bio-causal-genomics-mediation-analysis

Decompose genetic effects into direct and indirect paths through mediating variables using the mediation R package. Tests whether gene expression, methylation, or other molecular phenotypes mediate the effect of genetic variants on disease. Use when testing whether a molecular...

Quality

73%

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/Data Analysis/bio-causal-genomics-mediation-analysis/SKILL.md

Quality

Content

68%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 highly actionable with strong executable examples, but it is a single monolithic file with no progressive disclosure, and its batch mediation loop lacks the validation/feedback checkpoints the rubric requires for batch operations.

Suggestions

Add validation/sanity checkpoints to the eQTL loop (e.g. check mediate() succeeded and ACME CI excludes 0 before trusting results, or catch errors per gene) so batch mediation has an explicit feedback loop.

Split advanced sections (HDMA/HIMA, multi-omics mediation chains, visualization helpers) into reference files under references/ with one-level-deep links from SKILL.md to improve progressive disclosure.

Dedupe the repeated ACME/ADE/proportion-mediated definitions to a single framework block and reference it, reducing redundancy across sections.

Dimension	Reasoning	Score
Conciseness	Largely lean and code-heavy with minimal teaching of concepts Claude already knows; the main slack is ACME/ADE definitions repeated across the Basic, eQTL, and Multi-Omics sections, which could be tightened.	4 / 5
Actionability	Multiple complete, executable R blocks (mediate(), hima(), medsens(), ggplot), a reusable run_eqtl_mediation() function, inline parameter explanations, and output extraction cover the common cases copy-paste ready.	5 / 5
Workflow Clarity	Steps are numbered (Step 1/2/3) and sequenced, but the eQTL section loops bootstrap mediation (boot=TRUE, sims=1000) over many genes with no validation checkpoint that mediate() succeeded or CI-sanity check before p.adjust; per the rubric, a batch operation without validation caps this at 3.	3 / 5
Progressive Disclosure	All 274 lines live in a single SKILL.md with no references/, scripts/, or assets/ bundles and no navigation; advanced material (HDMA/HIMA, multi-omics chains, visualization) that would benefit from separate files is inlined into one monolith.	2 / 5
	Total	14 / 20 Passed

Description

78%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, well-targeted, and distinct, with a clear what and an intended when-clause. Its main weakness is that the 'Use when...' trigger is cut off mid-sentence, which slightly undercuts completeness.

Suggestions

Complete the truncated 'Use when testing whether a molecular...' clause so the trigger guidance is explicit and concrete rather than ending in an ellipsis.

Add 1-2 synonyms or common phrasings users might say (e.g. 'mediation analysis', 'indirect effect') to broaden trigger coverage.

Optionally surface the key output terms (ACME, ADE, proportion mediated) in the description itself so users searching for those quantities find the skill.

Dimension	Reasoning	Score
Specificity	Names the genomics mediation domain and several concrete actions ('Decompose genetic effects into direct and indirect paths', 'Tests whether gene expression, methylation, or other molecular phenotypes mediate', estimate ACME/ADE/proportion mediated), but stays within one domain without a broad multi-action list.	4 / 5
Completeness	Clearly states what the skill does and includes an explicit 'Use when testing whether a molecular...' trigger clause, but that trigger is literally truncated mid-sentence with an ellipsis, leaving the 'when' guidance incomplete rather than fully concrete.	4 / 5
Trigger Term Quality	Good coverage of natural domain terms a researcher would say ('mediation', 'mediates', 'mediating variables', 'gene expression', 'methylation', 'genetic variants'), but missing common synonyms or file extensions that would round out the set.	4 / 5
Distinctiveness Conflict Risk	A clearly defined niche (causal mediation analysis in genomics via the mediation R package) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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/Data Analysis/bio-causal-genomics-mediation-analysis/SKILL.md
Commit: f5ef65b

Reviewed: ~23 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.