medical-translation

Use medical translation for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.

Quality

42%

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-translation/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 body bundles real, runnable scripts and a valid one-level reference, but it is buried under large amounts of generic templated boilerplate, verbatim description repetition, and broken 'See above' cross-references. Actionable and workflow guidance is present but shallow and not specific to medical translation.

Suggestions

Remove the generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) or move them to a reference file; keep SKILL.md focused on how to run and use the translation script.

Fix or delete the broken 'See ## Prerequisites/Usage/Workflow above' stubs in Dependencies, Example Usage, and Implementation Details — those sections appear below, not above.

Replace abstract process phrasing ('produce a bounded deliverable', 'choose the packaged workflow') with concrete medical-translation guidance, e.g. how to handle terms missing from the script's dictionary and when to flag for manual confirmation.

Dimension	Reasoning	Score
Conciseness	The body is heavily padded: the frontmatter description is repeated verbatim multiple times, and generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Output Requirements) add no skill-specific value; broken 'See ## above' stubs (e.g. line 26 'Prerequisites', line 49 'Workflow') point to sections that actually appear later, adding confusing noise.	1 / 3
Actionability	There are concrete, executable commands (py_compile, smoke_test.py, main.py --help) and a real Parameters/Example block matching scripts/main.py, but the core translation guidance is abstract ('choose the packaged workflow', 'produce a bounded deliverable') and never tells Claude how to actually perform or verify a medical translation beyond invoking the script.	2 / 3
Workflow Clarity	The Workflow section lists 5 sequenced steps with an explicit stop-early validation (step 2) and a fallback path (step 5), but the broken 'See ## above' navigation references and the generic, non-translation-specific nature of the steps leave real gaps; there is no validate-then-fix loop for the translation output itself.	2 / 3
Progressive Disclosure	The single reference (references/audit-reference.md) is well-signaled and one level deep, and scripts are correctly referenced, but SKILL.md is a monolithic ~200-line wall of text with checklists and templates that should be split out, so the structure is only partially organized.	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 identifies a genuine niche (medical translation for academic writing) but pads it with abstract process boilerplate instead of concrete actions and natural trigger terms. It answers 'what' and weakly implies 'when' but lacks explicit, user-facing trigger language.

Suggestions

Replace the abstract boilerplate with concrete actions, e.g. 'Translates medical terminology between languages (e.g. Chinese-English, Spanish-English) for academic writing.'

Add an explicit natural-trigger clause: 'Use when the user asks to translate medical terms, drug names, or clinical terminology for academic papers.'

Drop the meta phrasing ('structured execution, explicit assumptions, and clear output boundaries') which does not help a user recognize the skill.

Dimension	Reasoning	Score
Specificity	Names the domain ('medical translation', 'academic writing workflows') and an implicit action (translation), but the remainder ('structured execution, explicit assumptions, and clear output boundaries') is abstract process language rather than concrete listed actions, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It has a 'Use ... for ...' construction that implies a when ('for academic writing workflows'), but the trigger is abstract rather than concrete natural triggers (e.g. 'when the user mentions medical terms or bilingual terminology'), so per the explicit-trigger cap it stays at 2.	2 / 3
Trigger Term Quality	'medical translation' and 'academic writing' are reasonably natural keywords, but the bulk ('structured execution, explicit assumptions, and clear output boundaries') is meta/buzzword language rather than natural user phrasing, and common variations like 'medical terms', 'terminology translation', or language pairs are missing.	2 / 3
Distinctiveness Conflict Risk	'medical translation' is a recognizable niche, but the generic boilerplate ('academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries') could overlap with general translation or academic-writing skills, so it is only somewhat distinctive.	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
Path: scientific-skills/Academic Writing/medical-translation/SKILL.md
Commit: f5ef65b

Reviewed: about 5 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.