Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    aml alert triage

    1

    Aggregates evidence for AML alerts, matches against approved typologies, computes risk scores, and produces prioritized investigation briefs. Decision support only; SAR filing decisions remain human.

    $1.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    aml alert triage

    aml alert triage

    Example session with this skill installed

    Triage these three alerts from the morning queue. Alert 101: High risk customer John Doe, 5 transactions totaling 50k to high-risk region. Alert 102 and 103 are low-value retail alerts.

    • Read your context and instructions
    • Compiled the aml alert triage

    Processed 3 alerts from the morning queue. Alert 101 has been flagged for immediate review due to high-risk typology matches.

    AML Alert Triage Report — Global Bank, 2023-10-27

    1. Summary

    • Total Alerts: 3
    • Priority Distribution: 1 High, 2 Low
    • Average Risk Score: 42.5
    • Escalation Candidates: Alert 101

    2. Investigation Briefs

    Alert 101: John Doe

    • Risk Score: 88/100
    • Typology: Rapid Movement of Funds / High-Risk Jurisdiction
    • Recommended Action: Immediate escalation to Senior Investigator.
    • Decision: Management decision required for SAR filing.

    3. Typology Distribution

    • High-Risk Jurisdiction: 1 match
    • Structuring: 0 matches
    • Retail/Standard: 2 matches

    4. Alert Details

    • Alert 101: 5 transactions to [Region X]. Source E1. Indicators: Large round-sum transfers.
    • Alert 102: Retail payment. Source E2. No indicators detected.
    • Alert 103: Retail payment. Source E3. No indicators detected.

    5. Warnings and Data Quality

    • No data quality warnings. All transactions successfully parsed.

    6. Items for Human Review

    • SAR Filing Decision: Required for Alert 101.
    • Customer Action: Review account 101 for potential restriction.

    Next steps

    • Review the evidence brief for Alert 101 in Section 2.
    • Confirm the SAR filing decision in the case management system.
    • Archive the low-priority briefs for Alerts 102 and 103.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    High volume AML alert queues often lead to analyst burnout and inconsistent risk assessment. Manual evidence gathering and typology matching are slow, error-prone, and difficult to audit. This skill automates the aggregation of transaction data to produce prioritized investigation briefs for human compliance officers.

    What it does

    • Automated Evidence Aggregation compiles transaction history, customer risk ratings, and narratives into structured briefs.
    • Typology Matching compares transaction patterns against approved money laundering indicators and categories.
    • Risk Scoring computes deterministic scores to rank alerts by priority, highlighting immediate escalation candidates.
    • Indicator Detection identifies specific red flags like structuring, rapid movement of funds, or high-risk jurisdictions.
    • Decision Support generates standardized investigation packages while leaving final SAR filing decisions to human analysts.

    How it works

    1. Data Intake parses alert records, including transaction details, customer profiles, and narratives, assigning source IDs for auditability.
    2. Request Generation constructs a request.json file following a strict schema to ensure all indicators are captured.
    3. Engine Execution runs a deterministic script to match typologies and compute risk scores without subjective bias.
    4. Report Production delivers a structured Markdown report featuring investigation briefs, typology distributions, and items requiring human review.

    Frameworks & tools

    The skill utilizes a Python-based processing engine (scripts/run.py) and JSON schema validation (assets/input.schema.json) for data integrity. It follows predefined AML methodologies and markers for compliance reporting.

    Why this beats prompting it yourself

    Manual prompting often results in inconsistent risk scoring and missed indicators across large datasets. This skill uses a deterministic script to ensure every alert is measured against the same typology definitions, removing LLM hallucinations from the risk calculation process.

    Use cases

    • Prioritizing daily transaction monitoring queues based on computed risk scores.
    • Preparing comprehensive evidence packages for SAR/STR committee reviews.
    • Performing quality assurance checks to ensure all red-flag indicators were identified.
    • Triage of suspicious activity reports in both English and French banking environments.

    Known limitations

    Does not perform real-time transaction blocking or sanctions screening. Cannot make final SAR filing decisions or close cases without human intervention. Standard KYC document review is out of scope.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Cannot file SARs or close cases. Human review is mandatory. Scope excludes real-time blocking, sanctions screening, and KYC document review. Requires alerts in specific JSON-compatible formats.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    By automating the tedious process of gathering evidence and matching patterns against known typologies, this skill allows compliance officers to focus on high-level decision-making rather than manual data entry, significantly reducing analyst burnout.

    This skill is designed to work with any AI agent capable of executing Python-based processing engines and handling JSON-structured data, making it adaptable to most enterprise AI orchestration platforms.

    You will receive a complete integration package including the Python-based processing engine, pre-defined JSON schemas for data validation, and standardized reporting templates for your investigation briefs.

    Unlike simple prompting, which can lead to inconsistent risk assessments and 'hallucinations,' this skill uses a deterministic script to ensure every alert is measured against the exact same compliance markers every time.

    No, this skill is a decision-support tool designed to triage and prioritize alerts; it does not have the authority to block live transactions or autonomously file Suspicious Activity Reports (SARs) without human oversight.

    Setting up involves mapping your internal transaction and customer data to the provided JSON schema, allowing the processing engine to ingest your records and begin generating prioritized briefs.