dual-disease-transcriptomic-ml-planner

Generates complete dual-disease transcriptomic + machine learning research designs from a user-provided disease pair. Use when users want to identify shared DEGs, common hub genes, cross-disease biomarkers, or shared molecular mechanisms between two diseases using public GEO data. Triggers:"shared biomarker study for two diseases", "dual-disease transcriptomic ML paper", "identify common DEGs between disease A and B", "cross-disease hub gene discovery", "shared DEG + PPI + ROC design", "immune infiltration shared biomarker", or "I want to study disease X and Y together". Always outputs four workload configurations (Lite / Standard / Advanced / Publication+) with a recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path.

Quality

90%

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

85%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, actionable research-planning skill with strong workflow validation and clean progressive disclosure into four real reference files. The main improvements are tightening a few prose sections and making the R template fully self-contained.

Suggestions

Make the R pipeline template self-contained: define deg_d2 (or note it mirrors the disease1 block) and define labels/scores before the roc() call so the snippet runs end-to-end once placeholders are filled.

Tighten the Supported Study Styles and Risk Review sections into denser bullets; several explanatory phrases restate Hard Rules already stated elsewhere.

Consider moving the full Hard Rules list into a reference file and keeping only the top 3-4 load-bearing rules inline to reduce token weight, since the rules are largely cross-referenced from the workflow steps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's bioinformatics knowledge, supplying only domain-specific thresholds and tool choices rather than basics; a few prose sections (study-style table, risk-review bullets) could be tightened without losing value.	4 / 5
Actionability	A copy-paste R pipeline template with an explicit EXAMPLE-ID convention and concrete thresholds is highly actionable, but the template references deg_d2, labels, and scores without defining them, leaving minor gaps.	4 / 5
Workflow Clarity	A clear 9-step sequence with explicit validation/feedback loops at dataset, DEG-intersection, and ROC levels (zero-intersection guard, AUC≈0.5 flagging, n<30 inflation warning) and recovery sequences for error correction.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references; all four bundle files (figure_plan_template, geo_search_and_tools, tissue_and_tool_decisions, upgrade_path) are linked inline and summarized in a Reference Files table, and verified to exist.	5 / 5
	Total	18 / 20 Passed

Description

96%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.

An exemplary description: third-person voice, concrete actions, explicit what/when, and enumerated trigger phrases for a well-defined niche. The only soft spot is one slightly broad trigger phrasing that could overlap with adjacent research skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Generates complete dual-disease transcriptomic + machine learning research designs", "identify shared DEGs, common hub genes, cross-disease biomarkers") and a comprehensive output set (four configurations, workflow, figure plan, validation strategy, minimal executable version, upgrade path).	5 / 5
Completeness	Clearly answers both "what" (Generates complete dual-disease transcriptomic + ML research designs) and "when" ("Use when users want to..." plus the explicit Triggers list), with concrete trigger phrases.	5 / 5
Trigger Term Quality	An explicit "Triggers:" list gives natural phrasings the target audience would say ("shared biomarker study for two diseases", "identify common DEGs between disease A and B", "I want to study disease X and Y together"), with good variation coverage.	5 / 5
Distinctiveness Conflict Risk	The dual-disease GEO transcriptomic niche is clearly distinct, but the catch-all trigger "I want to study disease X and Y together" is somewhat broad and carries minor overlap risk with a general transcriptomic skill.	4 / 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: scientific-skills/Protocol Design/dual-disease-transcriptomic-ml-planner/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.