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?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

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

Quality

Content

50%

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

The content offers a runnable script and concrete parameters, but is undercut by generic templated padding, inaccurate output/dependency claims, conflicting workflow sections, and a broken reference. Tightening and aligning the docs with the actual script would lift every dimension.

Suggestions

Remove generic template filler (the 'academic writing' bullet, duplicate description echoes, 'See ## Features above' cross-refs) and keep only prior-auth-specific guidance.

Correct the usage/dependency docs to match scripts/main.py: output is .txt (not .docx), and the script uses only stdlib (argparse, json, dataclasses) — not python-docx/jinja2.

Fix the broken references/letter_template.docx reference (file does not exist) and add a real output-validation step beyond py_compile, e.g. checking the generated letter contains required sections.

Dimension	Reasoning	Score
Conciseness	The body is efficient in places (parameter table, service types) but padded with generic template filler such as 'academic writing tasks that require explicit assumptions, bounded scope' and repeated echoes of the description that do not earn their tokens.	2 / 3
Actionability	Concrete usage commands and an input parameter table are provided, but guidance is partly inaccurate: usage shows '--output letter.docx' while the script emits .txt, and Technical Notes claim python-docx/jinja2 that the script does not use.	2 / 3
Workflow Clarity	Numbered workflow steps and a Quick Check are present, but two conflicting workflow sections appear and validation is limited to a py_compile syntax check with no output-validation feedback loop.	2 / 3
Progressive Disclosure	references/ contains real files and the body signals clinical_phrases.md and carrier_requirements.json, but it also references a non-existent references/letter_template.docx and the body is largely a monolithic inline template rather than well-organized one-level-deep references.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 is specific and distinctive about what the skill does, but omits an explicit 'when to use' trigger, which caps completeness and trigger-term quality. Adding a 'Use when...' clause would lift the weaker dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when drafting prior authorization, pre-approval, or medical necessity letters for insurance carriers.'

Add natural keyword variations users might say (e.g. 'pre-authorization', 'medical necessity', 'appeals', 'denials') to broaden trigger coverage.

Keep the concise what-description as-is; it already scores well on specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Generate prior authorization request letters', 'proper clinical justification', and 'formatting' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers 'what' but provides no 'when'/'Use when' trigger guidance; per the rubric, a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant natural terms ('prior authorization', 'insurance companies', 'letters') but lacks common variations and an explicit trigger phrase, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche — prior authorization letters for insurance — with distinct triggers unlikely to overlap with unrelated skills.	3 / 3
	Total	10 / 12 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
Commit: 7cc5680

Reviewed: 3 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.