CtrlK
BlogDocsLog inGet started
Tessl Logo

dual-disease-shared-transcriptome-biomarker-research-planner

Generates complete dual-disease shared-transcriptome biomarker and hub-gene research designs from a user-provided disease pair and shared-biology direction. Always use this skill whenever a user wants to design, plan, or build a non-oncology two-disease transcriptome study centered on per-disease differential expression, shared-signal intersection or concordance, PPI-based hub-gene prioritization, diagnostic evaluation across both diseases, immune infiltration context, pathway interpretation, and optional orthogonal validation. Covers five study patterns (shared-DEG-first workflow, hub-gene-first shared-biomarker workflow, hybrid shared-biomarker compression workflow, immune-context shared-biomarker workflow, orthogonal 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...

60

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./awesome-med-research-skills/Protocol Design/dual-disease-shared-transcriptome-biomarker-research-planner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 content is a well-organized instruction skill with a clear 7-step workflow, explicit validation checkpoints, and good one-level-deep progressive disclosure into six real reference files. It is held back by verbosity/repetition, instructional rather than executable method guidance, and two orphaned bundle files not surfaced from the body.

Suggestions

Deduplicate the no-fabrication guidance between Step 4.5, Step 5, and Hard Rule 15, keeping it in one authoritative place and cross-referencing it.

Link the two currently orphaned reference files (figure-deliverable-plan.md, validation-evidence-hierarchy.md) from Sections E and F so all prepared materials are discoverable.

Add a few concrete, runnable specifics (e.g. a representative DESeq2/limma command skeleton or the exact overlap-formula evaluation step) so the core plan is more directly executable rather than fully delegated to reference files.

DimensionReasoningScore

Conciseness

The body is mostly efficient and well-structured but includes padding and mild repetition — e.g. the literature rules in Step 4.5 and Hard Rule 15 both restate 'Never fabricate... output a search strategy', and Step 5's formula examples overlap the Hard Rules — so it could be tightened without losing meaning.

3 / 5

Actionability

Guidance is concrete on structure (mandatory output sections, formula notation like 'same-direction DEG overlap ∩ PPI hubs') but largely instructional rather than executable: there is no runnable code, no exact tool commands, and methods are named without parameters or commands, so key execution details are offloaded to reference files.

3 / 5

Workflow Clarity

The 7-step sequence is clearly ordered with an explicit mandatory dependency-consistency checkpoint (Step 5) and a self-critical risk review; the main gap is that Step 7's output is validated only by internal logic rather than an external verify/feedback loop, leaving minor validation gaps.

4 / 5

Progressive Disclosure

The body is an overview that signals six one-level-deep reference files via clear '→ ...: [references/x.md](references/x.md)' links, and those files do not nest further (verified no cross-references inside them); however two bundle files (figure-deliverable-plan.md, validation-evidence-hierarchy.md) are not linked from the body, a minor navigation gap.

4 / 5

Total

14

/

20

Passed

Description

83%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 and explicitly covers both what the skill does and when to use it, with strong specificity via enumerated analysis modules and study patterns. Its main weaknesses are verbosity and missing plainer trigger synonyms that a non-expert user might naturally say.

Suggestions

Trim the dense enumeration (e.g. drop the trailing 'Covers five study patterns...' clause duplication of the workflow list) to reduce verbosity and reward conciseness.

Add plainer trigger synonyms such as 'comorbidity', 'shared genes', or 'two-disease bioinformatics paper' so non-expert phrasing still matches.

Use a more decisive singular 'Use when...' sentence rather than a 'Always use this skill whenever...' construction stacked with long sub-clauses.

DimensionReasoningScore

Specificity

It lists many concrete actions ('per-disease differential expression, shared-signal intersection or concordance, PPI-based hub-gene prioritization, diagnostic evaluation across both diseases, immune infiltration context, pathway interpretation, and optional orthogonal validation') with comprehensive coverage, but the long enumeration is dense and somewhat padded, leaving minor gaps in crispness.

4 / 5

Completeness

It explicitly answers both 'what' ('Generates complete dual-disease shared-transcriptome biomarker and hub-gene research designs') and 'when' ('Always use this skill whenever a user wants to design, plan, or build...') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

It surfaces natural user phrasings like 'design, plan, or build a non-oncology two-disease transcriptome study' and 'shared-biology direction', plus domain terms (hub-gene, immune infiltration), but omits plainer synonyms a user might say (e.g. 'comorbidity', 'shared genes', 'two-disease bioinformatics paper').

4 / 5

Distinctiveness Conflict Risk

The niche is clearly bounded ('non-oncology two-disease', 'bulk-transcriptome', five named study patterns), making conflict risk low, though it sits close to adjacent single-disease or oncology biomarker skills and the scope could be sharper.

4 / 5

Total

17

/

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.