multi-omics-clinical-integration-planner

Designs complete research plans that integrate clinical variables with multi-omics data from a user-provided biomedical direction. Always use this skill whenever a user wants to design, scope, or structure a study that combines clinical variables with transcriptomics, proteomics, metabolomics, epigenomics, or related omics layers for mechanism interpretation, biomarker development, risk stratification, treatment-response analysis, or translational use. It should define the clinical use case, alignment across data layers, feature-reduction and fusion logic, modeling route, mechanism-interpretation layer, validation ladder, and four workload configurations (Lite / Standard / Advanced / Publication+). Never fabricate datasets, accession numbers, sample counts, metadata completeness, platform coverage, literature references, PMIDs, DOIs, or validation status. Always include the mandatory Dataset Disclaimer immediately before any workflow section that mentions datasets or public resources.

Quality

85%

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

Quality

Content

77%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 well-structured with excellent progressive disclosure, a clear gated workflow, and concrete actionable guidance. Its main weakness is repetition across the Hard Rules, should/should-not, and Quality Standard sections, which inflates length without adding information.

Suggestions

Consolidate the repeated 'never fabricate datasets/accessions/PMIDs/DOIs' rule and the self-critical risk-review checklist so each appears once; cross-reference from the other sections instead of restating.

Merge 'What This Skill Should Not Do' into the existing 'Core Function — should not' list and 'Hard Rules' to remove the triple-stated prohibitions on forcing fusion and treating AUC as translational readiness.

Trim the 'Quality Standard' section to a brief success-criteria pointer, since its bullets restate obligations already covered by the output structure and hard rules.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and decision-oriented but carries notable redundancy — the 'never fabricate' rule, the self-critical risk-review checklist, and the should/should-not lists each reappear across 'Hard Rules', 'What This Skill Should Not Do', and 'Quality Standard', padding the token budget without adding new information.	3 / 5
Actionability	Guidance is concrete and executable for an instruction-only skill: each reference module is mapped to a specific output section, the DESeq2/limma count-vs-normalized rule is exact, and the disclaimer wording lives in a reference file. Minor gaps remain because some executable specifics are delegated to references rather than stated inline.	4 / 5
Workflow Clarity	The 7-step execution sequence is ordered and gated by an explicit validation checkpoint (Step 5 'Dependency Consistency Check (mandatory before output)') with a strict Lite→Publication+ subset relationship, providing clear sequencing with a real feedback loop.	5 / 5
Progressive Disclosure	Nine real reference files are each mapped to a specific output section via clearly signaled one-level-deep navigation (arrows in 'Reference Module Integration'), with the overview kept in SKILL.md and details correctly offloaded — well-structured and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

92%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, specific description that clearly states what the skill produces and when to invoke it, with rich natural trigger terms and a distinctive niche. The only minor gap is occasional missing lay synonyms in the trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete deliverable components — 'clinical use case, alignment across data layers, feature-reduction and fusion logic, modeling route, mechanism-interpretation layer, validation ladder, and four workload configurations' — giving comprehensive, specific action coverage rather than vague language.	5 / 5
Completeness	It explicitly answers both 'what' (the defined plan components) and 'when' via 'Always use this skill whenever a user wants to design, scope, or structure a study...', with concrete trigger phrases.	5 / 5
Trigger Term Quality	It includes strong natural trigger phrasings ('design, scope, or structure a study', 'transcriptomics, proteomics, metabolomics, epigenomics', 'biomarker development, risk stratification, treatment-response analysis'), but a handful of common lay variations are absent, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The clinical–multi-omics integration niche is sharply defined with distinct triggers (omics layers plus clinical variables) and named workload tiers, giving it a clear niche with minimal overlap risk.	5 / 5
	Total	19 / 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/multi-omics-clinical-integration-planner/SKILL.md
Commit: 63c61d3

Reviewed: 11 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.