CtrlK
BlogDocsLog inGet started
Tessl Logo

kyc-rules

Apply the firm's KYC/AML rules grid to a parsed onboarding record — assign a risk rating, list every rule outcome with the rule cited, and flag what's missing or escalation-worthy. Use after kyc-doc-parse; this skill decides nothing, it scores and routes.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured instruction skill: concise, concrete field mappings and output schema, a clearly sequenced workflow with an explicit disposition gate, and clean single-file organization. No bundle files are needed given the scope.

DimensionReasoningScore

Conciseness

Lean and efficient: a compact factor table and JSON schema with no explanation of concepts Claude already knows; the trusted-source guardrail earns its place rather than padding.

3 / 3

Actionability

Concrete, actionable guidance — specific source fields (nationality_or_jurisdiction, applicant_type, beneficial_owners), an explicit JSON output schema, and a precise routing rule; directional scoring is appropriate since exact thresholds live in the trusted grid.

3 / 3

Workflow Clarity

A clear four-step sequence with explicit gating validation in Step 4 ('clear only if rating is low/medium, all required docs received, and no escalation rule fired') plus a self-check constraint ('no outcome without a rule reference').

3 / 3

Progressive Disclosure

Under 50 lines with no external references needed; well-organized into Inputs and Steps 1–4, so well-organized sections suffice for a top score.

3 / 3

Total

12

/

12

Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with concrete actions, explicit trigger guidance, and low conflict risk. Its only weakness is trigger-term quality: the 'when' clause is framed as a workflow dependency on another skill rather than natural user phrases.

Suggestions

Add natural user trigger phrasing, e.g. 'Use when scoring a KYC/AML onboarding record or applying compliance rules to a parsed applicant file,' alongside the kyc-doc-parse dependency.

Include common variations a user might say ('KYC check', 'AML screening', 'compliance review') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'assign a risk rating, list every rule outcome with the rule cited, and flag what's missing or escalation-worthy' — rather than vague language.

3 / 3

Completeness

Clearly answers both what (apply rules grid, rate risk, list outcomes, flag gaps) and when ('Use after kyc-doc-parse'), with an explicit trigger clause present.

3 / 3

Trigger Term Quality

Relevant domain keywords (KYC/AML, onboarding, risk rating) appear, but the explicit trigger is a workflow dependency ('Use after kyc-doc-parse') rather than natural user phrasings, missing common variations like 'KYC check' or 'AML screening'.

2 / 3

Distinctiveness Conflict Risk

A clear compliance niche (KYC/AML scoring/routing for onboarding records, post kyc-doc-parse) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
anthropics/financial-services
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.