mechanism-to-validation-planner

Extends a mechanistic or association-level biomedical finding into a staged validation pathway that moves from descriptive evidence toward stronger functional support, mechanistic specificity, and clinical relevance. Use this skill when a user has a pathway, biomarker, cell-state, target, mechanism, or association finding and needs to decide what should be validated next, in what order, and which evidence layers are necessary versus optional. Do not default to maximal validation stacks. Build a structured validation ladder with a primary route, stronger upgrade route, and optional extensions.

Quality

79%

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/mechanism-to-validation-planner/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.

A well-structured instruction-only skill with clear sequencing, a mandatory output template, and excellent progressive disclosure through real reference modules. The main weakness is redundant restatement of the same do/don't guidance across multiple sections.

Suggestions

Collapse the overlapping guidance in Core Function, Hard Rules, What This Skill Should Not Do, and Quality Standard into a single canonical rules section to remove redundancy and tighten conciseness.

Add one short worked example (a sample finding → the A–J output) so the mandatory output structure is unambiguous and concrete.

Convert the completeness gates into an explicit final validation checklist (verify each of Sections A–J is present and uses its reference module) to add a true feedback-loop checkpoint.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's domain competence (no basic-concept padding), but the same guidance is restated across Core Function, Hard Rules, What This Skill Should Not Do, and Quality Standard — e.g. 'Never confuse repeated association with functional validation' appears in three framings — so it could be tightened.	3 / 5
Actionability	Provides a concrete 10-step Decision Logic, a mandatory A–J output structure with per-section content rules and reference mapping, plus an explicit out-of-scope redirect; the missing worked example of a complete report is the main gap keeping it off the top anchor.	4 / 5
Workflow Clarity	A clearly sequenced 10-step workflow with explicit ordering and completeness checkpoints (out-of-scope redirect, 'treat the output as incomplete if it does not identify both the weakest evidence layer and the recommended next validation step'); these are completeness gates rather than explicit validate→fix→retry feedback loops.	4 / 5
Progressive Disclosure	The body is a clear overview with one-level-deep, well-signaled references, each mapped to a specific output section (e.g. 'references/finding-type-taxonomy.md → use when classifying... in Section B'); the referenced bundle files are real and match their described purposes.	5 / 5
	Total	16 / 20 Passed

Description

87%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.

A strong, complete description that clearly states both capability and trigger conditions with concrete domain-specific language. Minor conceptual phrasing in the action list is the only thing keeping specificity and trigger_term_quality off the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — classify the finding, decide 'what should be validated next, in what order', separate 'necessary versus optional' layers, and 'Build a structured validation ladder with a primary route, stronger upgrade route, and optional extensions' — but the surrounding language ('stronger functional support, mechanistic specificity, and clinical relevance') stays somewhat conceptual, keeping it just below comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' ('Extends a mechanistic or association-level biomedical finding into a staged validation pathway') and 'when' ('Use this skill when a user has a pathway, biomarker, cell-state, target, mechanism, or association finding and needs to decide...') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Surfaces natural domain triggers a user would actually say ('pathway, biomarker, cell-state, target, mechanism, or association finding', 'what should be validated next', 'in what order'), with good keyword coverage; not quite the 5 anchor's full synonym/extension-level comprehensiveness.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (biomedical validation-path planning) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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/mechanism-to-validation-planner/SKILL.md
Commit: 63c61d3

Reviewed: 12 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.