlmr_model.py
detection-model-pipeline/tests/conftest.py
detection-model-pipeline/tests/test_dynamic_batcher.py
detection-model-pipeline/tests/test_harness_validators.py
detection-model-pipeline/tests/test_hier_aidetect_model.py
detection-model-pipeline/tests/test_hier_xlmr_model.py
detection-model-pipeline/tests/test_i_prepare_hier_dataset.py
detection-model-pipeline/tests/test_j_train_hier_model.py
detection-model-pipeline/tests/test_k_calibrate_hier_model.py
detection-model-pipeline/tests/test_l_eval_hier_model.py
detection-model-pipeline/tests/test_m_serve_hier_api.py
detection-model-pipeline/tests/test_sentence_splitter.py
detection-model-pipeline/tools/refresh_demo_manifest.py
scripts/benchmark.py
scripts/detect.py
scripts/evaluate_hc3.py
scripts/setup.sh
src/aidetect/__init__.py
src/aidetect/cli.py
src/aidetect/core.py
tests/test_cli.py
tests/test_core.py

Files

.claude/skills/ai-detector/SKILL.mddoc1,269 bytes
.gitattributesasset66 bytes
.github/workflows/ci.ymlasset1,226 bytes
AGENTS.mddoc915 bytes
CONTRIBUTING.mddoc1,053 bytes
LICENSEasset1,081 bytes
Makefileruns331 bytes
README.mddoc11,514 bytes
README.zh-CN.mddoc11,548 bytes
SECURITY.mddoc728 bytes
SKILL.mdcore2,777 bytes
SKILL.mdcore2,777 bytes
SKILL.mdcore2,777 bytes
SKILL.mdcore2,777 bytes
SKILL.mdcore2,777 bytes
assets/hero.svgasset3,514 bytes
assets/score-bands.svgasset2,006 bytes
assets/templates/report.mddoc245 bytes
assets/workflow.svgasset2,988 bytes
detection-model-pipeline/.env.exampleasset380 bytes
detection-model-pipeline/.gitattributesasset175 bytes
detection-model-pipeline/.github/workflows/ci.ymlasset333 bytes
detection-model-pipeline/.gitignoreasset263 bytes
detection-model-pipeline/LICENSEasset1,082 bytes
detection-model-pipeline/Makefileruns7,287 bytes
detection-model-pipeline/README.mddoc7,602 bytes
detection-model-pipeline/README.zh-CN.mddoc6,927 bytes
detection-model-pipeline/code/harness/validate_demo_data.pyruns19,893 bytes
detection-model-pipeline/code/harness/validate_docs.pyruns4,465 bytes
detection-model-pipeline/code/harness/validate_manifest.pyruns4,598 bytes
detection-model-pipeline/code/i_prepare_hier_dataset.pyruns12,268 bytes
detection-model-pipeline/code/j_train_hier_model.pyruns25,321 bytes
detection-model-pipeline/code/k_calibrate_hier_model.pyruns4,224 bytes
detection-model-pipeline/code/l_eval_hier_model.pyruns9,013 bytes
detection-model-pipeline/code/m_serve_hier_api.pyruns21,710 bytes
detection-model-pipeline/code/sentence_splitter.pyruns1,417 bytes
detection-model-pipeline/data/README.mddoc2,776 bytes
detection-model-pipeline/data/README.zh-CN.mddoc2,546 bytes
detection-model-pipeline/data/demos/01_prepare/train_hier_demo.jsonlasset15,822 bytes
