Token导航 LogoToken导航

Agent Skill · 待分类

banking-expert(银行专家)

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

banking-expert 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描有提醒项,按安装量在待分类类的 11,209 个 Skill 里排第 1,382。

总安装 3,574周安装 146GitHub Stars 19下载 1,156核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:banking-expert(银行专家)
来源仓库:https://github.com/personamanagmentlayer/pcl
仓库路径:skills/banking-expert
安装命令:
npx skills add https://github.com/personamanagmentlayer/pcl --skill banking-expert
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/personamanagmentlayer/pcl --skill banking-expert

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

banking-expert 提供银行系统安全审计、合规检查和漏洞排查的专业指导。适合用于梳理核心 banking 平台架构、KYC/AML 流程和支付系统鉴权逻辑分析。可辅助生成安全复核清单,识别凭据风险与认证缺陷,支持 PSD2 等监管框架解读。

输出结果不能直接作为最终结论,涉及生产系统时应先验证最小权限与数据脱敏策略。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/banking-expert

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/personamanagmentlayer/pcl --skill banking-expe…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

banking-expert 怎么安装?

在终端执行 npx skills add https://github.com/personamanagmentlayer/pcl --skill banking-expert。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

banking-expert 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

banking-expert 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

banking-expert 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

banking-expert 用的人多吗?

公开数据是累计安装 3,574 次,近一周安装 146 次,下载 1,156 次,GitHub 19 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

banking-expert 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
banking-expert

银行专家 · 本页

3,57419需要联网MIT有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Banking Expert

Expert guidance for banking systems, core banking platforms, regulatory compliance, and banking technology.

Core Concepts

Banking Systems

  • Core banking systems (CBS)
  • Account management
  • Transaction processing
  • Payment systems (ACH, SWIFT, SEPA)
  • Loan management
  • Risk management systems

Regulations

  • Basel III/IV capital requirements
  • Know Your Customer (KYC)
  • Anti-Money Laundering (AML)
  • GDPR for banking
  • PSD2 (Payment Services Directive)
  • Dodd-Frank Act

Key Technologies

  • Real-time payment processing
  • Mobile banking
  • Open banking APIs
  • Digital wallets
  • Blockchain in banking
  • AI for fraud detection

Account Management

from decimal import Decimal
from datetime import datetime
from enum import Enum

class AccountType(Enum):
    CHECKING = "checking"
    SAVINGS = "savings"
    CREDIT = "credit"
    LOAN = "loan"

class Account:
    def __init__(self, account_number: str, account_type: AccountType,
                 customer_id: str, balance: Decimal = Decimal('0')):
        self.account_number = account_number
        self.type = account_type
        self.customer_id = customer_id
        self.balance = balance
        self.status = "ACTIVE"
        self.created_at = datetime.now()

    def deposit(self, amount: Decimal) -> dict:
        """Deposit funds with validation"""
        if amount <= 0:
            raise ValueError("Amount must be positive")

        self.balance += amount

        return {
            "transaction_id": self.generate_transaction_id(),
            "type": "DEPOSIT",
            "amount": amount,
            "balance": self.balance,
            "timestamp": datetime.now()
        }

    def withdraw(self, amount: Decimal) -> dict:
        """Withdraw funds with balance check"""
        if amount <= 0:
            raise ValueError("Amount must be positive")

        if self.balance < amount:
            raise ValueError("Insufficient funds")

        self.balance -= amount

        return {
            "transaction_id": self.generate_transaction_id(),
            "type": "WITHDRAWAL",
            "amount": amount,
            "balance": self.balance,
            "timestamp": datetime.now()
        }

    def transfer(self, to_account: 'Account', amount: Decimal) -> dict:
        """Transfer funds between accounts"""
        # Withdraw from source
        withdrawal = self.withdraw(amount)

        try:
            # Deposit to destination
            deposit = to_account.deposit(amount)

            return {
                "transaction_id": self.generate_transaction_id(),
                "type": "TRANSFER",
                "from_account": self.account_number,
                "to_account": to_account.account_number,
                "amount": amount,
                "timestamp": datetime.now()
            }
        except Exception as e:
            # Rollback on failure
            self.deposit(amount)
            raise e

KYC/AML Compliance

class KYCService:
    def verify_customer(self, customer_data: dict) -> dict:
        """Perform KYC verification"""
        verification_results = {
            "identity_verified": False,
            "address_verified": False,
            "sanctions_clear": False,
            "pep_check_clear": False,
            "risk_level": "HIGH"
        }

        # Identity verification
        verification_results["identity_verified"] = self.verify_identity(
            customer_data["id_document"]
        )

