本文へスキップ
TakoAPI
スキル一覧に戻る

ai-act-risk-check

bluesbell 作

DevOps & Cloud
10.8kダウンロード数はclawskills.shが公開している値です
22閲覧数
0件のいいねサインインするとこのスキルにいいねできます
—まだ評価がありません
あなたの評価

概要

**Description:** Quickly assesses a preliminary risk classification for an AI system based on the high-risk.

説明

このスキルでできること

Classifies an AI system as HIGH-RISK or LOW-RISK based on the Annex III high-risk categories in the EU AI Act. Covers biometrics, critical infrastructure, education, employment, essential services, law enforcement, and justice. Takes a plain-text description of the system and returns the classification with the matched category if applicable.

Gets an Annex III classification in one command without reading through the full EU AI Act text.

使いどころ

  • Checking if a hiring algorithm requires EU AI Act compliance review
  • Assessing a student grade prediction tool before deployment
  • Evaluating a biometric access system against Annex III thresholds
  • Screening a credit decision model for high-risk classification
  • Pre-audit review of an AI used in criminal justice decisions

ワークフロー例

入力

User asks: Does our AI system that screens job applications based on predicted performance metrics qualify as high-risk under the EU AI Act?

エージェント
  1. 1

    Receives the plain-text system description

  2. 2

    Passes the description to the LLM with hard-coded Annex III criteria

  3. 3

    Evaluates the description against all seven high-risk category groups

  4. 4

    Identifies a match with Annex III Category 4 covering employment and workers management

  5. 5

    Returns the classification with the matched category name

出力

HIGH-RISK — Annex III Category 4: Employment, workers management and access to self-employment

インストール

clawhub install bluesbell/ai-act-risk-check

CLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。

リンク