CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

medical-translation

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

Quality

56%

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/medical-translation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

48%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 workable core (documented parameters, a concrete example, an executable script with a smoke-test fallback and a real one-level-deep reference), but it is wrapped in heavy generic boilerplate, circular self-references, and duplicated commands, and it never shows the actual translation invocation.

Suggestions

Show the real invocation once, e.g. `python scripts/main.py "acute myeloid leukemia" English Chinese`, instead of only alluding to positional arguments in the Audit Note.

Remove the circular 'See `## X` above' lines and merge the three overlapping sections (Workflow, Implementation Details, Example Usage) into one coherent sequence.

Cut the templated boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) — it is generic, and the duplicated `python scripts/smoke_test.py` line in Audit-Ready Commands should be deduplicated.

DimensionReasoningScore

Conciseness

The body is noticeably verbose: templated boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Output Requirements) add no skill-specific knowledge, circular self-references ('See `## Prerequisites` above for related details') confuse navigation, and `python scripts/smoke_test.py` is listed twice in Audit-Ready Commands. Not 1 because genuinely useful content (parameters, example, workflow steps) is present.

2 / 5

Actionability

Concrete commands exist (`python -m py_compile scripts/main.py`, `python scripts/smoke_test.py`) and the Example section shows a real input/output pair, but the primary task invocation is never shown — `python scripts/main.py <term> <source_lang> <target_lang>` is only alluded to in the Audit Note. Not 4 because the key execution detail for the skill's core purpose is missing.

3 / 5

Workflow Clarity

The 5-step Workflow gives a clear sequence, and explicit checkpoints are present: the Quick Check compile validation, the deterministic smoke-test fallback documented in the Audit Note, and the Error Handling fallback path. Not 5 because the execution model is spread across three partially overlapping sections (Workflow, Implementation Details, Example Usage), and the steps remain generic rather than translation-specific. Not 3 because checkpoints are explicit, not merely implied.

4 / 5

Progressive Disclosure

The bundle structure is real and one level deep — references/audit-reference.md exists and is clearly linked from a dedicated References section, and both scripts exist. However, substantial generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) is inlined that should be trimmed or moved to reference files. Not 4 because the inline content that does not belong outweighs the minor-organization-gap profile.

3 / 5

Total

12

/

20

Passed

Description

45%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 names a real niche (medical translation) but buries it under generic workflow-management language. It lacks concrete actions, explicit trigger guidance, and the natural terminology users would employ when requesting medical translation.

Suggestions

Rewrite the description to state concrete capabilities, e.g. 'Translates medical terms and paragraphs between Chinese and English (with a curated terminology dictionary and manual-confirmation fallback for unknown terms).'

Add an explicit trigger clause with natural user phrases, e.g. 'Use when the user asks to translate medical terminology, medical records, or Chinese-English medical terms.'

Drop the generic process filler ('structured execution, explicit assumptions, clear output boundaries') — it applies to any skill and dilutes the distinct medical-translation trigger.

DimensionReasoningScore

Specificity

The description names the domain ('medical translation', 'academic writing workflows') but states no concrete actions — it never says what is translated (terms, paragraphs), which languages, or what the output is. Phrases like 'structured execution, explicit assumptions, and clear output boundaries' are generic process filler applicable to any skill.

2 / 5

Completeness

A recognizable 'what' is present (medical translation), but there is no explicit 'Use when...' clause — the 'when' is only weakly implied by 'for academic writing workflows', which per the judging guidelines caps completeness at 3. Not 4 because the trigger guidance is neither explicit nor concrete.

3 / 5

Trigger Term Quality

'medical translation' and 'academic writing' are relevant, naturally-sayable keywords, but common variations and synonyms are missing: 'translate medical terms', 'medical terminology', 'Chinese-English', and specific language pairs a user would actually mention.

3 / 5

Distinctiveness Conflict Risk

Medical translation is a distinct niche, but the framing 'academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries' is generic and overlaps with any structured academic-writing or translation skill. Somewhat specific, but overlap risk remains.

3 / 5

Total

11

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.