detection-model-pipeline/data/demos/01_prepare/val_hier_demo.jsonlasset2,837 bytes
detection-model-pipeline/data/demos/02_calibrate/calibration_demo.jsonasset113 bytes
detection-model-pipeline/data/demos/03_serve/detect_response_demo.jsonasset3,430 bytes
detection-model-pipeline/data/demos/manifest.yamlasset1,052 bytes
detection-model-pipeline/docs/API.mddoc11,320 bytes
detection-model-pipeline/docs/API.zh-CN.mddoc11,407 bytes
detection-model-pipeline/docs/ARCHITECTURE.mddoc6,478 bytes
detection-model-pipeline/docs/ARCHITECTURE.zh-CN.mddoc5,780 bytes
detection-model-pipeline/docs/DATA_CONSTRUCTION.mddoc5,331 bytes
detection-model-pipeline/docs/DATA_CONSTRUCTION.zh-CN.mddoc4,834 bytes
detection-model-pipeline/docs/MODEL.mddoc9,836 bytes
detection-model-pipeline/docs/MODEL.zh-CN.mddoc8,681 bytes
detection-model-pipeline/manifest.yamlasset4,495 bytes
detection-model-pipeline/model_entity/hier_aidetect_model.pyruns15,271 bytes
detection-model-pipeline/model_entity/hier_model_factory.pyruns840 bytes
detection-model-pipeline/model_entity/hier_xlmr_model.pyruns12,396 bytes
detection-model-pipeline/requirements-model.txtdoc189 bytes
detection-model-pipeline/requirements-test.txtdoc49 bytes
detection-model-pipeline/requirements.txtdoc49 bytes
detection-model-pipeline/tests/conftest.pyruns286 bytes
detection-model-pipeline/tests/test_dynamic_batcher.pyruns5,094 bytes
detection-model-pipeline/tests/test_harness_validators.pyruns7,245 bytes
detection-model-pipeline/tests/test_hier_aidetect_model.pyruns7,167 bytes
detection-model-pipeline/tests/test_hier_xlmr_model.pyruns3,891 bytes
detection-model-pipeline/tests/test_i_prepare_hier_dataset.pyruns4,139 bytes
detection-model-pipeline/tests/test_j_train_hier_model.pyruns11,861 bytes
detection-model-pipeline/tests/test_k_calibrate_hier_model.pyruns993 bytes
detection-model-pipeline/tests/test_l_eval_hier_model.pyruns884 bytes
detection-model-pipeline/tests/test_m_serve_hier_api.pyruns6,184 bytes
detection-model-pipeline/tests/test_sentence_splitter.pyruns2,288 bytes
detection-model-pipeline/tools/refresh_demo_manifest.pyruns5,797 bytes
docs/AGENT_PROMPT.mddoc639 bytes
docs/BENCHMARK.mddoc1,211 bytes
docs/HC3_EVALUATION.mddoc2,129 bytes
examples/sample_ai_like.txtdoc866 bytes
examples/sample_human_like.txtdoc572 bytes
pyproject.tomlasset838 bytes
references/api-reference.mddoc1,062 bytes
requirements.txtdoc129 bytes
scripts/benchmark.pyruns6,501 bytes
scripts/detect.pyruns286 bytes
scripts/evaluate_hc3.pyruns8,149 bytes
scripts/setup.shruns420 bytes
src/aidetect/__init__.pyruns95 bytes
src/aidetect/cli.pyruns1,577 bytes
src/aidetect/core.pyruns6,569 bytes
tests/test_cli.pyruns1,974 bytes
tests/test_core.pyruns2,446 bytes

