スキル ai-detector
📦

ai-detector

コンテンツリビジョン r1 安全

Review Text for Possible AI Writing Patterns

Writing patterns alone cannot reliably establish whether content was generated by AI. This skill organizes a qualitative assessment into an HTML report with supporting observations.

対応: Claude Codex Code(CC)
Maintain this Skill? Claim it 📊 72 十分

自分のエージェントでインストール

このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。

エージェントリクエスト
Review the Skillstore skill "ai-detector" from https://skillstore.io/skills/notegpt-official-ai-detector.md and its manifest at https://skillstore.io/api/skills/notegpt-official-ai-detector/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。

エージェントが読めるリソース

AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。

Markdown詳細 GET /skills/notegpt-official-ai-detector.md 署名済み manifest GET /api/skills/notegpt-official-ai-detector/manifest 署名済み lockfile GET /api/skills/notegpt-official-ai-detector/lockfile

テストする

「ai-detector」を使用しています。 Review a promotional paragraph that repeats broad claims without concrete examples.

期待される結果:

  • Illustrative report assessment: Repeated sentence structures and generic claims may resemble AI-generated writing.
  • Alternative explanation: A human author may use the same conventions in promotional copy.
  • The HTML report presents observations, an uncalibrated likelihood indicator, and a download link for the supplied paragraph.

「ai-detector」を使用しています。 Assess a personal account with specific dates, varied sentences, and detailed observations.

期待される結果:

  • Illustrative report assessment: The passage contains specific details and varied phrasing, but these features do not establish human authorship.
  • AI systems can produce similar details, and human editing can change the apparent writing patterns.
  • The report identifies the relevant passages and states the limits of its assessment.

セキュリティ監査

安全
v1 • 2026/11/6 バージョン別レポートを開く

Static analysis reported no findings, so no finding verdicts were required. The prompt requests content analysis and HTML reporting; no evidence found of prompt injection, credential access, or data exfiltration. Its likelihood scores have no documented validation and should not establish authorship.

1
スキャンされたファイル
9
解析済み行数
0
レビュー項目
0
誤検知を無視
最新の完了済み静的・セマンティック監査では、確認済みのセキュリティ検出事項は見つかりませんでした。これは、スキルに副作用がないことを証明するものではありません。
監査者: codex
このレポートを共有・引用

バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。

バージョン別レポートを開く
セキュリティ評価

レポートリンクをコピー

https://skillstore.io/skills/notegpt-official-ai-detector/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdownバッジ

[![Skillstore security assessment](https://skillstore.io/badges/skills/notegpt-official-ai-detector/security.svg)](https://skillstore.io/skills/notegpt-official-ai-detector?utm_source=security_passport_badge)

HTMLバッジ

<a href="https://skillstore.io/skills/notegpt-official-ai-detector?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/notegpt-official-ai-detector/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/notegpt-official-ai-detector.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
学術引用 (APA · BibTeX · CFF)

APA形式の引用

notegpt-official. (2026). ai-detector security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/notegpt-official-ai-detector/audits/1

BibTeX形式の引用

@techreport{notegpt-official-notegpt-official-ai-detector-2026, author = {notegpt-official}, title = {ai-detector security audit report (audit version 1)}, institution = {Skillstore}, year = {2026}, number = {1}, url = {https://skillstore.io/skills/notegpt-official-ai-detector/audits/1}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "ai-detector security audit report (audit version 1)" version: "unspecified" type: report authors: - name: "notegpt-official" date-released: "2026-11-06" url: "https://skillstore.io/skills/notegpt-official-ai-detector/audits/1" identifiers: - type: other value: "skillstore:notegpt-official-ai-detector:audit:1" description: "Skillstore immutable audit report identifier"

Skillstore スコア

このスコアの理由 証拠の信頼度: 中
55
アーキテクチャ
65
保守性
87
コンテンツ
65
コミュニティ
65
仕様準拠

作成できるもの

Editorial Content Review

Review a submitted article for possible AI writing patterns before discussing specific observations with its author.

Teaching Discussion Preparation

Prepare an exploratory review of a consented writing sample without treating the result as evidence of academic misconduct.

Draft Self-Assessment

Examine your own draft for repetitive or generic patterns and review the supporting observations in an HTML report.

これらのプロンプトを試す

Review a Short Passage 
Review this text for possible AI-generated patterns: [text]. Produce an HTML report and clearly state that the assessment cannot prove authorship.
Request Supporting Evidence 
Assess this draft: [text]. In the HTML report, quote relevant passages, explain each observation, and identify plausible human explanations.
Specify the Report Elements 
Analyze [text] and generate an HTML report. Include a circular percentage indicator with matching fill and color, evidence, limitations, and a content download link.
Account for Context and Uncertainty 
Review [text] given this context: [genre, editing history, language background]. Separate observations from inference, explain uncertainty, and label any percentage as uncalibrated.

ベストプラクティス

  • Use the report as a discussion aid and verify concerns through independent evidence.
  • Provide writing context and request alternative explanations for each observed pattern.
  • Remove sensitive information before submission and inspect the report and download link before sharing.

回避

  • Treating a generated percentage as a measured probability or proof of AI authorship.
  • Making disciplinary, hiring, or publication decisions solely from this assessment.
  • Submitting confidential content without permission or reviewing the host service's data handling.

よくある質問

Can this skill prove that text was generated by AI?
No. It reviews writing patterns and provides an assessment, not proof of authorship.
Is the likelihood percentage scientifically calibrated?
No calibration method or validation results are provided. Treat the percentage as an illustrative model judgment.
What does the report include?
The instructions request evidence-based HTML, a colored circular percentage indicator, and a download link for the analyzed content.
Which AI tools are listed as supported?
The marketplace metadata lists Claude, Codex, and Claude Code. Report rendering depends on the host environment.
Does the skill include a separate detection service?
No. The supplied file contains prompt instructions, without executable code or an external detection service integration.
Is confidential text safe to submit?
The skill defines no privacy safeguards. Follow your host service's data policies and remove confidential information before submitting content.

開発者情報

ライセンス

不明

Skillstore リビジョン

r1

バージョンに関する注意

作者はバージョンを宣言していません。

リポジトリ

https://github.com/notegpt-official/notegpt-skills/tree/bd26f364942d87681cb0d2dbfd0e21288a5c5298/skills/ai-detector

参照

c993c6abcbffafea2683d7748b53b3dfaf438415

メンテナンスの新しさ

2026/11/9

利用状況

0 ダウンロード · 0 閲覧

ファイル構成

📄 SKILL.md

関連スキル

すべて表示