Token导航 LogoToken导航

Agent Skill · 研究检索

mova-aml-triage(Mova AML 分类)

mova-aml-triage 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

mova-aml-triage 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为执行命令;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 18,757。

总安装 5,933周安装 240GitHub Stars 公开资料未说明下载 1,862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-0
版本
1.0.1

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:mova-aml-triage(Mova AML 分类)
来源仓库:https://github.com/mova-compact/mova-aml-triage
安装命令:
openclaw skills install mova-aml-triage
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。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install mova-aml-triage

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

提交AML交易监控警报进行L1分类与人机交互合规决策。适用于金融风控与反洗钱场景。mova-aml-triage 属于研究检索类 Skill,可作为该场景下的辅助能力补充。自动识别高风险交易并触发人工审核。需上传相关交易记录与上下文信息。注意数据脱敏与隐私保护要求。

适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。

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 OpenClaw;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 openclaw skills install mova-aml-triage;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

    它需要执行命令,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

mova-aml-triage 怎么安装?

在终端执行 openclaw skills install mova-aml-triage。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

mova-aml-triage 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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。

mova-aml-triage 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 openclaw skills install mova-aml-triage 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

mova-aml-triage 是免费的吗?

来源标注的许可证是 MIT-0。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。

mova-aml-triage 用的人多吗?

公开数据是累计安装 5,933 次,近一周安装 240 次,下载 1,862 次。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。

mova-aml-triage 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 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 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
mova-aml-triage

Mova AML 分类 · 本页

5,933—执行命令MIT-0通过

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

name
mova-aml-triage
description
Submit an AML transaction monitoring alert for automated L1 triage and human-in-the-loop compliance decision via MOVA. Trigger when the user mentions an AML alert, transaction monitoring alert ID, or asks to triage/review a suspicious transaction alert. Mandatory human escalation on sanctions hit, PEP flag, or risk score above 85.
license
MIT-0
metadata
{"openclaw":{"plugin":{"name":"MOVA","installCmd":"openclaw plugins install openclaw-mova"},"dataSentToExternalServices":[{"service":"MOVA API (api.mova-lab.eu)","data":"alert ID, rule ID, risk score, customer data, transaction list, PEP/sanctions flags, human decision, audit metadata"},{"service":"Sanctions screening connector (read-only)","data":"customer ID and transaction data screened against OFAC, EU, UN lists"},{"service":"Customer risk connector (read-only)","data":"customer ID for risk rating and prior alert history lookup"}]}}
Contract Skill — A ready-to-use MOVA HITL workflow. Requires the openclaw-mova plugin.

MOVA AML Alert Triage

Submit a transaction monitoring alert to MOVA for automated L1 triage — with typology matching, sanctions screening, and a human compliance decision gate backed by a tamper-proof audit trail.

What it does

  1. AI triage — checks sanctions lists (OFAC/EU/UN), PEP status, transaction burst patterns, customer risk rating, prior alert history, and typology matching (structuring, layering, smurfing, etc.)
  2. Risk snapshot — surfaces anomaly flags and triage recommendation
  3. Human decision gate — compliance analyst chooses: clear / escalate to L2 / immediate escalate
  4. Audit receipt — every decision is signed, timestamped, and stored in an immutable compact journal

Mandatory escalation rules enforced by policy:

  • Risk score > 85 → mandatory human escalation
  • Sanctions hit → immediate escalation, no exceptions
  • PEP flag → mandatory L2 escalation

Requirements

Plugin: MOVA OpenClaw plugin must be installed in your OpenClaw workspace.

