智能体工作流

sumsub-create-aml-resolution-rules

sumsub/agent-skills

Create, edit, reorder, delete, and publish Sumsub AML Resolution Rules (the AML Resolution Rule Chain) that auto-review AML screening hits. TRIGGER when the user wants to auto-clear false positives, auto-confirm true positives, carry over previous AML reviews, tag AML hits, or set up / inspect / publish the AML rule chain. SKIP for transaction-monitoring (KYT) rules, workflow routing, or AML check settings on a level (separate skills cover those).

  • 503 次安装
  • 7 星标
  • 收录于

安装命令

npx skills add https://github.com/sumsub/agent-skills --skill sumsub-create-aml-resolution-rules

SKILL.md

Sumsub — Create AML Resolution Rules

Builds AML resolution rules from a compact spec, upserts them into the tenant's draft AML rule chain via the agent API, and (optionally) publishes the draft to make it live. The chain (also called the AML Resolution Rule Chain) auto-reviews incoming AML screening hits: each rule, in order, is evaluated against every not-yet-reviewed hit, and on match sets the hit's review (match status / risk level / whitelisted / note) and/or tags the case.

Every network step goes through one signed client, ${CLAUDE_SKILL_DIR}/scripts/aml_rules_api.py (draft, published, archive, library, upsert, reorder, delete, publish); rule payloads are assembled by ${CLAUDE_SKILL_DIR}/scripts/build_aml_rule.py.

Endpoints

All under /resources/api/agent/amlResolutionRules. There is one rule chain per tenant, versioned as draft → published → archived revisions. (Each row maps to an aml_rules_api.py subcommand — you never call these paths by hand.)