Read SKILL.md


# AI Text Detector Skill

## Overview

This skill wraps the local `ai-detector-skill` analyzer into a reusable open source Codex-style skill.

It is designed for:

- essays
- emails
- articles
- reviews
- forum posts
- other prose where a user asks whether the writing may be AI-generated

View the complete source on GitHub

Skills included

ai-text-detector-github

Repository facts

License: MIT
Created: May 25, 2026
Last pushed: Oct 13, 2026
Forks: 30
Open issues: 3
Project activity: Active

Rank over the last 12 weeks

Now #953 · best #830 · down 53 in 30 days

#964 on Oct 15
#969 on Oct 16
#945 on Oct 17
#924 on Oct 18
#954 on Oct 19
#953 since Oct 20

20 earlier periods

#978 on Aug 1
#841 on Aug 4
#873 on Aug 10
#874 on Aug 11
#877 on Aug 13
#830 on Aug 15
#859 on Aug 17
#880 on Aug 18
#890 on Aug 27
#928 on Sep 1
#912 on Sep 14
#900 on Sep 15
#925 on Sep 23
#928 on Sep 30
#853 on Oct 3
#946 on Oct 7
#926 on Oct 10
#960 on Oct 12
#964 on Oct 13
#983 on Oct 14

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 4 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
2 dangerous shell commandsin 1 file: detection-model-pipeline/Makefile:123
63 network referencesin 9 files: README.md:7 README.zh-CN.md:7 detection-model-pipeline/Makefile:50 and 6 more
No hidden or obfuscated text
No instruction overrides
35 executable scriptsin 35 files: Makefile:1 detection-model-pipeline/Makefile:1 detection-model-pipeline/code/harness/validate_demo_data.py:1 and 32 more
13 references to secretsin 5 files: detection-model-pipeline/code/m_serve_hier_api.py:39 README.md:84 detection-model-pipeline/Makefile:130 and 2 more
No requests to vote in Hot

Show all 113 signals by file

`Makefile`

Executable scriptline 1
```
Executable file
```

`README.md`

Network accessline 7

<p align="center">   <a href="https://github.com/lynote-ai/ai-text-detector/actions/workflows/ci.yml"><img src="https://github.com/lynote-ai/ai-text-detector/actions/workflows/ci.yml/badge.svg" alt="CI" /></a>

Network accessline 8

<a href="https://github.com/lynote-ai/ai-text-detector/actions/workflows/ci.yml"><img src="https://github.com/lynote-ai/ai-text-detector/actions/workflows/ci.yml/badge.svg" alt="CI" /></a>

Network accessline 9

<img src="https://img.shields.io/badge/python-3.9%2B-3776ab" alt="Python 3.9+" />

Network accessline 10

<img src="https://img.shields.io/badge/license-MIT-16a34a" alt="MIT License" />

Network accessline 11

<img src="https://img.shields.io/badge/network-none-f59e0b" alt="No Network" />

Network accessline 25

<a href="#use-cases">Use Cases</a>   ·   <a href="https://lynote.ai/ai-detector-api"><b>Detector API</b></a>

Network accessline 26

·   <a href="https://lynote.ai/ai-detector-api"><b>Detector API</b></a> </p>

Network accessline 27

<a href="https://lynote.ai/ai-detector-api"><b>Detector API</b></a>

Network accessline 30

> 🚀 **New: the Lynote AI Detector API is live.** Need AI-text detection inside your own app, LMS, or moderation pipeline? Call Lynote's production detector with one REST request — no model to train or host. **[Get an API key → lynote.ai/ai-

Network accessline 32

**Other Quality Projects**</br> AI Humanize Text:https://github.com/lynote-ai/humanize-text</br>

Network accessline 33

AI Humanize Text:https://github.com/lynote-ai/humanize-text</br>

Network accessline 34

AI Image Detector:https://github.com/lynote-ai/ai-image-detector</br>

Network accessline 75

The local analyzer here is built for cautious, offline triage, and the production model above ships as a pipeline, not weights. If you need production-grade detection **inside your own product**, the [Lynote AI Detector API](https://lynote.

Network accessline 84
```
[Credential-related source omitted]
```
Access to secretsline 84
```
[Credential-related source omitted]
```
Access to secretsline 85
```
[Credential-related source omitted]
```

Network accessline 90

<p align="center">   <a href="https://lynote.ai/ai-detector-api"><img src="https://img.shields.io/badge/Get_your_API_key-Lynote_AI_Detector_API-blue?style=for-the-badge" alt="Get your Lynote AI Detector API key"></a>

Network accessline 91
```
[Credential-related source omitted]
```
Access to secretsline 91
```
[Credential-related source omitted]
```

Network accessline 94

Plans, rate limits, and full docs: **[lynote.ai/ai-detector-api](https://lynote.ai/ai-detector-api)**. As with any detector, treat results as a signal for human review, not proof of authorship.

Network accessline 172

We ran a reproducible evaluation on the public [HC3 dataset](https://huggingface.co/datasets/Hello-SimpleAI/HC3), using the English `finance`, `medicine`, and `open_qa` subsets with the first 100 rows from each subset.

Network accessline 306

🔌 Visit **[lynote.ai/ai-detector-api](https://lynote.ai/ai-detector-api)** to get your AI Detector API key.

