スキル data-quality-assessment-expert

📦

data-quality-assessment-expert

Name: data-quality-assessment-expert
Author: 图灵数盟

コンテンツリビジョン r1 安全 📁 ファイルシステムへのアクセス⚙️ 外部コマンド🌐 ネットワークアクセス

Assess Data Quality with Six-Dimension Scoring

Unclear data quality weakens asset, transaction, and governance decisions. This skill scores six dimensions, assigns grades, and recommends focused remediation.

対応: Claude Codex Code(CC)

🥉 77 ブロンズ

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 "data-quality-assessment-expert" from https://skillstore.io/skills/dhturing-data-quality-assessment-expert.md and its manifest at https://skillstore.io/api/skills/dhturing-data-quality-assessment-expert/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/dhturing-data-quality-assessment-expert.md 署名済み manifest GET /api/skills/dhturing-data-quality-assessment-expert/manifest 署名済み lockfile GET /api/skills/dhturing-data-quality-assessment-expert/lockfile

テストする

「data-quality-assessment-expert」を使用しています。 Assess a customer dataset with 96% accuracy, 82% completeness, and delayed monthly updates.

期待される結果:

The assessment highlights strong accuracy, weak completeness, and material timeliness risk. It recommends filling critical fields and enforcing update deadlines before final grading.

「data-quality-assessment-expert」を使用しています。 Explain whether a C-grade dataset should proceed to accounting recognition.

期待される結果:

A C grade indicates material quality gaps. Complete targeted remediation and reassessment before recognition, while documenting evidence, ownership, and remaining limitations.

「data-quality-assessment-expert」を使用しています。 Create a report outline for transaction due diligence.

期待される結果:

Purpose, scope, and evaluation date
Standards, methods, sampling, and rules
Six-dimension results and issue evidence
Weighted score, grade, and reference delta range
Remediation plan, limitations, and appendices

セキュリティ監査

安全

v1 • 2026/9/27 バージョン別レポートを開く

All twelve static findings are false positives caused by Markdown formatting, installation documentation, ordinary website links, and the entropy of Chinese-language text. No executable scripts, network requests, obfuscated payloads, prompt injection, or unsafe data-handling intent were found.

スキャンされたファイル

391

解析済み行数

レビュー項目

誤検知を無視

リスク要因

📁 ファイルシステムへのアクセス (2)

profile.md:38 profile.md:38

⚙️ 外部コマンド (3)

SKILL.md:20 SKILL.md:26 SKILL.md:33

🌐 ネットワークアクセス (2)

SKILL.md:6 SKILL.md:12

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

レポートリンクをコピー

https://skillstore.io/skills/dhturing-data-quality-assessment-expert/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/dhturing-data-quality-assessment-expert/security.svg)](https://skillstore.io/skills/dhturing-data-quality-assessment-expert?utm_source=security_passport_badge)

HTMLバッジ

<a href="https://skillstore.io/skills/dhturing-data-quality-assessment-expert?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dhturing-data-quality-assessment-expert/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/dhturing-data-quality-assessment-expert.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

图灵数盟. (2026). data-quality-assessment-expert security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dhturing-data-quality-assessment-expert/audits/1

BibTeX形式の引用

@techreport{dhturing-data-quality-assessment-expert-2026,
  author = {图灵数盟},
  title = {data-quality-assessment-expert security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/dhturing-data-quality-assessment-expert/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: "data-quality-assessment-expert security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "图灵数盟"
date-released: "2026-09-27"
url: "https://skillstore.io/skills/dhturing-data-quality-assessment-expert/audits/1"
identifiers:
  - type: other
    value: "skillstore:dhturing-data-quality-assessment-expert: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

アーキテクチャ

保守性

コンテンツ

コミュニティ

仕様準拠

作成できるもの

Prepare data for accounting recognition

Build a six-dimension assessment, document evidence, and identify quality gaps before data resource recognition.

Support buyer due diligence

Evaluate transaction data, explain its grade, and present reproducible checks for buyer review.

Prioritize quality remediation

Rank defects by severity and define focused actions for the weakest quality dimensions.

これらのプロンプトを試す

Create a basic quality checklist

Create a six-dimension data quality checklist for [dataset]. State one measurable indicator and one evidence source for each dimension.

Design a weighted scorecard

Design a GB/T 36344-2018 scorecard for [purpose]. Explain each weight, scoring rule, threshold, and required evidence.

Analyze assessment results

Assess these quality results: [results]. Calculate dimension scores, the weighted total, the grade, major defects, and recommended remediation priorities.

Develop an assessment and valuation package

Develop a complete assessment for [dataset and purpose]. Include scope, sampling, rules, scores, grade, delta range, caveats, remediation, and monitoring.

ベストプラクティス

Define the business purpose, dataset scope, evaluation date, and evidence requirements before scoring.
Use read-only access and avoid copying or retaining source data during assessment.
Document formulas, samples, thresholds, and exceptions so reviewers can reproduce every score.

回避

Do not raise scores to satisfy a preferred accounting, transaction, or valuation outcome.
Do not infer a final grade from undocumented samples or incomplete dimension results.
Do not present reference delta ranges as certified appraisal or regulatory conclusions.