CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

70

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

The body is a highly actionable, well-sequenced planning framework with explicit validation checkpoints and a clean reference structure. Its main weaknesses are redundancy between the Hard Rules and the step definitions, and three bundle files that lack navigation pointers from the main skill.

Suggestions

Consolidate the Hard Rules section: rules that duplicate Step 4.5 (12–14), Step 3 (2), Step 4 (3), and the mandatory-section requirements of Steps 6–7 (15, 17, 20–23) could be replaced by a short pointer to the corresponding steps, cutting significant duplicated tokens.

Add inline reference links for the three orphaned bundle files (references/analysis-modules.md, references/method-library.md, references/workflow-step-template.md) from the relevant steps so their content is discoverable during execution.

Tighten Step 6, which mostly repeats the Step 7 section list, by merging the duplicated output inventory into the mandatory-sections step.

DimensionReasoningScore

Conciseness

Mostly efficient instruction content with no padding of concepts Claude already knows, but the 23-item Hard Rules section extensively restates rules already specified in the steps — e.g., rules 12–14 duplicate Step 4.5's citation rules verbatim in substance, and rules 15/17/20/21/23 restate the mandatory-section requirements of Steps 6–7 — so it could be meaningfully tightened.

3 / 5

Actionability

Fully concrete instruction-only guidance: exact input format ("[cancer type] + [target gene] + [validation direction or emphasis]"), worked example inputs, pattern and config selection tables, verbatim redirect and Dataset Disclaimer templates, and a fully specified A–J output section list with per-section content requirements.

5 / 5

Workflow Clarity

The 7 steps are explicitly ordered ("always run in order"), and Step 5 is a genuine validation checkpoint ("Dependency Consistency Check (mandatory before output)") with an explicit failure-handling rule — "If dependency fails, remove or downgrade the downstream claim rather than silently keeping it" — plus a fallback for insufficient input detail.

5 / 5

Progressive Disclosure

Good structure with five clearly signaled one-level-deep references (e.g., "→ Detailed pattern logic: [references/study-patterns.md](references/study-patterns.md)"), all of which exist in the bundle; however, three bundle files (analysis-modules.md, method-library.md, workflow-step-template.md) are never referenced from SKILL.md, leaving navigation gaps.

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.

The description is strong: third-person, concrete, comprehensive in capability listing, and with an explicit 'Use when' clause covering concrete triggers. The only weakness is a few missing natural synonyms (e.g., survival analysis, biomarker) that users might say.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions and deliverables — "Generates complete conventional single-gene oncology research designs", "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" — comprehensive and in third person.

5 / 5

Completeness

It explicitly answers both: the "what" ("Generates complete conventional single-gene oncology research designs from a user-provided cancer context, target gene, and validation direction") and the "when" ("Use when a study centers on a fixed candidate gene and needs expression, prognosis, clinicopathologic association, ...") with concrete trigger needs.

5 / 5

Trigger Term Quality

Good natural-keyword coverage — "single-gene", "oncology", "cancer context", "target gene", "expression", "prognosis", "immune context", "drug-response", "validation" — but misses common user phrasings like "survival analysis", "biomarker study", or portal names (e.g., TCGA), so a few natural terms are missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche — conventional single-gene oncology bioinformatics study design with a fixed candidate gene — with distinct triggers that would not fire for genome-wide, wet-lab, or clinical-treatment requests; minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
Reviewed

Table of Contents

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.