`README.zh-CN.md`

Network accessline 7

<p align="center">   <a href="https://github.com/lynote-ai/ai-detector-skill/actions/workflows/ci.yml"><img src="https://github.com/lynote-ai/ai-detector-skill/actions/workflows/ci.yml/badge.svg" alt="CI" /></a>

Network accessline 8

<a href="https://github.com/lynote-ai/ai-detector-skill/actions/workflows/ci.yml"><img src="https://github.com/lynote-ai/ai-detector-skill/actions/workflows/ci.yml/badge.svg" alt="CI" /></a>

Network accessline 9

<img src="https://img.shields.io/badge/python-3.9%2B-3776ab" alt="Python 3.9+" />

Network accessline 10

<img src="https://img.shields.io/badge/license-MIT-16a34a" alt="MIT License" />

Network accessline 11

<img src="https://img.shields.io/badge/network-none-f59e0b" alt="No Network" />

Network accessline 25

<a href="#典型使用场景">典型使用场景</a>   ·   <a href="https://lynote.ai/ai-detector-api"><b>Detector API</b></a>

Network accessline 26

·   <a href="https://lynote.ai/ai-detector-api"><b>Detector API</b></a> </p>

Network accessline 27

<a href="https://lynote.ai/ai-detector-api"><b>Detector API</b></a>

Network accessline 30

> 🚀 **新上线:Lynote AI Detector API。** 想在自己的应用、教学平台或内容审核流程里接入 AI 文本检测?一个 REST 请求即可调用 Lynote 线上同款检测模型,无需自己训练或部署模型。**[获取 API Key → lynote.ai/ai-detector-api](https://lynote.ai/ai-detector-api)**

Network accessline 73

本仓库的本地分析器定位是谨慎的离线初筛,上面的生产模型也只开源了管线、不含权重。如果你需要**在自己的产品里**接入生产级检测能力,[Lynote AI Detector API](https://lynote.ai/ai-detector-api) 通过一个接口提供 Lynote 线上同款检测模型:

Network accessline 82
```
[Credential-related source omitted]
```
Access to secretsline 82
```
[Credential-related source omitted]
```
Access to secretsline 83
```
[Credential-related source omitted]
```

Network accessline 88

<p align="center">   <a href="https://lynote.ai/ai-detector-api"><img src="https://img.shields.io/badge/获取_API_Key-Lynote_AI_Detector_API-blue?style=for-the-badge" alt="获取 Lynote AI Detector API Key"></a>

Network accessline 89

<a href="https://lynote.ai/ai-detector-api"><img src="https://img.shields.io/badge/获取_API_Key-Lynote_AI_Detector_API-blue?style=for-the-badge" alt="获取 Lynote AI Detector API Key"></a>

Network accessline 92

套餐、速率限制和完整文档:**[lynote.ai/ai-detector-api](https://lynote.ai/ai-detector-api)**。和所有检测器一样,检测结果应作为人工复核的参考信号,而非作者身份的证据。

Network accessline 170

我们基于公开的 [HC3 数据集](https://huggingface.co/datasets/Hello-SimpleAI/HC3) 做了一轮可复现测试，使用英文 `finance`、`medicine`、`open_qa` 三个子集，每个子集取前 100 条问答对。

Network accessline 304

🔌 访问 **[lynote.ai/ai-detector-api](https://lynote.ai/ai-detector-api)** 获取 AI Detector API Key。

`assets/hero.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" width="1200" height="630" viewBox="0 0 1200 630" role="img" aria-labelledby="title desc">

`assets/score-bands.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" width="960" height="360" viewBox="0 0 960 360" role="img" aria-labelledby="title desc">

`assets/workflow.svg`

Network accessline 1

<svg xmlns="http://www.w3.org/2000/svg" width="960" height="420" viewBox="0 0 960 420" role="img" aria-labelledby="title desc">

`detection-model-pipeline/.gitignore`

Access to secretsline 17
```
[Credential-related source omitted]
```

`detection-model-pipeline/Makefile`

Executable scriptline 1
```
Executable file
```

Network accessline 50

@printf '%s\n'  	  'env-check                         Validate the Python runtime'  	  'manifest-validate                 Validate the project manifest'  	  'demo-validate                     Enforce synthetic-only demos, pinned counts, and

Network accessline 63

'serve                             Start the HTTP service on $(HOST):$(PORT)' \ 	  '                                  BEST=<checkpoint-dir> (required)' \ 	  'probe                             Smoke-test a running service with curl' \

Network accessline 64

'                                  BEST=<checkpoint-dir> (required)' \ 	  'probe                             Smoke-test a running service with curl' \ 	  'detect                            Detect one sentence; TEXT="<your text>" (optional)'

