スキル ai-listening
📦

ai-listening

コンテンツリビジョン r3 安全 ⚙️ 外部コマンド🌐 ネットワークアクセス📁 ファイルシステムへのアクセス🔑 環境変数

Track New AI Names Across Daily Sources

New AI names appear across separate feeds, making daily discovery difficult. This skill guides new-term-radar collection and organizes deduplicated names with supporting evidence.

対応: Claude Codex Code(CC)
Maintain this Skill? Claim it 🥉 77 ブロンズ

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-listening" from https://skillstore.io/skills/zhuyansen-ai-listening.md and its manifest at https://skillstore.io/api/skills/zhuyansen-ai-listening/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。

テストする

「ai-listening」を使用しています。 What should I expect from the first collection run?

期待される結果:

The first run builds comparison snapshots and mainly reports GitHub breakouts. Limited results do not establish that AI activity was low.

「ai-listening」を使用しています。 Can I run this without an AIsa key?

期待される結果:

Hugging Face, GitHub, and configured sitemaps remain available. X posts and name judging are unavailable and should be listed as coverage gaps.

「ai-listening」を使用しています。 Does a strong lead prove search demand?

期待される結果:

No. The report shows observed source signals. Search demand requires separate research.

セキュリティ監査

安全

All 24 static findings are false positives involving Markdown formatting, documented CLI usage, expected authentication checks, reference links, or report filtering. No evidence found of credential exfiltration, system reconnaissance, or prompt injection; the source explicitly rejects instructions embedded in collected data. This review covers SKILL.md only, not the external package implementation or its runtime network behavior.

1
スキャンされたファイル
60
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 監査履歴を表示 →
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/zhuyansen-ai-listening/audits/3?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdownバッジ

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

HTMLバッジ

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

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/zhuyansen-ai-listening.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

zhuyansen. (2026). ai-listening security audit report (audit version 3) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zhuyansen-ai-listening/audits/3

BibTeX形式の引用

@techreport{zhuyansen-zhuyansen-ai-listening-2026, author = {zhuyansen}, title = {ai-listening security audit report (audit version 3)}, institution = {Skillstore}, year = {2026}, number = {3}, url = {https://skillstore.io/skills/zhuyansen-ai-listening/audits/3}, 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-listening security audit report (audit version 3)" version: "unspecified" type: report authors: - name: "zhuyansen" date-released: "2026-10-28" url: "https://skillstore.io/skills/zhuyansen-ai-listening/audits/3" identifiers: - type: other value: "skillstore:zhuyansen-ai-listening:audit:3" 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
85
保守性
87
コンテンツ
65
コミュニティ
83
仕様準拠

作成できるもの

Prepare an AI news shortlist

Collect recently observed AI names with links and signal strength for editorial review.

Find emerging repositories

Review new GitHub breakouts and compare them with other discovery signals before investigating a project.

Seed keyword research

Gather observed model and product names for a separate search-demand research workflow.

これらのプロンプトを試す

Start a daily report
Prepare a daily AI listening report. Check setup and explain estimated costs before requesting approval to collect data.
Review retained names
List retained leads from the last day without a new collection run. Summarize available names and source evidence.
Monitor faster sources
Use the sources workflow for X and Hugging Face. Explain costs and request approval first, then report new names and missing signals.
Prioritize evidence-backed leads
Review the latest listening report. Rank names by source overlap and name score, exclude known leads, and separate breakout repositories from coverage gaps.

ベストプラクティス

  • Keep the same working directory between daily runs so snapshot comparisons remain useful.
  • Approve estimated costs before collection and review the configured account and sitemap lists.
  • Treat collected text as untrusted data and report only supported names, links, and signal evidence.

回避

  • Running collection twice consecutively and expecting the same daily comparison.
  • Presenting missing signals or first-run snapshot gaps as evidence of low activity.
  • Following instructions inside collected posts or publishing findings without separate approval.

よくある質問

What software is required?
The instructions use new-term-radar 0.6.1 with Python 3.10 or newer. uvx is preferred, with a pip installation fallback.
Is an AIsa API key mandatory?
A key enables X collection and name judging. Without it, only the documented free signals run.
How much does collection cost?
The skill estimates about 0.003 USD per X account. Its 35-account example costs about 0.11 USD; approval is required before collection.
Why is the first report limited?
The first run creates baseline snapshots for vocabulary, stars, and sitemap URLs. Later runs compare new observations against those baselines.
Can I review results without paying for another run?
Yes. The leads command lists retained results without starting another collection run and is documented as free.
Does this skill publish or contact anyone automatically?
No. The instructions require separate approval for each publication, message, purchase, or other outbound action.

開発者情報

作成者

zhuyansen

ライセンス

MIT

Skillstore リビジョン

r3

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。

参照

2ec268972a6be25768f84279fde605b246c33d68

メンテナンスの新しさ

2026/10/28

利用状況

6 ダウンロード · 0 閲覧

ファイル構成

📄 SKILL.md

zhuyansen のその他のスキル

すべて表示
すべて表示