cell-annotation

Name: cell-annotation
Availability: InStock
Author: zongtingwei

Annotate single-cell RNA-seq data with cell-type labels using marker review and reference transfer.

25|5|Updated Mar 22, 2026

Search Tags:#confidence #single-cell #annotation #scRNA-seq #celltypist #marker-review #reference-transfer

Ready to run

npx skills add https://github.com/zongtingwei/Bioclaw_Skills_Hub --skill cell-annotation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cell-annotation
Source: https://github.com/zongtingwei/Bioclaw_Skills_Hub/tree/main/skills/single-cell-and-spatial/cell-annotation
Command: npx skills add https://github.com/zongtingwei/Bioclaw_Skills_Hub --skill cell-annotation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates and guides the assignment of cell-type labels to single-cell RNA-seq data by integrating marker-guided evidence, reference atlas transfer, and confidence-aware curation to reduce manual curation time and improve consistency.

Core Features & Use Cases

Automated cell-type annotation using marker review and reference transfer
Confidence-aware labeling with per-cell and per-cluster outputs for uncertainty handling
Outputs include annotated labels, marker summaries, and annotation notes for reproducibility
Real-world use case: annotate a newly generated PBMC scRNA-seq atlas against a reference atlas to produce a ready-to-publish cell-type map

Quick Start

Run the annotation workflow on a processed scRNA-seq dataset to obtain per-cell labels, confidence scores, and a cluster-level summary.

Frequently Asked Questions about cell-annotation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate cell-type annotation for scRNA-seq data using marker review and reference transfer?▼

Automated single-cell cell-type annotation integrates marker-guided evidence and reference atlas transfer to assign accurate labels, reducing manual curation time and improving consistency across scRNA-seq experiments.

How does confidence-aware curation work when labeling single-cell clusters?▼

Confidence-aware curation evaluates per-cell and per-cluster confidence scores during reference transfer, allowing you to handle uncertainty and refine cell-type labels across scRNA-seq experiments.

Do I need scanpy and CellTypist to assign cell-type labels to my scRNA-seq data?▼

Yes, assigning cell-type labels requires a Python environment with scanpy and CellTypist to execute the automated annotation workflow and output annotated h5ad files and label summaries.

What is the best way to annotate a newly generated PBMC scRNA-seq atlas against a reference?▼

The best way to annotate a PBMC scRNA-seq atlas is using automated reference transfer with marker review, producing a ready-to-publish cell-type map with per-cell labels, confidence scores, and summaries.

What outputs are generated when applying reference transfer to single-cell data?▼

Applying reference transfer generates annotated h5ad files, per-cell labels, confidence scores, cluster-level summaries, marker summaries, and annotation notes to ensure full reproducibility of the labeling process.