medical-email-polisher

Transforms rough email drafts into polished, professional medical correspondence.

Quality

46%

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/medical-email-polisher/SKILL.md

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 content is well-structured and points to real bundle files, but it is padded with generic process boilerplate and delegates the actual transformation logic to the script without showing it. Validation is limited to a syntax check rather than output verification.

Suggestions

Remove or relocate generic boilerplate (Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) that does not teach the email-polishing task, to improve conciseness.

Replace the bare py_compile checkpoint with an output-validation step that confirms the polished email meets the documented tone and HIPAA criteria.

Link references/guidelines.md explicitly by name where its templates and standards apply, instead of the generic 'Reference material available in references/' pointer.

Dimension	Reasoning	Score
Conciseness	The body carries substantial boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Output Requirements) plus redundant 'See `## Features`/`## Prerequisites`/`## Workflow` above' pointers, fitting 'noticeably verbose; several unnecessary padded sections'.	2 / 5
Actionability	It provides executable commands (py_compile, --help, demo) and an input-parameter table, but the core email-polishing logic is delegated entirely to scripts/main.py and references/guidelines.md is only a non-actionable list, leaving concrete guidance incomplete.	3 / 5
Workflow Clarity	A 5-step Workflow with an explicit fallback exists, but validation checkpoints are process-level (a py_compile syntax check) rather than output validation of the polished email, matching 'steps listed but validation gaps; checkpoints implicit'.	3 / 5
Progressive Disclosure	The body is well sectioned and references real files (references/guidelines.md, scripts/main.py), but references are only generically signaled ('Reference material available in references/') and large boilerplate sections are inlined rather than split out, matching 'some structure but could be better organized'.	3 / 5
	Total	11 / 20 Passed

Description

50%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 clearly states what the skill does but omits any 'when to use' trigger guidance, capping its completeness and distinctiveness. It is competent but not exemplary, sitting at the midpoint of the scale.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when polishing a draft email to a mentor, editor, colleague, or patient.'

Include 1-2 more concrete actions (e.g. tone adjustment, HIPAA-aware phrasing) to raise specificity beyond a single verb.

Add natural synonyms users would say (proofread, rewrite, professionalize my email) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the medical-correspondence domain and one concrete action ("Transforms rough email drafts into polished, professional medical correspondence"), but offers only a single action rather than several, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	The description gives a clear "what" but includes no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	"email drafts", "polished", and "professional medical correspondence" are relevant keywords, but common user synonyms such as proofread, rewrite, or edit my email are missing, so it lands at 'some relevant keywords' rather than 'good coverage'.	3 / 5
Distinctiveness Conflict Risk	"professional medical correspondence" is a somewhat specific niche, but without explicit triggers it could still overlap with general email- or writing-polishing skills, matching the 'somewhat specific but could overlap' anchor.	3 / 5
	Total	12 / 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/medical-email-polisher/SKILL.md
Commit: 63c61d3

Reviewed: 12 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.