kyc-doc-parse

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

93%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 tightly written, highly actionable extraction skill: concrete JSON schema, clear three-step sequence, and an appropriate untrusted-input warning. The only gap is the absence of an explicit validate/retry feedback loop, which keeps workflow clarity at 4 rather than 5.

Dimension	Reasoning	Score
Conciseness	The body is lean: a justified untrusted-input warning, a compact doc-type table, a single JSON schema, and a one-line gap-flagging step, with no padding or explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	The output is a fully specified, copy-paste-ready JSON schema with typed fields, enumerated values (e.g. "individual \| entity \| trust", control_basis options), and concrete doc-type examples, giving Claude an unambiguous, executable target.	5 / 5
Workflow Clarity	Three clearly sequenced steps (inventory, extract, flag gaps) with Step 3 acting as a verification checkpoint, but there is no explicit validate-and-retry feedback loop; this sits above the 3-anchor (gaps present) but below the 5-anchor (explicit validation with error-recovery loops).	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and none are needed; the self-contained, well-sectioned body is under 50 lines and cleanly organized, meeting the simple-skill exception for a top progressive-disclosure score.	5 / 5
	Total	19 / 20 Passed

Description

78%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 specific, third-person description that clearly states what the skill does and when to use it, with strong distinctiveness and good trigger coverage. Its main weakness is that the 'when' clause frames usage as workflow position rather than user-facing trigger phrases.

Suggestions

Add explicit user-facing trigger phrasing to the 'when' clause, e.g. 'Use when the user provides an investor or client onboarding packet for KYC review'.

Broaden trigger-term coverage with synonyms such as 'AML onboarding', 'customer due diligence', or relevant form names (W-8BEN-E, CRS).

Consider naming additional concrete actions beyond 'parse' (e.g. 'extract, normalize, and inventory') to push specificity toward the 5-anchor.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Parse an investor or client onboarding packet into structured KYC fields") and enumerates specific extracted categories (identity, ownership, control, source of funds, document inventory), but the action vocabulary is essentially a single verb (parse) rather than multiple distinct actions, so it sits just below the comprehensive 5-anchor.	4 / 5
Completeness	The 'what' is clear (parse onboarding packet into structured KYC fields) and a 'when' is provided ("Use as the first step of KYC screening"), satisfying the explicit-trigger requirement above the cap of 3; however the 'when' describes workflow position rather than concrete user trigger phrases, matching the 4-anchor where 'when' could be more specific.	4 / 5
Trigger Term Quality	Natural user-facing terms like "onboarding packet", "KYC fields", and "KYC screening" are present and domain-appropriate, but common synonyms or filename/extension triggers are absent, leaving it just short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche (KYC/onboarding document parsing) with distinct triggers and an explicit downstream handoff ("output feeds the rules engine"), minimizing overlap with unrelated skills.	5 / 5
	Total	17 / 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-doc-parse/SKILL.md
Commit: 69cbc81

Reviewed: about 9 hours 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.