scVelo (Claude Skill)
Claude skill that drives scVelo for RNA-velocity analysis — estimating directed cell-state transitions from unspliced/spliced mRNA dynamics in single-cell RNA-seq data.
| Type | Claude Skill |
| Supplier | K-Dense Inc. (community OSS) |
| Availability | GA — actively maintained 2025–2026 |
| Pricing | Free / OSS skill (MIT collection); scVelo itself is BSD-3 |
| Capabilities | Read/Write — Claude executes scVelo via Python/Bash |
How to install
- Claude Code / Claude.ai — Skills CLI (recommended):
npx skills add K-Dense-AI/scientific-agent-skillsInstalls the K-Dense collection; enable the
scveloskill when prompted (also works in Cursor/Codex via the Agent Skills spec; requires Node ≥ 18). - Claude Code / Claude Desktop — manual clone:
git clone https://github.com/K-Dense-AI/scientific-agent-skills cp -r scientific-agent-skills/skills/scvelo ~/.claude/skills/ pip install scvelo
Project-scoped alternative: copy into .claude/skills/ instead of ~/.claude/skills/.
What it does
SKILL.md with recipes for:
- Preprocessing unspliced/spliced counts from loom / velocyto / STARsolo / Kallisto-bustools outputs
- Steady-state, stochastic, and dynamical velocity models
- Velocity-embedding projections onto UMAP / t-SNE
- Latent-time inference and driver-gene identification
- Velocity confidence and coherence scoring
- Trajectory and lineage analysis paired with PAGA
Primary use cases: Mapping differentiation trajectories, identifying lineage-decision genes, dynamics analysis in development and disease, ordering cells by inferred latent time.
Notes
Pairs with the catalog’s scanpy, anndata, cellxgene-census, and scvi-tools skills for end-to-end single-cell trajectory workflows. RNA-velocity requires upstream alignment that emits spliced + unspliced count matrices (velocyto, kallisto-bustools, or STARsolo Velocyto mode) — scVelo cannot recover velocities from a counts-only AnnData. Skill is documentation plus Python recipes — Claude calls scVelo locally via Bash/Python.
Sources
K-Dense-AI/scientific-agent-skillsskills/scvelo/SKILL.md- scVelo documentation
- Bergen et al. Nat Biotechnol 2020
Installed this tool?
Share feedback — install path, OS, errors, workarounds. The form opens with this tool pre-selected and a link back to this page.