CtrlK
BlogDocsLog inGet started
Tessl Logo

mr-scrna-research-planner

Generates complete Mendelian Randomization + single-cell transcriptomics (scRNA-seq) research designs from a user-provided direction. Always use this skill whenever a user wants to design, plan, or build a study combining MR and single-cell data — even if phrased as "help me write a paper on X", "design a bioinformatics study for Y", or "I want to study Z using MR and scRNA". Covers five study patterns (mechanism gene-set, key-cell, candidate-gene reverse validation, exposure-disease-cell triangulation, translational biomarker) 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.

72

Quality

90%

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 well-structured, highly directive control document with a clear sequenced workflow, mandatory validation, and a clean one-level reference layer. Its main weakness is redundancy — several rules and dependency constraints are restated across steps, output sections, and the Hard Rules list.

Suggestions

Consolidate the reference-verification rules: state them once (e.g., in Step 4.5 / Section I) and have the Hard Rules reference that canonical statement instead of repeating the same constraints three times.

De-duplicate the dependency/QTL-forbidden rules across Step 5, Section C.5, and Hard Rules 16/18 into a single authoritative definition to reduce token cost and the risk of the copies drifting apart.

Move the verbose per-section A–J specifications into a reference file (e.g., a section checklist) so the body stays a lean overview, keeping SKILL.md closer to the progressive-disclosure score-5 pattern.

DimensionReasoningScore

Conciseness

The body is dense and directive with no concept-explanation padding Claude already knows, but several rules are restated multiple times (reference-verification rules in Step 4.5, Section I, and Hard Rules 11–13; dependency rules in Step 5, C.5, and Hard Rules 16/18), which is noticeable redundancy rather than the lean score-5 ideal.

4 / 5

Actionability

Provides concrete executable structure — exact output sections A–J, exact redirect text, exact disclaimer wording, explicit intersection formulas (DEG ∩ MR ∩ coloc), and a mandatory dependency check — but defers the actual 8-field workflow template and module/method details to reference files, leaving minor gaps versus copy-paste-ready score-5 guidance.

4 / 5

Workflow Clarity

A clear 7-step always-in-order sequence with an explicit mandatory validation checkpoint (Step 5 Dependency Consistency Check) and a revise-before-output feedback loop ('If any dependency inconsistency is found, revise the plan before outputting'), matching the score-5 anchor with explicit validation and error-recovery.

5 / 5

Progressive Disclosure

All eight reference files are real, clearly signaled one-level-deep links in consistent '→ ... [references/X.md]' format, but the body still inlines substantial material (the 23 Hard Rules and full A–J section specs) that could be partly consolidated, leaving minor organization gaps versus the score-5 ideal.

4 / 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.

The description is third-person, dense, and fully specifies both capability and trigger conditions, including natural user paraphrases. It cleanly matches the top anchors on every dimension with no padding or over-claims.

DimensionReasoningScore

Specificity

Lists many concrete actions and outputs (four workload configs, recommended primary plan, step-by-step workflow, figure plan, validation strategy, minimal executable version, publication upgrade path, verified reference layer) across five named study patterns — comprehensive coverage matching the score-5 anchor; not below since no meaningful capability is omitted.

5 / 5

Completeness

Explicitly answers both what (generates complete MR + scRNA-seq research designs with the listed components) and when ('Always use this skill whenever a user wants to design, plan, or build a study...') with concrete trigger phrases, matching the score-5 anchor.

5 / 5

Trigger Term Quality

Includes natural user phrasings ('help me write a paper on X', 'design a bioinformatics study for Y', 'I want to study Z using MR and scRNA') plus the direct trigger 'design, plan, or build a study combining MR and single-cell data', giving comprehensive synonym/paraphrase coverage a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The narrow MR + scRNA-seq research-design niche with explicit triggers is highly distinct and unlikely to fire for unrelated skills; minimal conflict risk, matching the score-5 anchor.

5 / 5

Total

20

/

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.