Bioinformatics
PassAudited by ClawScan on May 1, 2026.
Overview
This skill is coherent for local bioinformatics analysis, but users should notice that it runs command-line genomics tools, may install external packages/databases, and can store project context locally with consent.
Install and run this only if you are comfortable using local bioinformatics command-line tools. Keep sensitive genomic data local, verify package and database sources, review paths before running commands, and only enable ~/bioinformatics/ memory for information you want persisted.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Running the suggested commands can modify the working directory, generate large outputs, and use substantial CPU, memory, and time.
The skill provides local shell pipelines that read sequencing inputs and write analysis outputs; this is central to the bioinformatics purpose, but it can create or overwrite large files and consume significant resources.
bwa mem -t 8 reference.fa R1.fq.gz R2.fq.gz | samtools sort -o aligned.bam -
Review commands and paths before running them, keep raw data read-only or backed up, and confirm before long or resource-intensive jobs.
Installed tool versions or external databases may affect analysis results or introduce ordinary package-supply-chain risk.
The setup guidance uses external package channels and does not pin exact versions; this is normal for scientific tooling but affects provenance and reproducibility.
conda create -n bioinfo -c bioconda -c conda-forge samtools bcftools bedtools bwa star fastqc fastp multiqc
Install from trusted channels, pin versions for important analyses, and verify reference genomes/databases where possible.
Project notes could persist sensitive research, organism, sample, or health-related context on the local machine.
The skill can persist project context, references, compute details, and preferences across sessions; the artifacts say this should be consent-based and limited to explicit user disclosures.
Ask for consent to create `~/bioinformatics/` for storing project context... Save to `~/bioinformatics/memory.md` only information the user explicitly provides
Approve persistence only for details you are comfortable saving, avoid storing identifiers or clinical details unless necessary, and review/delete ~/bioinformatics/memory.md when needed.