Data flows:

  • Alert data + customer ID + transactions → api.mova-lab.eu (MOVA platform, EU-hosted)
  • Customer data → sanctions screening (OFAC, EU, UN — read-only, no data stored)
  • Customer ID → risk rating and prior alert history (read-only)
  • Audit journal → MOVA R2 storage, cryptographically signed
  • No data is sent to third parties beyond the above

Quick start

Say "triage AML alert ALERT-1002" and provide the alert details:

https://raw.githubusercontent.com/mova-compact/mova-bridge/main/test_aml_ALERT-1002.png

Demo

Step 1 — Alert submitted: TM-STRUCT-11, risk 91, RISK HIGH flag Step 1

Step 2 — AI analysis: structuring typology matched, risk 91/100, escalate_l2 decision Step 2

Step 3 — Audit receipt + compact journal with full compliance event chain Step 3

Why contract execution matters

  • Escalation rules are policy, not prompts — risk_score > 85 and sanctions hits trigger mandatory gates that cannot be bypassed
  • Full typology matching — AI identifies structuring, layering, and smurfing patterns against your transaction monitoring rules
  • Immutable audit trail — when a regulator asks "who cleared or escalated ALERT-1002 and why?" — the answer is in the system with an exact timestamp and reason
  • AMLD6 / FATF ready — AML decisions require the human oversight, full explainability, and documented decision chain required by AMLD6 and FATF guidance

What the user receives

OutputDescription
Risk score0–100 assessment with threshold evaluation
Typology matchRule ID + description (structuring, layering, etc.)
Sanctions checkOFAC / EU / UN screening result
PEP statusPEP flag with category
Customer riskRisk rating, burst intensity, jurisdiction risk
Anomaly flagsrapid_transfer, new_beneficiary, high_burst, sanctions_hit, pep_flag
FindingsStructured list with severity codes
Prior alertsHistorical alert count
Recommended actionAI-suggested triage decision
Decision optionsclear / escalate_l2 / immediate_escalate
Audit receipt IDPermanent signed record of the compliance decision
Compact journalFull event log: triage → sanctions → human decision

When to trigger

Activate when the user:

  • Mentions an alert ID (e.g. "ALERT-1002")
  • Says "triage this alert", "review AML alert", "check transaction monitoring alert"
  • Provides customer and transaction data for compliance review

Before starting, confirm: "Submit alert [alert_id] for MOVA L1 triage?"

If details are missing — ask once for: alert ID, rule ID, risk score, customer ID, customer jurisdiction, triggered transactions.

Step 1 — Submit alert

Call tool mova_hitl_start_aml with:

  • alert_id, rule_id, rule_description, risk_score
  • customer_id, customer_name, customer_risk_rating (low/medium/high), customer_type (individual/business), customer_jurisdiction (ISO country code)
  • triggered_transactions: array of {transaction_id, amount_eur}
  • pep_status: boolean, sanctions_match: boolean
  • historical_alerts: optional array of prior alert IDs

Step 2 — Show analysis and decision options

If status = "waiting_human" — show AI triage summary and ask to choose:

  • clear — Clear as false positive
  • escalate_l2 — Escalate to L2 analyst
  • immediate_escalate — Immediate escalation — freeze account

Show recommended option if present (mark ← RECOMMENDED).

Call tool mova_hitl_decide with:

  • contract_id: from the response above (NOT the alert ID)
  • option: chosen decision
  • reason: analyst reasoning

Step 3 — Show audit receipt

Call tool mova_hitl_audit with contract_id. Call tool mova_hitl_audit_compact with contract_id for the full signed event chain.

Connect your real AML systems

By default MOVA uses a sandbox mock. To route checks against your live infrastructure, call mova_list_connectors with keyword: "aml".

Relevant connectors:

Connector IDWhat it covers
connector.screening.pep_sanctions_v1PEP & sanctions screening (OFAC, EU, UN)
connector.aml.transaction_history_v1Transaction history from core banking
connector.policy.aml_rules_v1AML rule engine / typology rules
connector.risk.jurisdiction_v1Country FATF risk classification

Call mova_register_connector with connector_id, endpoint, optional auth_header and auth_value.

Rules

  • NEVER make HTTP requests manually
  • NEVER invent or simulate results — if a tool call fails, show the exact error
  • Use MOVA plugin tools directly — do NOT use exec or shell
  • CONTRACT_ID comes from the mova_hitl_start_aml response, not from the alert ID

平台分布

OpenClaw

85.26%
按下载量换算1,588

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 openclaw skills install mova-aml-triage 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills