compliance-training-eval
A tool to parse compliance training data, identify rule violations, and generate structured reports for the trust industry.
Install
mkdir -p .claude/skills/compliance-training-eval && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19421" && unzip -o skill.zip -d .claude/skills/compliance-training-eval && rm skill.zipInstalls to .claude/skills/compliance-training-eval
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
用于信托领域合规与运营中的合规培训测评助手场景，支持结构化处理与报告输出。Key capabilities
- →Parse JSON or JSONL compliance training datasets
- →Analyze input data against business rules
- →Identify rule-based compliance failures
- →Generate structured compliance analysis reports
- →Flag records requiring manual human review
How it works
The tool processes structured data by applying predefined business rules to identify risks and compliance failures, then outputs a report that highlights specific items for human verification.
Inputs & outputs
When to use compliance-training-eval
- →Parse compliance training datasets
- →Identify rule-based compliance failures
- →Generate compliance analysis reports
- →Flag records requiring manual human review
About this skill
compliance-training-eval
概述
本技能用于信托业务场景的结构化处理，支持数据解析、规则识别与报告输出。
输入要求
- 支持 JSON 数组或 JSONL
- 建议字段：
id,name,text,status,timestamp，以及场景相关业务字段
工作流程
- 明确业务口径与目标
- 读取并清洗输入数据
- 执行规则分析与风险识别
- 输出结构化结果并标注复核事项
- 人工复核后进入正式流程
执行方式
python scripts/analyze.py --input input.json --output report.md
输出结构
- 样本概览（数量、等级分布）
- 重点条目（分值、命中原因）
- 风险提示与复核建议
- 免责声明
质量要求
- 事实与判断分离
- 规则命中可追溯
- 保留自动生成需人工复核声明
- 不输出投资建议、授信决策或法律最终意见
使用示例
示例 1: 基本使用
# 调用 skill
result = run_skill({
"param1": "value1",
"param2": "value2"
})
示例 2: 命令行使用
python scripts/run_skill.py --input data.json
Limitations
- →Does not provide investment advice, credit decisions, or final legal opinions
How it compares
This tool automates the identification of rule-based failures in compliance datasets, whereas manual review requires individual inspection of every record.
Compared to similar skills
compliance-training-eval side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| compliance-training-eval (this skill) | 0 | 4mo | Review | Intermediate |
| data-lineage-tracker | 0 | 1mo | No flags | Intermediate |
| pdf-processing | 37 | 8mo | Review | Intermediate |
| whisper | 11 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by aifinlab
View all by aifinlab →You might also like
data-lineage-tracker
LeoYeAI
Track data origin, transformations, and flow through construction systems. Essential for audit trails, compliance, and debugging data issues.
pdf-processing
Ming-Kai-LC
Comprehensive PDF processing techniques for handling large files that exceed Claude Code's reading limits, including chunking strategies, text/table extraction, and OCR for scanned documents. Use when working with PDFs larger than 10-15MB or more than 30-50 pages.
whisper
davila7
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
office-docs
Xxiii8322766509
Extract text and tables from .docx and .xlsx using local scripts (no external deps).
prompt-xray
huangserva
提示词X光透视 - 从优秀提示词中逆向提取"如何做X"的知识，让黑盒变透明
pdf-processor
lofcz
Extracts text and tables from PDF files, fills forms, and merges documents. Use when working with PDF files or when the user mentions PDFs, forms, or document extraction.