Network accessline 65

'probe                             Smoke-test a running service with curl' \

Network accessline 122

probe: 	curl -s -X POST localhost:$(PORT)/detect \

Dangerous shell operationline 123

curl -s -X POST localhost:$(PORT)/detect  	  -H 'Content-Type: application/json'  	  -d '{"text": "Artificial intelligence is transforming education. Teachers must adapt their methods."}'  	  | python3 -c "import json,sys; d=json.load(sys.s

Network accessline 123

curl -s -X POST localhost:$(PORT)/detect \

Network accessline 130
```
[Credential-related source omitted]
```
Access to secretsline 130
```
[Credential-related source omitted]
```

Network accessline 131

import json, os, urllib.request;\ 	req = urllib.request.Request(\ 	    'http://localhost:$(PORT)/detect',\

Network accessline 132
```
req = urllib.request.Request(\
```
Network accessline 133
```
'http://localhost:$(PORT)/detect',\
```
Network accessline 134
```
[Credential-related source omitted]
```
Access to secretsline 134
```
[Credential-related source omitted]
```

Network accessline 135

headers={'Content-Type': 'application/json'});\ 	d = json.load(urllib.request.urlopen(req));\ 	doc = d['data']['documents'][0];\

Network accessline 136

d = json.load(urllib.request.urlopen(req));\

Access to secretsline 138
```
[Credential-related source omitted]
```
Dangerous shell operationline 154
```
rm -rf "$(PROJECT_DIR)/$(RUN_DIR)"
```

`detection-model-pipeline/code/harness/validate_demo_data.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/code/harness/validate_docs.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/code/harness/validate_manifest.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/code/i_prepare_hier_dataset.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/code/j_train_hier_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/code/k_calibrate_hier_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/code/l_eval_hier_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/code/m_serve_hier_api.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 39
```
[Credential-related source omitted]
```
Access to secretsline 40
```
[Credential-related source omitted]
```
Access to secretsline 44
```
[Credential-related source omitted]
```
Access to secretsline 45
```
[Credential-related source omitted]
```

`detection-model-pipeline/code/sentence_splitter.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/docs/API.md`

Network accessline 70

# single document curl -X POST localhost:8100/detect \

Network accessline 71
```
curl -X POST localhost:8100/detect \
```

Network accessline 75

# batch (same endpoint, array input) curl -X POST localhost:8100/detect \

Network accessline 76
```
curl -X POST localhost:8100/detect \
```

Network accessline 90

curl -X POST localhost:8100/detect/batch \

`detection-model-pipeline/docs/API.zh-CN.md`

Network accessline 70

# 单篇 curl -X POST localhost:8100/detect \

Network accessline 71
```
curl -X POST localhost:8100/detect \
```

Network accessline 75

# 批量（同一接口，直接传数组） curl -X POST localhost:8100/detect \

Network accessline 76
```
curl -X POST localhost:8100/detect \
```

Network accessline 90

curl -X POST localhost:8100/detect/batch \

`detection-model-pipeline/model_entity/hier_aidetect_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/model_entity/hier_model_factory.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/model_entity/hier_xlmr_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/conftest.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_dynamic_batcher.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_harness_validators.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_hier_aidetect_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_hier_xlmr_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_i_prepare_hier_dataset.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_j_train_hier_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_k_calibrate_hier_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_l_eval_hier_model.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_m_serve_hier_api.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tests/test_sentence_splitter.py`

Executable scriptline 1
```
Executable file
```

`detection-model-pipeline/tools/refresh_demo_manifest.py`

Executable scriptline 1
```
Executable file
```

`scripts/benchmark.py`

Executable scriptline 1
```
Executable file
```

`scripts/detect.py`

Executable scriptline 1
```
Executable file
```

`scripts/evaluate_hc3.py`

Executable scriptline 1
```
Executable file
```

Network accessline 23

def _download_lines(subset: str) -> list[str]:     url = f"https://huggingface.co/datasets/{DATASET_NAME}/resolve/main/{subset}.jsonl?download=true"

Network accessline 24

url = f"https://huggingface.co/datasets/{DATASET_NAME}/resolve/main/{subset}.jsonl?download=true"

`scripts/setup.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`src/aidetect/init.py`

