Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Aml Program Review

ASecurity

Structured review of an AML program against FATF / FFIEC expectations — the 5 pillars, common findings, regulatory citations with primary sources. Used by `aml-kyc-analyst` (primary).

7 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgotesting

Security Analysis

A100/100

Scanned 9/23/2026

$npx -y skills add mcorbett51090/RavenClaude --skill aml-program-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Aml Program Review?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Aml Program Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mcorbett51090-aml-program-review/badge)](https://www.skillsdirectory.com/skills/mcorbett51090-aml-program-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: aml-program-review
description: Structured review of an AML program against FATF / FFIEC expectations — the 5 pillars, common findings, regulatory citations with primary sources. Used by `aml-kyc-analyst` (primary).
---

# Skill: aml-program-review

**Purpose:** Structured review of an AML program against FATF / FFIEC expectations. Used by `aml-kyc-analyst` (primary).

## When to use

- Pre-exam AML program review
- Annual independent review (mandated under most regimes)
- Post-incident program assessment
- New-licence applicant readiness check
- Acquired-entity integration

## The 5 pillars (US BSA / FFIEC framework; equivalent concepts in most regimes)

Most regulators expect an AML program with these components:

1. **Designated AML Officer** with appropriate authority, resources, board access
2. **Internal policies, procedures, and controls** for CDD, EDD, transaction monitoring, sanctions, reporting
3. **Ongoing training** for relevant employees, with records
4. **Independent testing** at appropriate frequency, with documented findings + remediation
5. **CDD / beneficial-ownership** identification + ongoing risk-based monitoring

(Bermuda's AMLR 2008 captures equivalent concepts with different structure; map them on review.)

## Review structure

For each pillar, assess:

- **Design** — does the documented program meet the regulator's expectations?
- **Implementation** — does what's done in practice match what's documented?
- **Effectiveness** — does the implementation actually catch what it's supposed to catch?

A program can be well-designed but poorly implemented, or implemented as designed but ineffective at catching what it should. Differentiate.

## Common findings (in order of frequency in mid-market firms)

### Design findings

- BOI verification weak (relies on customer's own statement for higher-risk corporate customers)
- EDD triggers documented but actual EDD content is the same as CDD with more pages
- Sanctions screening covers customers but not connected parties / counterparties
- Negative-news screening has no documented procedure
- Transaction monitoring rule set never validated; thresholds at vendor defaults
- AML training is generic; doesn't reflect the firm's actual product / customer base

### Implementation findings

- KYC files have gaps (missing BOI, expired ID, no risk rating recorded)
- Sanctions hits cleared with no documented rationale
- Alert backlogs (TM alerts unworked beyond regulator-expected SLAs)
- SAR / STR filings sparse; no continuing-activity reports
- Periodic refresh skipped on higher-risk customers
- AML Officer not actually independent (also runs operations)

### Effectiveness findings

- Independent-testing reports never trigger material remediation
- Training records exist but knowledge doesn't (interviews fail)
- Board / committee minutes show no substantive AML discussion
- Risk assessment static for years; new products / customers / geographies not reflected

## Report structure

For each pillar, produce:

| Pillar | Design (✅ / ⚠️ / 🔴) | Implementation (✅ / ⚠️ / 🔴) | Effectiveness (✅ / ⚠️ / 🔴) | Findings | Severity (P0 / P1 / P2) |
|---|---|---|---|---|---|

Plus:
- **Top 3 remediations** prioritized
- **Regulator-exposure score** (e.g., "BMA exam unlikely to clear without addressing finding #1")
- **Recommendation** (e.g., refresh program, targeted remediation, comprehensive rebuild)

## Severity guide

- **P0** — program fails a regulator's published expectation; remediate before next exam window.
- **P1** — program meets expectations on paper, fails in practice; remediate before next refresh.
- **P2** — improvable; not a current gap.

## Anti-patterns the review catches

- Program designed by the vendor template, customized only by find-and-replace
- "Independent" testing done by the team being tested
- AML Officer with no actual authority to escalate to the board
- Training records that don't tie to the people actually doing AML work
- "We follow industry best practice" used as substantive policy text

## See also

- Skill: [`../sar-narrative-drafting/SKILL.md`](../sar-narrative-drafting/SKILL.md)
- Template: [`../../templates/aml-program-outline.md`](../../templates/aml-program-outline.md)
- Template: [`../../templates/kyc-edd-workpaper.md`](../../templates/kyc-edd-workpaper.md)
- Agent: [`../../agents/aml-kyc-analyst.md`](../../agents/aml-kyc-analyst.md)

Attribution

mcorbett51090mcorbett51090
View sourceSee grades on GitHubMore from mcorbett51090 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →