Single-cell RNA quality checker
Give it an h5ad or h5 file. Get low-quality cells filtered and plots showing data quality.
Single-cell RNA quality checker is a free AI skill for the job "Test and fix code". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · Apache 2.0 licence · Made by Anthropic · Level: advanced
Made by Anthropic. See the original on GitHub; we copied it as it is, with its licence.
What it does
Low-quality cells filtered out of your single-cell file, plus plots that show how good the data is. It sets thresholds from your own data instead of a fixed number. Give it an h5ad file or a 10X Cell Ranger h5 file. A bundled script loads either format, calculates metrics such as genes per cell, counts and mitochondrial share, then flags outliers using median absolute deviation, the scverse standard. Cells outside the limits are removed, and the plots show the before and after. You can adjust thresholds or run many datasets in a batch. You need Python with scanpy installed.
You give it
- An h5ad or 10X h5 file
- Python with scanpy
- Custom thresholds (optional)
You get
- A filtered dataset
- QC plots before and after
- Per-cell quality metrics
- A summary of cells removed
Use it when
- You just received a new single-cell dataset and need to clean it.
- Dead or broken cells may be skewing your clusters.
- You want the same QC across many samples.
- A reviewer asks you to follow scverse practice.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run code.