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.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

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

A lean, security-aware instruction skill with concrete decision logic and a clear output schema, structured into well-signaled steps. The main gap is the absence of explicit feedback-loop guidance for upstream or screening failures.

Dimension	Reasoning	Score
Conciseness	Lean and dense throughout — no re-teaching of KYC/AML concepts, a compact factor table, and a non-obvious trust-boundary callout that earns its tokens; every section pulls its weight.	5 / 5
Actionability	Concrete guidance via a field-to-scoring factor table, an output JSON schema with enum values, and an explicit 'clear only if' routing rule; falls short of a 5 only because rule-outcome generation depends on an external grid with no worked example.	4 / 5
Workflow Clarity	A clear four-step sequence with an explicit gating checkpoint for 'clear' in Step 4, but no feedback loop for upstream or screening-MCP failures keeps it below the anchor-5 bar.	4 / 5
Progressive Disclosure	Well-organized into clearly headed steps with a table and code block, no nested references, and the large external source (the rules grid) is appropriately externalized to the screening MCP or a provided file; no bundle files exist to require further splitting.	5 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 concise, specific, third-person description that pinpoints the skill's concrete actions and gives an explicit upstream trigger, with only minor gaps in trigger-term synonym coverage. Voice and distinctiveness are strong.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions tied to the domain — 'assign a risk rating', 'list every rule outcome with the rule cited', 'flag what's missing or escalation-worthy' — with comprehensive coverage of the skill's stated purpose.	5 / 5
Completeness	Clearly answers both 'what' (apply rules grid → rating + outcomes + flags) and 'when' ('Use after kyc-doc-parse'), but the trigger is sequencing-based rather than a user-utterance phrase, keeping it just below the anchor-5 bar.	4 / 5
Trigger Term Quality	Strong domain-natural terms (KYC/AML, onboarding record, risk rating, escalation) plus an explicit upstream trigger ('Use after kyc-doc-parse'), but lacks synonyms and file-extension-style variants that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (KYC/AML rules-grid scoring) bound to a named upstream skill, with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anthropics/financial-services
Path: plugins/agent-plugins/kyc-screener/skills/kyc-rules/SKILL.md
Commit: 69cbc81

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

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.