medical-translation

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

Quality

52%

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

60%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 is well-structured with executable commands, a worked example, a sequenced workflow with validation, and a clean one-level reference — but it is padded with generic templated sections and duplicated/filler content that hurt token efficiency. Domain-specific translation guidance is thin relative to boilerplate.

Suggestions

Remove templated boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) and the 'See `## X` above' filler, or move them into a reference file if retained.

Fix the duplicated `python scripts/smoke_test.py` line in Audit-Ready Commands and correct the Example output so it matches main.py's actual English→Chinese result.

Add concrete medical-translation guidance (e.g. how to handle terms outside the dictionary, language-pair coverage, terminology nuance) instead of relying on 'run the script' alone.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: it re-pastes the description verbatim inside 'Key Features', includes repeated 'See `## X` above for related details' filler, duplicates the `python scripts/smoke_test.py` line, and carries templated boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that adds little medical-translation-specific value.	2 / 5
Actionability	It provides concrete, executable commands (py_compile, --help, smoke_test.py) and a worked example with named parameters and output, all backed by real bundle files; minor gaps are the example output not matching main.py's actual behavior and thin domain-specific translation guidance beyond 'run the script'.	4 / 5
Workflow Clarity	The Workflow section gives a clear 5-step sequence with an explicit scope-validation checkpoint (step 2) and a fallback loop (step 5), plus a Quick Check validation command; because translation is not a destructive/batch operation the cap does not apply, but the checkpoints are somewhat generic rather than concrete output-verification steps.	4 / 5
Progressive Disclosure	A single, well-signaled one-level-deep reference (references/audit-reference.md, linked with a clear description) offloads real detail (scope, audit paths, fallback boundary), and section headers organize the body; minor gaps remain from the bloated inline boilerplate that could be trimmed.	4 / 5
	Total	14 / 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 identifies a real niche (medical translation for academic writing) but frames it almost entirely in generic process terms rather than concrete capabilities, and lacks an explicit 'Use when…' trigger clause. It is distinguishable but weak on specificity and trigger coverage.

Suggestions

State concrete actions, e.g. 'Translates medical terminology between language pairs (e.g. Chinese-English, Spanish-English) for academic writing.'

Add an explicit 'Use when…' clause with natural trigger phrases users would say, such as 'translate medical terms', 'medical terminology translation', or specific language pairs.

Replace generic process qualities ('structured execution, explicit assumptions') with domain-specific triggers that distinguish this from general translation or academic-writing skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('medical translation') but the only action is the generic 'Use medical translation'; the remainder ('structured execution, explicit assumptions, and clear output boundaries') lists process qualities rather than concrete actions, matching the 'Names the domain but actions are minimal or generic' anchor.	2 / 5
Completeness	It gives a vague 'what' (medical translation, without stating it translates terminology across languages) and a present 'when' ('for academic writing workflows that need…'), but there is no explicit 'Use when…' clause, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	'medical translation' and 'academic writing' are relevant natural keywords a user might say, but common variations/synonyms (e.g. 'translate medical terms', 'terminology translation', language pairs) are absent, fitting 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	The medical-translation niche is somewhat specific, but the generic process framing ('structured execution, explicit assumptions, clear output boundaries') could overlap with any structured academic-writing or workflow skill, matching 'Somewhat specific but could still overlap with similar skills'.	3 / 5
	Total	11 / 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-translation/SKILL.md
Commit: 63c61d3

Reviewed: 13 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.