referral-letter-generator

Generate medical referral letters with patient summary, reason for referral, key findings, and requested next steps; use when transferring care or communicating with another clinician or department.

Quality

74%

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/referral-letter-generator/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 delivers concrete, executable usage guidance and a reasonable workflow with validation, but it is bloated with generic template boilerplate and an off-topic bullet, and its references are vaguely signaled and mismatched to the actual bundle. Tightening the boilerplate and linking specific reference files would markedly improve it.

Suggestions

Remove or collapse generic boilerplate sections (Security Checklist, Risk Assessment, Lifecycle Status, Evaluation Criteria, Output Contract) that add no referral-letter-specific value, and delete the off-topic 'academic writing tasks' bullet under When to Use.

Replace the generic 'See references/ folder for' pointer with explicit links to the actual files (e.g., [referral_template.md](references/referral_template.md), [referral_standards.md](references/referral_standards.md), [templates.md](references/templates.md)) and move the inlined parameter/format detail there where appropriate.

Make the Workflow steps referral-letter-specific (e.g., validate required patient fields against the Input Parameters table, run scripts/main.py, verify the generated letter against the template) rather than reusing abstract objective/assumption/deliverable language.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several padded generic sections (Security Checklist, Risk Assessment table, Lifecycle Status with a review date, Evaluation Criteria test cases, Output Contract) and an off-topic 'academic writing tasks' bullet that does not belong in a referral-letter skill.	2 / 5
Actionability	Provides mostly executable guidance — concrete CLI commands ('python scripts/main.py --input ... --output ...'), py_compile checks, and an example JSON payload — with only minor gaps such as the '{...}' placeholders in the Python API snippet.	4 / 5
Workflow Clarity	A clear five-step Workflow sequence includes a scope-validation checkpoint (step 2) and a fallback loop (step 5), plus Quick Validation checks; however the steps are generic rather than referral-letter-specific, leaving minor gaps.	4 / 5
Progressive Disclosure	Structure exists via section headers, but references are only a generic 'See references/ folder for' pointer with no specific file links, and the described contents (e.g. 'Privacy compliance checklist') do not match the actual bundle files; much content that could live in separate files is inlined.	3 / 5
	Total	13 / 20 Passed

Description

92%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 strong: it concisely states concrete capabilities and an explicit use-when trigger with natural synonyms, yielding a clear, distinctive niche. The only minor gap is trigger-term breadth (no file extensions or variants like 'specialist'/'consult').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'patient summary, reason for referral, key findings, and requested next steps' — giving comprehensive coverage of what the letter contains, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both what ('Generate medical referral letters with patient summary, reason for referral, key findings, and requested next steps') and when ('use when transferring care or communicating with another clinician or department') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keywords with synonyms ('transferring care or communicating with another clinician or department'), but lacks file extensions and common variants like 'specialist' or 'consult', so it sits below the comprehensive score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear medical-referral niche with distinct triggers ('medical referral letters', 'transferring care', 'clinician or department'), giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Academic Writing/referral-letter-generator/SKILL.md
Commit: 63c61d3

Reviewed: 7 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.