prior-auth-letter-drafter

Generate professional prior authorization request letters for insurance companies with proper clinical justification and formatting.

Quality

36%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/prior-auth-letter-drafter/SKILL.md

Quality

Content

14%

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

This skill is heavily padded with generic boilerplate content that is not specific to prior authorization letter drafting. The actual domain-specific value (input parameters table, service types, output description, reference files) is buried among repetitive purpose statements, circular cross-references, and template sections like Risk Assessment and Security Checklist that don't help Claude draft better letters. The skill would benefit enormously from being stripped down to its core: input schema, an example letter output, clinical justification guidance, and carrier-specific formatting rules.

Suggestions

Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) and circular 'See ## X above' references to cut the document by at least 60%.

Add a concrete example showing a complete input → output pair: sample patient data and the resulting prior authorization letter, so Claude knows exactly what format and tone to produce.

Replace the generic workflow with prior-auth-specific steps: validate ICD-10/CPT code pairing, check carrier-specific requirements, draft clinical justification, format letter per carrier template, verify all required fields are present.

Inline the key content from referenced files (e.g., common clinical justification phrases, carrier requirement differences) since the bundle files are not available, or provide the actual bundle files.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. Multiple sections restate the same purpose verbatim ('Generate professional prior authorization request letters for insurance companies with proper clinical justification and formatting'). Contains boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) that add no actionable value for Claude. Self-referential 'See ## X above' links are circular and wasteful. Much of the content is generic template filler not specific to prior auth letters.	1 / 3
Actionability	The input parameters table and service types are concrete and useful. The usage command and audit-ready commands provide executable examples. However, the actual letter generation logic is entirely opaque—there's no example of what a generated letter looks like, no template structure shown, and the core clinical justification guidance is deferred to a references file that isn't provided. The workflow steps are generic process steps, not specific to prior auth letter drafting.	2 / 3
Workflow Clarity	The workflow section is entirely generic ('Confirm the user objective, required inputs...') with no steps specific to prior authorization letter drafting. There are no validation checkpoints for the actual letter content (e.g., verifying ICD-10 codes match the clinical justification, checking carrier-specific requirements). The 'Example run plan' is also generic. For a medical document generation task with compliance implications, the absence of content validation steps is a significant gap.	1 / 3
Progressive Disclosure	The document contains circular self-references ('See ## Features above for related details' placed before the Features section, 'See ## Prerequisites above' when Prerequisites is below). References to bundle files (references/letter_template.docx, references/clinical_phrases.md, references/carrier_requirements.json) cannot be verified as no bundle is provided. The content is a monolithic wall mixing boilerplate with actual skill content, making navigation difficult.	1 / 3
	Total	5 / 12 Passed

Description

57%

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

The description identifies a clear and distinctive niche—prior authorization letters for insurance—which reduces conflict risk. However, it lacks an explicit 'Use when...' clause and could benefit from more specific action verbs and common user trigger terms like 'prior auth', 'PA request', or 'medical necessity'.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks for a prior auth letter, PA request, insurance pre-authorization, or medical necessity justification.'

Include common trigger term variations such as 'prior auth', 'PA request', 'pre-authorization', 'medical necessity letter', and 'insurance approval letter'.

List more specific concrete actions, e.g., 'Cites diagnosis codes (ICD-10), references treatment guidelines, structures appeal arguments, and formats letters per insurance company requirements.'

Dimension	Reasoning	Score
Specificity	Names the domain (prior authorization) and a couple of actions (generate letters, clinical justification, formatting), but doesn't list multiple distinct concrete actions like filling specific sections, citing medical codes, or attaching supporting documentation.	2 / 3
Completeness	Clearly answers 'what does this do' (generate prior authorization request letters with clinical justification and formatting), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill.	2 / 3
Trigger Term Quality	Includes good natural terms like 'prior authorization', 'insurance companies', and 'clinical justification', but misses common variations users might say such as 'prior auth', 'PA request', 'insurance approval', 'pre-authorization', 'medical necessity letter', or 'appeal letter'.	2 / 3
Distinctiveness Conflict Risk	Prior authorization request letters for insurance companies is a very specific niche that is unlikely to conflict with other skills. The combination of medical/insurance domain with letter generation creates a distinct trigger profile.	3 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: aipoch/medical-research-skills
Commit: d915031

Reviewed: 5 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.