Executable scriptline 1
```
Executable file
```

`src/aidetect/cli.py`

Executable scriptline 1
```
Executable file
```

`src/aidetect/core.py`

Executable scriptline 1
```
Executable file
```

`tests/test_cli.py`

Executable scriptline 1
```
Executable file
```

`tests/test_core.py`

Executable scriptline 1
```
Executable file
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 109 facts

Executable script in code of a file that runsMakefile:1High confidence
Network access in prose of documentationREADME.md:7Low confidence
Network access in prose of documentationREADME.md:8Low confidence
Network access in prose of documentationREADME.md:9Low confidence
Network access in prose of documentationREADME.md:10Low confidence
Network access in prose of documentationREADME.md:11Low confidence
Network access in prose of documentationREADME.md:25Low confidence
Network access in prose of documentationREADME.md:26Low confidence
Network access in prose of documentationREADME.md:27Low confidence
Network access in prose of documentationREADME.md:30Low confidence
Network access in prose of documentationREADME.md:32Low confidence
Network access in prose of documentationREADME.md:33Low confidence
Network access in prose of documentationREADME.md:34Low confidence
Network access in prose of documentationREADME.md:75Low confidence
Network access in code of documentationREADME.md:84Low confidence
Access to secrets in code of documentationREADME.md:84Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueREADME.md:85Low confidence
Network access in prose of documentationREADME.md:90Low confidence
Network access in prose of documentationREADME.md:91Low confidence
Access to secrets in prose of documentationREADME.md:91Low confidence
Network access in prose of documentationREADME.md:94Low confidence
Network access in prose of documentationREADME.md:172Low confidence
Network access in prose of documentationREADME.md:306Low confidence
Network access in prose of documentationREADME.zh-CN.md:7Low confidence
Network access in prose of documentationREADME.zh-CN.md:8Low confidence
Network access in prose of documentationREADME.zh-CN.md:9Low confidence
Network access in prose of documentationREADME.zh-CN.md:10Low confidence
Network access in prose of documentationREADME.zh-CN.md:11Low confidence
Network access in prose of documentationREADME.zh-CN.md:25Low confidence
Network access in prose of documentationREADME.zh-CN.md:26Low confidence
Network access in prose of documentationREADME.zh-CN.md:27Low confidence
Network access in prose of documentationREADME.zh-CN.md:30Low confidence
Network access in prose of documentationREADME.zh-CN.md:73Low confidence
Network access in code of documentationREADME.zh-CN.md:82Low confidence
Access to secrets in code of documentationREADME.zh-CN.md:82Low confidence
Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueREADME.zh-CN.md:83Low confidence
Network access in prose of documentationREADME.zh-CN.md:88Low confidence
Network access in prose of documentationREADME.zh-CN.md:89Low confidence
Network access in prose of documentationREADME.zh-CN.md:92Low confidence
Network access in prose of documentationREADME.zh-CN.md:170Low confidence
Network access in prose of documentationREADME.zh-CN.md:304Low confidence
Executable script in a comment of a file that runsdetection-model-pipeline/Makefile:1Low confidence
Network access in code of a file that runsdetection-model-pipeline/Makefile:50High confidence
Network access in code of a file that runsdetection-model-pipeline/Makefile:63High confidence
Network access in code of a file that runsdetection-model-pipeline/Makefile:64High confidence
Network access in code of a file that runsdetection-model-pipeline/Makefile:65High confidence
Network access in code of a file that runsdetection-model-pipeline/Makefile:122High confidence
Dangerous shell operation in code of a file that runsdetection-model-pipeline/Makefile:123High confidence
Network access in code of a file that runsdetection-model-pipeline/Makefile:123High confidence
Network access in code of a file that runsdetection-model-pipeline/Makefile:130High confidence