        # Address verification
        verification_results["address_verified"] = self.verify_address(
            customer_data["proof_of_address"]
        )

        # Sanctions screening
        verification_results["sanctions_clear"] = self.screen_sanctions(
            customer_data["name"],
            customer_data["date_of_birth"]
        )

        # PEP (Politically Exposed Person) check
        verification_results["pep_check_clear"] = self.check_pep(
            customer_data["name"]
        )

        # Calculate risk level
        verification_results["risk_level"] = self.calculate_risk_level(
            verification_results
        )

        return verification_results

class AMLMonitoring:
    def monitor_transaction(self, transaction: dict) -> dict:
        """Monitor transaction for suspicious activity"""
        flags = []

        # Large transaction
        if transaction["amount"] > 10000:
            flags.append("LARGE_TRANSACTION")

        # Rapid succession of transactions
        if self.check_velocity(transaction["account_id"]):
            flags.append("HIGH_VELOCITY")

        # Unusual pattern
        if self.check_pattern(transaction):
            flags.append("UNUSUAL_PATTERN")

        # International transfer to high-risk country
        if transaction.get("international") and \
           self.is_high_risk_country(transaction.get("destination")):
            flags.append("HIGH_RISK_COUNTRY")

        if flags:
            self.file_suspicious_activity_report(transaction, flags)

        return {
            "flagged": len(flags) > 0,
            "flags": flags,
            "risk_score": self.calculate_aml_risk_score(flags)
        }

Payment Processing

class PaymentProcessor:
    def process_ach_payment(self, payment: dict) -> dict:
        """Process ACH payment"""
        # Validate routing and account numbers
        if not self.validate_routing_number(payment["routing_number"]):
            raise ValueError("Invalid routing number")

        # Create ACH file
        ach_batch = self.create_ach_batch([payment])

        # Submit to ACH network
        submission_result = self.submit_to_ach_network(ach_batch)

        return {
            "payment_id": payment["id"],
            "status": "PENDING",
            "expected_settlement": self.calculate_settlement_date(),
            "trace_number": submission_result["trace_number"]
        }

    def process_wire_transfer(self, wire: dict) -> dict:
        """Process SWIFT wire transfer"""
        # Generate SWIFT message
        swift_message = self.create_swift_mt103(wire)

        # Send via SWIFT network
        result = self.send_swift_message(swift_message)

        return {
            "wire_id": wire["id"],
            "status": "SENT",
            "swift_reference": result["reference"],
            "fee": self.calculate_wire_fee(wire["amount"])
        }

Interest Calculation

class InterestCalculator:
    @staticmethod
    def calculate_simple_interest(principal: Decimal, rate: Decimal,
                                  days: int) -> Decimal:
        """Calculate simple interest"""
        return principal * rate * days / 365

    @staticmethod
    def calculate_compound_interest(principal: Decimal, annual_rate: Decimal,
                                   years: int, compounds_per_year: int = 12) -> Decimal:
        """Calculate compound interest"""
        rate_per_period = annual_rate / compounds_per_year
        num_periods = years * compounds_per_year

        return principal * ((1 + rate_per_period) ** num_periods - 1)

    @staticmethod
    def calculate_loan_payment(principal: Decimal, annual_rate: Decimal,
                              months: int) -> Decimal:
        """Calculate monthly loan payment"""
        monthly_rate = annual_rate / 12

        payment = principal * (monthly_rate * (1 + monthly_rate) ** months) / \
                  ((1 + monthly_rate) ** months - 1)

        return payment.quantize(Decimal('0.01'))

Best Practices

  • Implement two-factor authentication
  • Use encryption for sensitive data (at rest and in transit)
  • Maintain complete audit trails
  • Implement real-time fraud detection
  • Ensure ACID compliance for transactions
  • Regular security audits and penetration testing
  • Implement rate limiting on APIs
  • Use tokenization for sensitive data
  • Maintain disaster recovery and business continuity plans
  • Regular regulatory compliance reviews

Anti-Patterns

❌ Storing sensitive data unencrypted ❌ No transaction logging/audit trail ❌ Synchronous payment processing ❌ Ignoring regulatory compliance ❌ No fraud detection mechanisms ❌ Using floats for money calculations ❌ No backup and recovery procedures

Resources

平台分布

Claude Code

30.01%
按下载量换算347

OpenCode

21.75%
按下载量换算251

Antigravity

18.26%
按下载量换算211

Cursor

12.65%
按下载量换算146

Codex

8.02%
按下载量换算93

Gemini CLI

3.24%
按下载量换算37

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。

继续浏览同类 Skills