medical-email-polisher

Transforms rough email drafts into polished, professional medical correspondence.

Quality

42%

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/medical-email-polisher/SKILL.md

Quality

Content

35%

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

The skill bundles a real, executable script and concrete I/O contracts, but the SKILL.md body is dominated by generic boilerplate and process filler that crowds out skill-specific guidance. Trimming the boilerplate and showing the actual polishing invocation would materially improve the two highest-weighted dimensions.

Suggestions

Cut generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template) that restate process concepts Claude already knows; keep only medical-email-specific content.

Add a concrete usage example showing the real invocation, e.g. 'python scripts/main.py "hey, wanted to follow up on our manuscript" mentor', with sample output, instead of only --help and demo.

Replace generic 'references/' pointers with explicit links like [guidelines.md](references/guidelines.md) and move the template/etiquette detail into that reference file to tighten the overview.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate Claude already knows ('validate the request, choose the packaged workflow, and produce a bounded deliverable', 'keep results reproducible, identify assumptions explicitly'), repeats the description in 'When to Use', and includes filler cross-references ('See ## Features above') and generic Risk/Security/Evaluation/Lifecycle sections, matching the verbose score-1 anchor.	1 / 3
Actionability	Provides a real executable script and concrete commands ('python -m py_compile scripts/main.py', 'python scripts/main.py demo') plus a concrete Input Parameters table and Output Format, but never shows the actual polishing invocation with real arguments (only --help/demo), so guidance is incomplete.	2 / 3
Workflow Clarity	The 'Workflow' section is a clear 5-step sequence with a fallback path, but validation checkpoints are implicit ('Quick Check' is only py_compile) and the steps describe generic meta-process rather than the task-specific email-polishing flow, fitting the 'steps listed but validation gaps' anchor.	2 / 3
Progressive Disclosure	Bundle files references/guidelines.md and scripts/main.py are real and one level deep, but the body signals them generically ('Reference material available in references/') rather than with crisp file links, and substantial inline boilerplate could be split out, matching the 'some structure but not clearly signaled' anchor.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 clear and domain-specific about what the skill does, but it is uniformly mid-tier because it omits an explicit 'when to use' trigger clause and lacks a rich set of natural trigger terms and concrete actions. Adding trigger guidance would lift the two heaviest-weighted dimensions.

Suggestions

Append a 'Use when...' clause naming concrete triggers, e.g. 'Use when drafting or refining emails to mentors, journal editors, colleagues, or patients, or when the user asks to polish professional medical correspondence.'

Add more natural trigger terms users would actually say ('polish my email', 'proofread this email', 'write an email to my editor/patient/mentor') to improve trigger_term_quality.

List a few concrete actions beyond the single 'transforms' verb (e.g. adjust tone, optimize openings/closings, suggest subject lines, ensure HIPAA-aware phrasing) to raise specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('medical correspondence') and a transformation action ('Transforms rough email drafts into polished, professional'), but lists only one action rather than a comprehensive set of concrete actions like the score-3 anchor.	2 / 3
Completeness	Clearly answers 'what' the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric guideline, a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant terms ('email drafts', 'polished', 'professional medical correspondence') but misses common natural variations a user would say such as 'polish my email', 'write an email to my mentor/editor/patient', or 'proofread'.	2 / 3
Distinctiveness Conflict Risk	'Medical correspondence' is a niche, but without explicit distinct triggers the skill could still overlap with generic email or professional-writing skills, matching the 'somewhat specific but could overlap' anchor rather than the clear-niche anchor.	2 / 3
	Total	8 / 12 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
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.