Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

scVelo RNA Velocity Analysis

A complete scVelo workflow skill for inferring cell-state transition directions, latent time, and driver genes from spliced/unspliced mRNA dynamics.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Computes RNA velocity from unspliced/spliced mRNA ratios and renders directional arrow and stream plots over your UMAP embedding.
  • Guides model selection across stochastic, deterministic, and dynamical estimators, and uses the dynamical model to derive latent time plus per-gene transcription, splicing, and degradation rates.
  • Covers downstream steps end to end: rank_velocity_genes, velocity_confidence, velocity pseudotime, PAGA transition graphs, and a reference table of every field written back into AnnData.
  • Flags real-world pitfalls: scVelo 0.3 dropped log-transform/HVG from filter_and_normalize, the dynamical model needs pandas<3, and the stochastic estimator needs numpy<2.

Who it's for

  • Single-cell researchers who need differentiation directionality (hematopoiesis, neurogenesis, EMT) from snapshot data.
  • Analysts who already have clusters and UMAPs from Scanpy/scVI-tools and want directional trajectory information.
  • Pipeline engineers who produced spliced/unspliced counts with velocyto, STARsolo, or alevin-fry.

Example uses

  1. "Merge velocyto.loom with processed.h5ad and give me a quick stochastic-mode velocity stream plot" — handles merge, preprocessing, and moments in one pass.
  2. "Run the dynamical model, compute latent time, and plot a heatmap of the top 300 genes by fit_likelihood."
  3. "My velocity arrows look random — debug it" — walks the troubleshooting table (n_neighbors tuning, swapped spliced/unspliced layers, low unspliced coverage).

· · · Install guide · · ·

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 skills/scvelo folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/scvelo/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/scvelo ~/.claude/skills/

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

  1. Open a terminal and cd into the folder where you keep repos.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/scvelo ~/.claude/skills/
  5. Install Python dependencies: uv pip install scvelo scanpy anndata (respect the pandas<3 and numpy<2 constraints noted in the skill).
  6. Restart Claude Code, then ask something like "use scvelo to run RNA velocity on my AnnData."
  7. Before running, verify with print(adata) that your object has layers['spliced'], layers['unspliced'], and obsm['X_umap'].
View source on GitHub ↗License: MIT