and 59 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Path .claude/skills/ai-detector/SKILL.md	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

lynote-ai/ai-text-detector

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

ai-text-detector-github

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

Makefile

README.md

README.zh-CN.md

assets/hero.svg

assets/score-bands.svg

assets/workflow.svg

detection-model-pipeline/.gitignore

detection-model-pipeline/Makefile

detection-model-pipeline/code/harness/validate_demo_data.py

detection-model-pipeline/code/harness/validate_docs.py

detection-model-pipeline/code/harness/validate_manifest.py

detection-model-pipeline/code/i_prepare_hier_dataset.py

detection-model-pipeline/code/j_train_hier_model.py

detection-model-pipeline/code/k_calibrate_hier_model.py

detection-model-pipeline/code/l_eval_hier_model.py

detection-model-pipeline/code/m_serve_hier_api.py

detection-model-pipeline/code/sentence_splitter.py

detection-model-pipeline/docs/API.md

detection-model-pipeline/docs/API.zh-CN.md

detection-model-pipeline/model_entity/hier_aidetect_model.py

detection-model-pipeline/model_entity/hier_model_factory.py

detection-model-pipeline/model_entity/hier_xlmr_model.py

detection-model-pipeline/tests/conftest.py

detection-model-pipeline/tests/test_dynamic_batcher.py

detection-model-pipeline/tests/test_harness_validators.py

detection-model-pipeline/tests/test_hier_aidetect_model.py

detection-model-pipeline/tests/test_hier_xlmr_model.py

detection-model-pipeline/tests/test_i_prepare_hier_dataset.py

detection-model-pipeline/tests/test_j_train_hier_model.py

detection-model-pipeline/tests/test_k_calibrate_hier_model.py

detection-model-pipeline/tests/test_l_eval_hier_model.py

detection-model-pipeline/tests/test_m_serve_hier_api.py

detection-model-pipeline/tests/test_sentence_splitter.py

detection-model-pipeline/tools/refresh_demo_manifest.py

scripts/benchmark.py

scripts/detect.py

scripts/evaluate_hc3.py

scripts/setup.sh

src/aidetect/__init__.py

src/aidetect/cli.py

src/aidetect/core.py

tests/test_cli.py

tests/test_core.py

How the signals fit together

Works with

You might also use

limingrui679-design/high-stakes-analytics-decision-lab

harshaneel/humanize

taxueseek/argo

Xquik-dev/hermes-tweet

MemPalace/mempalace

langchain-ai/deepagents

`SKILL.md`

`Makefile`

`README.md`

`README.zh-CN.md`

`assets/hero.svg`

`assets/score-bands.svg`

`assets/workflow.svg`

`detection-model-pipeline/.gitignore`

`detection-model-pipeline/Makefile`

`detection-model-pipeline/code/harness/validate_demo_data.py`

`detection-model-pipeline/code/harness/validate_docs.py`

`detection-model-pipeline/code/harness/validate_manifest.py`

`detection-model-pipeline/code/i_prepare_hier_dataset.py`

`detection-model-pipeline/code/j_train_hier_model.py`

`detection-model-pipeline/code/k_calibrate_hier_model.py`

`detection-model-pipeline/code/l_eval_hier_model.py`

`detection-model-pipeline/code/m_serve_hier_api.py`

`detection-model-pipeline/code/sentence_splitter.py`

`detection-model-pipeline/docs/API.md`

`detection-model-pipeline/docs/API.zh-CN.md`

`detection-model-pipeline/model_entity/hier_aidetect_model.py`

`detection-model-pipeline/model_entity/hier_model_factory.py`

`detection-model-pipeline/model_entity/hier_xlmr_model.py`

`detection-model-pipeline/tests/conftest.py`

`detection-model-pipeline/tests/test_dynamic_batcher.py`

`detection-model-pipeline/tests/test_harness_validators.py`

`detection-model-pipeline/tests/test_hier_aidetect_model.py`

`detection-model-pipeline/tests/test_hier_xlmr_model.py`

`detection-model-pipeline/tests/test_i_prepare_hier_dataset.py`

`detection-model-pipeline/tests/test_j_train_hier_model.py`

`detection-model-pipeline/tests/test_k_calibrate_hier_model.py`

`detection-model-pipeline/tests/test_l_eval_hier_model.py`

`detection-model-pipeline/tests/test_m_serve_hier_api.py`

`detection-model-pipeline/tests/test_sentence_splitter.py`

`detection-model-pipeline/tools/refresh_demo_manifest.py`

`scripts/benchmark.py`

`scripts/detect.py`

`scripts/evaluate_hc3.py`

`scripts/setup.sh`

`src/aidetect/init.py`

`src/aidetect/cli.py`

`src/aidetect/core.py`

`tests/test_cli.py`

`tests/test_core.py`