How to use
- Copy the installation command and review the source package before installing it in your own agent environment.
- Check the source document for required tools, credentials and supported hosts.
- Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/vyayasan/kyc-analyst --skill screeningBefore you start
- Installation does not include a model subscription, API allowance or permission to access your files.
- Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document
Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.
Screening Skill - v1.0.0
Comprehensive sanctions and PEP screening with multi-database search, false positive assessment, and HITL decision gates.
Overview
Screening is a mandatory component of all KYC workflows. This skill provides standalone screening capability for ad-hoc checks, batch processing, and integration into onboarding/refresh workflows.
Screening Databases (12+ Sources)
Sanctions Lists
- OFAC SDN - US Specially Designated Nationals
- EU Consolidated Sanctions List - European Union
- UK HM Treasury - UK Financial Sanctions
- UN Consolidated List - United Nations Security Council
- Interpol - Red and Yellow Notices
- OpenSanctions - Open-source aggregated sanctions data
PEP Databases
- EveryPolitician - Global political figures
- Wikidata - Political and public figures
- UK Parliament - Register of Members' Interests
- CIA World Factbook - National leadership
- Electoral Commission databases - Candidates and office holders
Criminal/Legal
- UK Court records - Criminal convictions, CCJs
- Companies House - Insolvency records, disqualified directors
Screening Process
Step 1: Identify Screening Targets
- Customer (individual or entity)
- All beneficial owners (>25% threshold)
- Directors and senior management (entities)
- Family members and close associates (PEP cases)
Step 2: Execute Searches
For each target, search against all applicable databases:
- Record search date, platform, and search terms
- Document all matches (including potential false positives)
- Screenshot or save evidence
Step 3: False Positive Assessment [HITL Checkpoint]
When a potential match is found:
| Factor | Assessment |
|---|---|
| Name similarity | Exact / Partial / Common name |
| Date of birth | Match / Mismatch / Unknown |
| Nationality | Match / Mismatch |
| Location | Match / Mismatch |
| Photograph | Match / Mismatch / Not available |
| Context | Supports match / Against match |
Decision:
- TRUE MATCH: Immediate escalation to Manager + MLRO
- FALSE POSITIVE: Document reasoning and evidence, proceed
- UNCERTAIN: Escalate for senior review
Step 4: Generate Report
- Screening summary with all targets and results
- False positive assessment documentation (if applicable)
- Escalation brief (if true match or uncertain)
- Recommendations and next steps
Batch Screening
For processing multiple alerts:
Analyze [X] screening alerts from uploaded CSV.
For each alert:
- Assess match quality
- Check for false positive patterns
- Research as needed
- Provide recommendation (CLEAR/ESCALATE)
Create Excel report with all analyses.Regulatory Basis
- OFAC compliance (US)
- EU Sanctions Regulations
- UK Money Laundering Regulations 2017
- UN Security Council Resolutions
- AMLD5 screening requirements
Version: 1.0.0 Author: Vyayasan
