# sumsub-create-aml-resolution-rules

Builds and publishes Sumsub rules that auto-review AML screening hits: clearing false positives, confirming true ones.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 447 installs · ★ 7
- Author: sumsub
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/sumsub/agent-skills/tree/HEAD/skills/sumsub-create-aml-resolution-rules/SKILL.md
- Updated: 2026-10-02
- HTML: https://affpapa.org/en/nevibecode/skills/sumsub-create-aml-resolution-rules

## What it does

The skill manages the AML Resolution Rule Chain inside a Sumsub tenant. Rules run top to bottom against every hit that has not been reviewed yet; on a match they set the review outcome (match status, risk level, whitelist flag, note) and can tag the case. You describe rules in a compact spec, the skill upserts them into the draft chain through the agent API, and publishing is optional.

Network calls go through one signed client, `${CLAUDE_SKILL_DIR}/scripts/aml_rules_api.py`, with the subcommands `draft`, `published`, `archive`, `library`, `upsert`, `reorder`, `delete`, `publish`; rule bodies are assembled by `${CLAUDE_SKILL_DIR}/scripts/build_aml_rule.py`. You need an AI-purpose App Token holding `manageAmlCases` and `manageClientSettings`, plus `SUMSUB_APP_TOKEN` and `SUMSUB_SECRET_KEY`. The token must start with `sbx:` — a production token is rejected, since these rules decide real AML hits.

Live and sandbox share the same chain; only cases and applicants are separated. Publishing rewrites the rules that handle production screening hits, so do it only when the user asks outright. Everything before that step is safe: reading, upserting, reordering and deleting touch the draft, which reviews nothing until it goes live. A refused publish is normal once the integration is active — report it and send the user to the Sumsub web UI.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add sumsub/agent-skills --skill sumsub-create-aml-resolution-rules -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/sumsub-create-aml-resolution-rules/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/sumsub-create-aml-resolution-rules/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add sumsub/agent-skills --skill sumsub-create-aml-resolution-rules -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/sumsub-create-aml-resolution-rules/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add sumsub/agent-skills --skill sumsub-create-aml-resolution-rules -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/sumsub-create-aml-resolution-rules/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install sumsub/agent-skills sumsub-create-aml-resolution-rules
```

2. **Manually: put the files in place**
- File: `.github/skills/sumsub-create-aml-resolution-rules/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add sumsub/agent-skills --skill sumsub-create-aml-resolution-rules -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/sumsub/agent-skills --path skills/sumsub-create-aml-resolution-rules
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/sumsub-create-aml-resolution-rules/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add sumsub/agent-skills --skill sumsub-create-aml-resolution-rules -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/sumsub/agent-skills/tree/HEAD/skills/sumsub-create-aml-resolution-rules/SKILL.md

## When to use it
- clear a false positive AML hit automatically
- confirm a true match without manual review
- carry a previous review result onto a new hit
- tag a case when a rule matches
- reorder the rule chain and publish the draft

## Example prompts
- Build a rule that clears false positives on AML screening and show me the draft chain
- Add a rule tagged `match_tin` and place it above the broad cleanup rules
- Publish the AML Resolution Rules draft chain

## Similar
- [git-guardrails-claude-code](https://affpapa.org/en/nevibecode/skills/git-guardrails-claude-code.md) — skill · 499069 installs
- [ponytail-review](https://affpapa.org/en/nevibecode/skills/ponytail-review.md) — skill · 57000 installs
- [ponytail-audit](https://affpapa.org/en/nevibecode/skills/ponytail-audit.md) — skill · 45400 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit.md) — skill · 54800 installs
- [security-and-hardening](https://affpapa.org/en/nevibecode/skills/security-and-hardening.md) — skill · 70200 installs
- [supabase](https://affpapa.org/en/nevibecode/skills/supabase.md) — skill · 8 installs

From the same set: [sumsub/agent-skills](https://affpapa.org/en/nevibecode/by/sumsub/agent-skills.md) — 11 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md