cross-disease-shared-biomarker-network-research-planner

Generates complete cross-disease shared-biomarker bioinformatics research designs from a user-provided disease pair and validation direction. Always use this skill whenever a user wants to design, plan, or build a multi-dataset study linking two related diseases through shared DEGs, enrichment, PPI hub genes, public validation, regulatory-network analysis, immune infiltration, drug-gene interaction screening, and optional qRT-PCR or cell-line validation. Covers five study patterns (shared-DEG discovery, hub-gene prioritization, regulatory-network interpretation, immune/drug follow-up, bioinformatics-plus-validation) and always outputs four workload configs (Lite / Standard / Advanced / Publication+) with recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, and a strictly verified reference literature retrieval layer with real references only.

Quality

88%

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.

A strongly structured, actionable instruction-only skill with clear sequencing, explicit validation checkpoints, and exemplary one-level-deep progressive disclosure. The main weakness is conciseness: the Hard Rules section largely restates the execution steps and mandatory output sections.

Suggestions

Consolidate the 23 Hard Rules into the Execution steps and output-section definitions they restate (e.g., dataset-disclaimer, mandatory G/C.5/I/J, dependency-formula rules), keeping a short 'Non-negotiables' summary rather than a full duplicated list.

Move the dependency-consistency and forbidden-claim rules that already appear in Step 5 out of the Hard Rules section to avoid stating the same constraints twice.

Tighten the repeated references to the Dataset Disclaimer (Step 6, Step 7-D, and Hard Rule 22) into a single canonical statement plus one pointer.

Dimension	Reasoning	Score
Conciseness	Tone is efficient and does not over-explain concepts Claude already knows, but the 23-item 'Hard Rules' section substantially duplicates the Execution steps and output sections (dependency rules, dataset disclaimer, mandatory sections G/C.5/I/J are all restated) and could be consolidated.	3 / 5
Actionability	Provides a concrete, actionable spec — input format, worked examples, pattern/config tables with specific additions, exact dependency formulas, the exact mandatory disclaimer line, the exact redirect message, and required output sections A–J — with only minor inline gaps since fine-grained method detail is delegated to reference files.	4 / 5
Workflow Clarity	Clear numbered 7-step sequence run in order, an explicit validation checkpoint (Step 5 Dependency Consistency Check, mandatory before output), a feedback loop ('If any dependency inconsistency is found, revise the plan before outputting'), and a checklist via the mandatory A–J output sections; no destructive/batch cap applies.	5 / 5
Progressive Disclosure	The body is a well-organized overview delegating detail to 8 reference files that are all one-level deep (no nested references), each clearly signaled with a '→ [references/X.md]' pointer, and every referenced path resolves to a real file.	5 / 5
	Total	17 / 20 Passed

Description

100%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 excellent description: third-person, concrete, comprehensive, and explicit about both capability and trigger conditions. The 'Always use this skill whenever...' clause satisfies the 'Use when' requirement and the niche is sharply distinct.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — generating research designs, shared-DEG/enrichment/PPI-hub/public-validation/regulatory-network/immune-infiltration/drug-gene screening, plus four workload configs with recommended primary plan, workflow, figure plan, validation strategy, minimal executable version, and publication upgrade path — giving comprehensive coverage in third person.	5 / 5
Completeness	Explicitly answers both what ('Generates complete cross-disease shared-biomarker bioinformatics research designs from a user-provided disease pair and validation direction') and when ('Always use this skill whenever a user wants to design, plan, or build a multi-dataset study...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural domain keywords a researcher would actually say: 'design, plan, or build a multi-dataset study', 'shared DEGs', 'PPI hub genes', 'immune infiltration', 'drug-gene interaction screening', 'qRT-PCR or cell-line validation', and 'disease pair'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (cross-disease shared-biomarker bioinformatics planning) with distinct, domain-specific triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 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/cross-disease-shared-biomarker-network-research-planner/SKILL.md
Commit: f5ef65b

Reviewed: ~14 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.