Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Single-Cell RNA-seq Cell Type Annotation Guide

A decision-tree-driven skill for labeling cell types in scRNA-seq data via manual markers, automated classifiers, or reference label transfer.

Data & AnalyticsIntermediate★ 361⑂ 36AI score 8/10Last updated: Aug 29, 2026

What it does

  • Standardizes the cell type annotation workflow for single-cell RNA-seq datasets.
  • Helps you choose among manual marker-based (Scanpy/Seurat), automated (CellTypist), and reference label transfer (scArches/scANVI/Azimuth/SingleR) using a decision tree and scenario tables.
  • Provides a 4-step workflow — QC first, marker assessment, automated validation, reference refinement — with runnable Python snippets.
  • Documents 7 common pitfalls (doublet clusters, ambient RNA, over-interpreting tiny clusters, reference mismatch, conflating states with types, etc.) and how to avoid each.
  • Includes marker panels for immune, epithelial, and stromal lineages plus a final validation checklist.

Who it's for

  • Bioinformaticians and grad students analyzing scRNA-seq data
  • Anyone who has clustered in Scanpy/Seurat but is stuck on naming clusters
  • Teams needing objective criteria to validate automated annotation output
  • Researchers who must document annotation evidence and confidence for publication

Example uses

  1. "I have 150k human PBMCs — which annotation strategy?" → decision tree routes you to CellTypist with a manual marker dot-plot cross-check.
  2. "Leiden cluster 7 expresses both CD3D and CD14" → flags a likely doublet cluster and walks through re-running Scrublet and removal.
  3. "Can I transfer human atlas labels onto zebrafish data?" → warns about cross-species reference mismatch and suggests manual markers with ortholog mapping.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/jaechang-hits/SciAgent-Skills/HEAD/legacy/single-cell-annotation/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the legacy/single-cell-annotation folder from the GitHub repo jaechang-hits/SciAgent-Skills into my ~/.claude/skills/single-cell-annotation/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/jaechang-hits/SciAgent-Skills.git && mkdir -p ~/.claude/skills && cp -r SciAgent-Skills/legacy/single-cell-annotation ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/jaechang-hits/SciAgent-Skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r SciAgent-Skills/legacy/single-cell-annotation ~/.claude/skills/
  5. Restart Claude Code and confirm single-cell-annotation appears in your skill list.
  6. Because the skill has no explicit trigger phrases, invoke it directly: "Use the single-cell annotation skill to plan labeling for this dataset."
  7. To actually run the code samples, install scanpy, celltypist, and scarches in your Python environment separately.
View source on GitHub ↗License: NOASSERTION