translational-gap-analyzer

Assess translational gaps between preclinical models and human diseases.

Quality

48%

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/Evidence Insight/translational-gap-analyzer/SKILL.md

Quality

Content

50%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 actionable with concrete commands and examples, but it is padded with generic template boilerplate that hurts conciseness, and the workflow lacks explicit validation feedback loops for its batch assessment operations.

Suggestions

Remove or relocate generic template sections (Lifecycle Status, Security Checklist, Evaluation Criteria, Response Template) that restate knowledge Claude already has, keeping only skill-specific material in SKILL.md.

Add an explicit validation feedback loop to the workflow (e.g. run py_compile/main.py --help, on failure fix inputs and re-run) with checkpoints for batch assessment runs.

Move the detailed model-types table, gap-scoring rubric, and example output into references/ and link to them from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with large amounts of template boilerplate (Lifecycle Status, Security Checklist, Evaluation Criteria, Output Requirements, Response Template) that restates generic process guidance Claude already knows rather than skill-specific substance.	2 / 5
Actionability	It provides mostly executable guidance — real CLI invocations (python scripts/main.py --model mouse --disease ...) plus a full arguments table and example JSON output — with only minor gaps such as placeholder values in some commands.	4 / 5
Workflow Clarity	A sequenced workflow and validation commands exist, but batch/assessment operations lack an explicit validate-then-fix feedback loop and the validation checkpoints are implicit rather than enforced, which caps clarity at 3.	3 / 5
Progressive Disclosure	Structure exists with one real one-level reference (references/audit-reference.md, verified present), but the SKILL.md inlines a great deal of content that could live in references and navigation to the bundle is only loosely signaled.	3 / 5
	Total	12 / 20 Passed

Description

46%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 states a clear, specific purpose but omits any explicit 'when to use' trigger guidance, which limits completeness. Trigger terms are domain-jargon-heavy and miss the natural phrases a user would say.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g. 'Use when evaluating whether a mouse or animal model will translate to human clinical trials').

Include more user-natural synonyms such as 'animal model', 'mouse model', and 'will this translate to humans' alongside the technical 'preclinical models'.

Name 1-2 concrete deliverables (e.g. 'produces a gap score and clinical-failure-risk report') to lift specificity beyond a single action.

Dimension	Reasoning	Score
Specificity	Phrases the action as 'Assess translational gaps between preclinical models and human diseases' — names the domain and one concrete action but no enumeration of what the assessment produces or how.	3 / 5
Completeness	It gives a clear 'what' but entirely omits a 'Use when...' clause or any explicit 'when' trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	It uses 'preclinical models' and 'human diseases', which are domain jargon; it lacks the natural phrases or synonyms a user would actually say such as 'animal model', 'mouse model', or 'will this translate to humans'.	2 / 5
Distinctiveness Conflict Risk	The niche (preclinical-to-human translational gap assessment) is fairly distinct and unlikely to collide with unrelated skills, with only minor overlap risk against general biomedical-analysis skills.	4 / 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/Evidence Insight/translational-gap-analyzer/SKILL.md
Commit: 63c61d3

Reviewed: 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.