CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

prior-auth-letter-drafter

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

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

42%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 contains a genuinely useful core (a working script, an accurate input-parameter table, and a service-type taxonomy) buried under heavy auto-generated boilerplate and self-contradictory metadata. Multiple documented commands and referenced files do not match the actual bundle (missing template file, wrong output format, conflicting dependency claims), which directly undermines trust in the executable guidance.

Suggestions

Fix the factual mismatches: remove the nonexistent references/letter_template.docx, correct the output format to plain text, reconcile the dependency claims with requirements.txt (stdlib only), and replace the broken audit command with a working one (e.g. create a sample via --create-sample, then run --input sample_input.json --output letter.txt).

Cut the boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, duplicated Workflow/Features/Dependencies sections with "See X above" pointers) and consolidate the three overlapping workflow descriptions into one.

Reference the actual bundle contents in a single References section (clinical_phrases.md, carrier_requirements.json, guidelines.md) with one-line descriptions of when to consult each.

DimensionReasoningScore

Conciseness

The 236-line body is padded with boilerplate meta-sections (Risk Assessment table, Security Checklist, Evaluation Criteria, Lifecycle Status with a stale "Next Review Date: 2026-03-06"), duplicates the same workflow guidance across "When to Use", "Key Features", "Implementation Details", and "Workflow", and uses filler like "See `## Workflow` above for related details" pointing at sections that actually appear below. It fits 'noticeably verbose; several unnecessary explanations or padded sections' rather than the severely-verbose level-1 anchor, which requires extensive explanation of basic concepts.

2 / 5

Actionability

Concrete guidance exists (a runnable scripts/main.py, a parameter table matching the script's input fields, and py_compile/--help commands), but several documented commands and paths are wrong or broken: "Audit-Ready Commands" passes a prose string as --input (the script expects a JSON file path and exits with an error), the References section lists references/letter_template.docx which does not exist, "--output letter.docx" implies DOCX while the script writes plain text, and Technical Notes claim python-docx/jinja2 dependencies that requirements.txt explicitly disclaims. This matches 'Some concrete guidance but incomplete; missing key details' rather than the mostly-executable level-4 anchor.

3 / 5

Workflow Clarity

A sequence is listed (Example run plan, Workflow 1-5, Quick Check via py_compile) and error handling has a documented fallback, but the Workflow steps are generic ("Use the packaged script path or the documented reasoning path with only the inputs that are actually available") with no explicit validate-fix-retry checkpoint on a concrete command. This matches 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

The bundle has a real references/ directory (carrier_requirements.json, clinical_phrases.md, guidelines.md, requirements.txt) and a References section signals some of it, but it points to a nonexistent references/letter_template.docx, omits guidelines.md entirely, and inlines large boilerplate sections (Security Checklist, Evaluation Criteria, Lifecycle Status) that add no navigational value. This fits 'Some structure but could be better organized; references present but not clearly signaled' rather than the good-structure level-4 anchor.

3 / 5

Total

11

/

20

Passed

Description

65%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 is concrete, domain-specific, and uses the natural phrase users would say ("prior authorization"), making it highly distinct from other skills. Its main weakness is the complete absence of 'when to use' trigger guidance, which caps completeness, and missing common synonyms like "prior auth" or "pre-authorization".

Suggestions

Add an explicit trigger clause, e.g. "Use when the user needs to draft a prior authorization (PA) request letter, appeal a prior auth denial, or respond to an insurance pre-authorization request."

Include common synonyms and colloquialisms users actually say ("prior auth", "pre-auth", "PA letter", "insurance approval") to improve trigger term coverage.

Mention the supported request types (procedures, medications, DME, imaging) in the description to strengthen the 'what' coverage.

DimensionReasoningScore

Specificity

"Generate professional prior authorization request letters for insurance companies" names the domain and one concrete action (generate letters); "with proper clinical justification and formatting" describes attributes of that single deliverable rather than several distinct actions. It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' and falls short of the level-4 anchor, which requires several separate specific actions.

3 / 5

Completeness

The description has a clear 'what' (generate prior authorization request letters) but no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. The insurance-company context only weakly implies 'when', and the 'what' is concrete rather than vague, so this is not the level-2 anchor.

3 / 5

Trigger Term Quality

Strong natural phrases a user would say ("prior authorization", "request letters", "insurance companies") with good domain keyword coverage. Common variations are missing ("prior auth", "pre-authorization", "PA letter", "insurance approval"), so it fits 'Good keyword coverage; a few natural terms missing' rather than the level-5 comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

"Prior authorization request letters for insurance companies with clinical justification" is a clearly defined healthcare-administrative niche with distinct triggers, and it is unlikely to fire for unrelated letter-drafting or general writing skills. This matches the 'Clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.