CtrlK
BlogDocsLog inGet started
Tessl Logo

conventional-oncology-hub-gene-research-planner

Generates complete conventional oncology bulk-transcriptome biomarker and hub-gene research designs from a user-provided cancer type and study direction. Always use this skill whenever a user wants to design, plan, or build a tumor bioinformatics study centered on differential expression, prognostic filtering or risk modeling, PPI-based hub-gene prioritization, diagnostic/prognostic evaluation, clinical association, immune infiltration context, methylation context, and optional tissue or cell validation. Covers five study patterns (signature-first prognostic workflow, hub-gene-first biomarker workflow, hybrid signature-to-hub workflow, immune-context biomarker workflow, translational validation workflow) 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...

69

Quality

85%

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

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 body is a highly actionable, well-sequenced planning skill with excellent progressive disclosure via eight clearly-linked, one-level-deep reference files. Its primary weakness is conciseness: the hard-rules section and several dependency/disclaimer/formula rules are restated across the body and reference files, creating substantial redundancy.

Suggestions

Consolidate the 23 'Hard Rules' with the corresponding Step 1–7 sections instead of restating them; keep rules inline where they apply and remove the duplicated end-of-document list.

De-duplicate the dependency/forbidden-combination rules and the Dataset Disclaimer — state each once in the relevant step and reference it, rather than repeating in Steps 5–6, hard rules, and reference files.

Tighten the YAML description into a shorter sentence or two; it currently runs as a dense wall of text trailing into '...'.

DimensionReasoningScore

Conciseness

The 23 'Hard Rules' largely restate content already embedded in Steps 1–7, and the dependency/forbidden-combination/disclaimer/intersection-formula rules are repeated across the body, the hard-rules section, and the reference files. This is noticeably verbose with several padded, redundant sections. Not 3 because the redundancy is substantial rather than a single tighten-able spot; not 1 because it never explains concepts Claude already knows.

2 / 5

Actionability

Provides a fully concrete output template (mandatory sections A–J, an 8-field step template), explicit decision rules (DESeq2 for raw counts, limma for non-count matrices), exact intersection formulas (DEG ∩ survival-associated genes ∩ PPI hubs), and specific parameter defaults (FDR<0.05, |log2FC|>1.0, AUC>0.70). For an instruction-only planner skill this is as actionable as it gets. Not 4 because there are no meaningful gaps in the executable guidance.

5 / 5

Workflow Clarity

A clear 7-step sequence 'always run in order' with an explicit Step 5 dependency-consistency validation checkpoint, a 'revise before outputting' feedback loop, phase-gate deliverable checklists, and redirect-and-stop handling for out-of-scope input. Not 4 because validation checkpoints, feedback loops, and checklists are all explicitly present.

5 / 5

Progressive Disclosure

Eight one-level-deep reference files (study-patterns, workload-configurations, workflow-step-template, analysis-modules, method-library, validation-evidence-hierarchy, figure-deliverable-plan, literature-retrieval-and-citation), all verified to exist and each clearly signaled in the body with markdown links; the body is an overview pointing to detailed materials with no nested reference chains. Not 4 because navigation is consistently clear and references stay exactly one level deep.

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.

The description is comprehensive, specific, and explicitly answers both what the skill does and when to use it, with a clearly distinct niche. Its main weakness is verbosity — it is a dense wall of text trailing into '...' that could be tightened without losing content.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (differential expression, prognostic filtering/risk modeling, PPI-based hub-gene prioritization, diagnostic/prognostic evaluation, clinical association, immune infiltration, methylation, tissue/cell validation) plus five study patterns and four workload configs, giving comprehensive coverage. Not 4 because the action inventory is exhaustive rather than having only minor gaps.

5 / 5

Completeness

Explicitly answers both 'what' ('Generates complete... research designs', 'Covers five study patterns', 'always outputs four workload configs') and 'when' ('Always use this skill whenever a user wants to design, plan, or build a tumor bioinformatics study centered on...') with concrete trigger phrases. The explicit trigger clause means the 3-cap does not apply.

5 / 5

Trigger Term Quality

Contains strong natural domain terms with synonyms ('prognostic filtering or risk modeling', 'diagnostic/prognostic evaluation', 'design, plan, or build a tumor bioinformatics study') that a user in this field would actually say. Not 5 because the phrasing is jargon-dense and the trigger ('Always use this skill whenever a user wants to...') is somewhat formulaic rather than crisp.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (conventional oncology bulk-transcriptome biomarker / hub-gene computational research design) with distinct, specialized triggers and minimal overlap with other skills. Not 4 because the scope is sharply bounded to this specific study family.

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.

Validation15 / 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.