single-gene-oncology-reference-grounded-research-planner

Generates complete conventional single-gene oncology research designs from a user-provided cancer context, target gene, and validation direction. Use when a study centers on a fixed candidate gene and needs expression, prognosis, clinicopathologic association, functional interpretation, immune context, genomic or epigenetic context, optional drug-response hypotheses, and orthogonal validation. Covers five study patterns and always outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval.

Quality

86%

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

81%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 highly actionable, well-sequenced skill body with strong workflow validation and clear reference disclosure. Main weaknesses are redundancy between the execution steps and Hard Rules, and three unreferenced bundle files.

Suggestions

Consolidate the Hard Rules with the 7-step execution section: remove rules that verbatim restate steps (e.g., rules 2, 11-13, 16-20) or convert the rules list into a short cross-referenced checklist to cut duplication.

Link the three orphaned bundle files (analysis-modules.md, method-library.md, workflow-step-template.md) from the relevant steps, or remove them from references/ if unused, so all bundle content is navigable from the overview.

Tighten the opening framing paragraphs (lines 10-18), which mix meta-commentary about sibling skills with task definition; lead with the task and move baseline-comparison detail into a reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational content, but the Hard Rules section (rules 2, 11-13, 16-20, 21-23) substantially restates material already specified in the 7-step execution section, creating noticeable duplication that could be tightened.	3 / 5
Actionability	Provides fully actionable, concrete guidance: verbatim redirect text, a config comparison table, exact required output sections (A-J), explicit dependency formulas, and mandatory element checklists — copy-paste ready for an instruction-only skill.	5 / 5
Workflow Clarity	Seven steps run in explicit order with a mandatory pre-output dependency consistency check (Step 5), a feedback loop ("If dependency fails, remove or downgrade the downstream claim"), and checklists for complex outputs.	5 / 5
Progressive Disclosure	Good structure with five well-signaled one-level-deep references (study-patterns, workload-configurations, literature-retrieval, figure-deliverable-plan, validation-evidence-hierarchy), all of which exist; however analysis-modules.md, method-library.md, and workflow-step-template.md are present in references/ but never linked from the body, leaving them orphaned.	4 / 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 both capability and trigger conditions with concrete deliverables and a well-defined niche. Minor room to broaden natural-language trigger phrasings beyond specialized jargon.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with comprehensive coverage: "outputs Lite / Standard / Advanced / Publication+ with a recommended primary plan, stepwise workflow, figure plan, validation hierarchy, minimal executable version, publication upgrade path, and strictly verified literature retrieval."	5 / 5
Completeness	Explicitly answers both what ("Generates complete conventional single-gene oncology research designs...") and when ("Use when a study centers on a fixed candidate gene and needs...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good domain keyword coverage ("single-gene oncology", "target gene", "expression", "prognosis", "clinicopathologic association", "immune context", "genomic or epigenetic context", "drug-response", "orthogonal validation") with some synonyms, but phrasing leans specialized rather than spanning the full range of natural user phrasings.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche (conventional single-gene oncology bioinformatics) with distinct triggers; the body further separates it from clinical, genome-wide, single-cell, and wet-lab scopes, minimizing conflict 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/single-gene-oncology-reference-grounded-research-planner/SKILL.md
Commit: f5ef65b

Reviewed: ~18 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.