albert-ying/scanpy
.autolab/acquired_skills/scanpy/SKILL.md
Single-cell RNA-seq analysis with Scanpy. QC, normalization, clustering, visualization, marker gene identification.
$ install --global
skillsauthnpx skillsauth add albert-ying/autonomous-lab scanpyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 3:22 PM1.8s1 file scanned
SKILL.md
- name:
- scanpy
- description:
- Single-cell RNA-seq analysis with Scanpy. QC, normalization, clustering, visualization, marker gene identification.
- skill-author:
- Albert Ying
Scanpy
When to use
- Single-cell RNA-seq data preprocessing and QC
- Dimensionality reduction (PCA, UMAP, t-SNE)
- Cell clustering (Leiden, Louvain)
- Marker gene identification
- Cell type annotation
Standard workflow
import scanpy as sc
import anndata as ad
# Read 10X data
adata = sc.read_10x_mtx('path/to/data/', var_names='gene_symbols')
# QC
sc.pp.filter_cells(adata, min_genes=200)
sc.pp.filter_genes(adata, min_cells=3)
adata.var['mt'] = adata.var_names.str.startswith('MT-')
sc.pp.calculate_qc_metrics(adata, qc_vars=['mt'], inplace=True)
adata = adata[adata.obs.pct_counts_mt < 20].copy()
# Normalize and log-transform
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)
# HVG selection
sc.pp.highly_variable_genes(adata, n_top_genes=2000, batch_key='batch')
# Scale, PCA, neighbors, clustering
sc.pp.scale(adata, max_value=10)
sc.tl.pca(adata, n_comps=50)
sc.pp.neighbors(adata, n_pcs=30)
sc.tl.leiden(adata, resolution=0.5)
sc.tl.umap(adata)
# Marker genes
sc.tl.rank_genes_groups(adata, 'leiden', method='wilcoxon')
Key decisions
- Filter cells with < 200 genes and > 20% mitochondrial reads
- Use batch-aware HVG selection when integrating multiple samples
- Leiden resolution controls cluster granularity (0.3-1.0 typical)
- Use Wilcoxon rank-sum test for marker gene identification
Related Skills
albert-ying/scientific-analysis-review
development
VerifiedTrustedCommunity
Critically review AI-agent-conducted scientific analyses for correctness, rigor, and completeness. Use this skill whenever an analysis session has completed and needs validation, when a user asks to "review," "validate," "check," or "audit" a computational analysis, or when an agent pipeline produces scientific results that require quality control before reporting. Also trigger when the user references an execution trace, notebook, or conversation history from a prior analysis session. This skill should run as the final step of any autonomous scientific analysis pipeline.
7SKILL.mdUpdated Apr 3, 2026
albert-ying/.autolab/acquired_skills/variant-calling
tools
VerifiedTrustedCommunity
# Variant Calling Skill ## When to Use Use when calling SNPs and indels from aligned BAM files against a reference. ## Standard Workflow 1. Mark duplicates (optional): `samtools markdup` 2. Call variants with freebayes: `freebayes -f reference.fasta -p 1 sample.bam > variants.vcf` OR with bcftools: `bcftools mpileup -f ref.fa sample.bam | bcftools call -mv -Oz -o variants.vcf.gz` 3. Filter variants: `bcftools filter -s LowQual -e 'QUAL<20' variants.vcf` ## Key Decisions - For haploid organ
7SKILL.mdUpdated Apr 3, 2026
albert-ying/.autolab/acquired_skills/trimmomatic
tools
VerifiedTrustedCommunity
# Trimmomatic - Read Quality Trimming ## When to Use Use Trimmomatic to trim adapter sequences and low-quality bases from Illumina sequencing reads. ## Standard Workflow 1. Install: `conda install -c bioconda trimmomatic` 2. Run: `trimmomatic PE <input_R1.fastq.gz> <input_R2.fastq.gz> <output_R1_paired.fastq.gz> <output_R1_unpaired.fastq.gz> <output_R2_paired.fastq.gz> <output_R2_unpaired.fastq.gz> ILLUMINACLIP:<adapters.fa>:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36` ## Key Pa
7SKILL.mdUpdated Apr 3, 2026
albert-ying/.autolab/acquired_skills/spades-assembly
testing
VerifiedTrustedCommunity
# SPAdes Assembly Skill ## When to Use Use for de novo genome assembly when no reference genome is available. ## Standard Workflow 1. Run SPAdes: `spades.py -1 R1.fastq.gz -2 R2.fastq.gz -o assembly_output --careful` 2. Check assembly stats: look at scaffolds.fasta or contigs.fasta 3. Use assembled genome as reference for read mapping ## Key Decisions - Use `--careful` flag for bacterial genomes to reduce misassemblies - For small bacterial genomes, default k-mer sizes work well - Output scaf
7SKILL.mdUpdated Apr 3, 2026