single-cell-rnaseq-pipeline

Generate single-cell RNA-seq analysis code templates for Seurat and Scanpy, supporting QC, clustering, visualization, and downstream analysis. Trigger when users need scRNA-seq analysis pipelines, preprocessing workflows, or batch correction code.

1.28x

Quality

86%

Does it follow best practices?

Impact

90%

1.28x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

100%

20%

PBMC Multi-Donor Integration Analysis

Scanpy QC parameters and clustering

Criteria

Without context

With context

Human MT pattern

100%

MT percent threshold

100%

Min genes threshold

100%

Max genes threshold

100%

Normalization target sum

100%

Log transform

100%

HVG count

100%

Leiden clustering

100%

Wilcoxon markers

100%

Neighbor parameters

50%

100%

Harmony for small batches

100%

Relative paths

100%

Without context: $0.3545 · 1m 40s · 16 turns · 23 in / 5,552 out tokens

With context: $1.0438 · 4m 50s · 33 turns · 1,761 in / 9,399 out tokens

100%

38%

Mouse Tumor Microenvironment Multi-Lab scRNA-seq Pipeline

Seurat pipeline with species-specific settings and batch correction

Criteria

Without context

With context

Mouse MT pattern

100%

MT percent threshold

100%

Min genes threshold

100%

Max genes threshold

100%

RPCA for large batches

100%

LogNormalize scale factor

100%

VST nfeatures

50%

100%

PCA dimensions

100%

FindAllMarkers params

100%

Clustering resolution

100%

Relative paths

100%

No API calls

100%

Without context: $0.3013 · 2m 6s · 11 turns · 16 in / 6,415 out tokens

With context: $0.9555 · 3m 46s · 34 turns · 202 in / 7,518 out tokens

70%

Generate scRNA-seq Analysis Pipelines for Cross-Tissue Developmental Study

CLI tool usage and output structure

Criteria

Without context

With context

Script invocation

100%

Tool both flag

100%

Species flag

100%

Trajectory flag

100%

Complex variation batch method

Seurat R file generated

100%

Scanpy Python file generated

100%

README generated

100%

Trajectory code in Scanpy output

100%

Invalid param error format

20%

Batch method in Seurat output

Without context: $0.4615 · 2m 3s · 13 turns · 17 in / 8,908 out tokens

With context: $0.9580 · 3m 52s · 34 turns · 206 in / 9,151 out tokens

Repository: aipoch/medical-research-skills
Commit: ca9aaa4

Evaluated: 17 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

PBMC Multi-Donor Integration Analysis Mouse Tumor Microenvironment Multi-Lab scRNA-seq Pipeline Generate scRNA-seq Analysis Pipelines for Cross-Tissue Developmental Study

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.