prior-auth-letter-drafter

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

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/prior-auth-letter-drafter/SKILL.md

Quality

Content

56%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.

The body offers executable commands, a clear sequenced workflow with validation and fallback, and a parameter table, but it is weighed down by generic boilerplate, an off-topic 'academic writing' bullet, empty forward-references, and a broken reference to a missing letter_template.docx. Trimming the boilerplate and fixing the reference would raise the two lowest dimensions.

Suggestions

Remove the off-topic 'academic writing tasks' bullet from When to Use and delete the 'See `## X` above' forward-references that convey no information.

Fix or remove the broken reference to references/letter_template.docx, which does not exist in the bundle.

Move generic skill-management sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) into a separate reference file to reduce inline bulk and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several padded sections — generic 'See `## X` above' forward-references that add no information, an off-topic 'academic writing tasks' bullet in When to Use, and large boilerplate blocks (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria) unrelated to prior auth letters.	2 / 5
Actionability	It provides copy-pasteable executable commands (py_compile, --help, --input/--output invocations) and a concrete input-parameter table with typed required/optional fields, with only minor gaps since the actual letter-production logic is delegated to scripts/main.py.	4 / 5
Workflow Clarity	A clear 5-step sequence (confirm → validate scope → execute packaged script → return structured result → fallback on failure) with a parse-validation checkpoint (py_compile) and an explicit error/fallback path; validation is light (compile-only, no output verification) so it stops just short of explicit feedback-loop anchoring.	4 / 5
Progressive Disclosure	A dedicated References section signals one-level-deep files, but references/letter_template.docx is cited in the body yet absent from the bundle (broken reference), and substantial generic content is inlined rather than split out, so structure is only partial.	3 / 5
	Total	13 / 20 Passed

Description

61%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.

The description has a clear, domain-specific 'what' with decent natural trigger terms, but it omits any explicit 'when to use' guidance and relies on a single core action, capping completeness and specificity. Adding a 'Use when...' clause with common synonyms would lift the two lowest dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when drafting prior authorization, prior auth, pre-authorization, or appeal/denial letters for insurance companies,' to remove the completeness cap and add natural synonyms.

Enumerate concrete actions beyond 'Generate' — e.g. 'draft, format, and assemble prior auth letters with ICD-10/CPT codes and clinical justification' — to move specificity from 1-2 actions toward comprehensive coverage.

Include common user synonyms (prior auth, pre-auth, appeal, denial) to push trigger term quality from good to comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain ('prior authorization request letters for insurance companies') and the core action 'Generate' with modifiers ('clinical justification and formatting'), but does not list several distinct concrete actions, so it sits at the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action anchor above.	3 / 5
Completeness	It clearly answers 'what' (generate prior auth letters with clinical justification and formatting) but the description contains no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	'prior authorization request letters' and 'insurance companies' are natural terms a user would say, giving good keyword coverage; a few common synonyms (prior auth, pre-authorization, appeal, denial letter) are missing, so it is just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The prior-authorization-for-insurers niche is specific and unlikely to collide with unrelated skills, but the absence of an explicit trigger clause slightly weakens distinctiveness signaling, placing it just below the clear-niche anchor.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Academic Writing/prior-auth-letter-drafter/SKILL.md
Commit: 63c61d3

Reviewed: 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.