validation-strategy-designer

Designs internal, external, temporal, and functional validation strategies at the protocol stage for medical research studies.

Quality

68%

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 ./awesome-med-research-skills/Protocol Design/validation-strategy-designer/SKILL.md

Quality

Content

71%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.

This is a well-structured, actionable instruction-only skill with excellent progressive disclosure and a clear staged workflow, weakened mainly by repetition across its hard-rules, should-not-do, and quality-standard sections.

Suggestions

Consolidate the overlapping warnings in 'Hard Rules', 'What This Skill Should Not Do', and 'Quality Standard' into a single canonical section, cross-referencing it elsewhere instead of restating.

Add one short worked-example memo (e.g., a biomarker study case) to anchor the mandatory A-L output structure and lift actionability.

Dimension	Reasoning	Score
Conciseness	The body is directive and avoids explaining concepts Claude already knows, but the same warnings (don't overclaim, don't invent experiments, separate internal/external) are restated across 'Important Distinctions', 'Hard Rules', 'What This Skill Should Not Do', and 'Quality Standard', adding notable redundancy that could be tightened.	3 / 5
Actionability	Provides a concrete tier taxonomy, a necessary/recommended/optional/not-justified classification scheme, an 8-step execution flow, and a fully specified A-L output structure; the main gap is the absence of a worked example output memo to anchor the expected format.	4 / 5
Workflow Clarity	The 8-step sequence is clearly ordered with an explicit clarify-before-expand gate, an evidence-boundary review (Step 7), and a self-critical risk review (Section L) acting as checkpoints; not a 5 because the steps are more descriptive than fully checkpointed and the skill is planning-oriented rather than error-recovery-oriented.	4 / 5
Progressive Disclosure	The body is a clear overview that points to five real, one-level-deep reference files, each signaled with a specific 'Use to/Use when' purpose line; no nested references were found, and navigation is easy.	5 / 5
	Total	16 / 20 Passed

Description

66%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 is specific, in third person, and names a clear niche, but it omits the 'when to use' trigger guidance that the rubric requires for a top completeness score.

Suggestions

Append an explicit 'Use when ...' clause listing concrete trigger phrases (e.g., 'Use when designing validation for a biomarker, prognostic, or omics study at the protocol stage').

Expand the validation-type list to reflect the full tier set covered in the body (e.g., add split-sample, cross-validation, site-based, orthogonal, translational).

Dimension	Reasoning	Score
Specificity	Names the domain ('validation strategies') and lists several concrete sub-types ('internal, external, temporal, and functional'), but omits several tiers the body covers (split-sample, bootstrap, site-based, orthogonal, translational), so coverage is not comprehensive.	4 / 5
Completeness	Provides a clear 'what' ('Designs ... validation strategies at the protocol stage for medical research studies') but lacks any 'Use when...' clause or explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes natural terms users would say ('external validation', 'functional validation', 'validation strategies', 'medical research studies') that align with the skill's sample triggers; a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The 'protocol stage' medical-research validation niche is distinctive and low-conflict, but the absence of explicit trigger phrasing leaves minor overlap risk with sibling medical-research skills.	4 / 5
	Total	15 / 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: awesome-med-research-skills/Protocol Design/validation-strategy-designer/SKILL.md
Commit: f5ef65b

Reviewed: ~18 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.