Agent skill

Sc Pseudotime

by TianGzlab in TianGzlab/OmicsClaw

Load when ordering cells along a developmental trajectory in a normalised scRNA AnnData via DPT, Palantir, VIA, CellRank, Slingshot (R), or Monocle3 (R).

Apache-2.0Auto-check passedResearch & Science

Install Sc Pseudotime

skills CLI
$ npx skills add TianGzlab/OmicsClaw --skill sc-pseudotime -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install TianGzlab/OmicsClaw sc-pseudotime --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/singlecell/scrna/sc-pseudotime .claude/skills/sc-pseudotime && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
sc-pseudotime
GitHub stars
161
Token cost
~1.9k tokens
SKILL.md length
695 words
Files
12 (incl. references)
Skills in repo
88
Repo updated
First seen
Licence
Apache-2.0

At a glance

Load when ordering cells along a developmental trajectory in a normalised scRNA AnnData via DPT, Palantir, VIA, CellRank, Slingshot (R), or Monocle3 (R).

  • Tasks that involve Bioinformatics
  • SKILL.md covers Use from a step, API, Methods and parameters and Gotchas, plus 3 more sections
  • Runs Python scripts from its folder; calls python

What it does

Sc Pseudotime is an agent skill from TianGzlab/OmicsClaw. Load when ordering cells along a developmental trajectory in a normalised scRNA AnnData via DPT, Palantir, VIA, CellRank, Slingshot (R), or Monocle3 (R). Skip when ranking marker genes per cluster (use sc-markers); RNA velocity vector fields (use sc-velocity).

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `_api.py`, `examples/example_step.py` and `references/methodology.md`).

It sits in Research & Science, covering Bioinformatics. It works with AnnData. The repository describes itself as: Conversational & memory-enabled AI research partner for multi-omics analysis. CLI + Desktop App (installers in Releases). From biological idea to full research paper. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Bioinformatics

Example prompts

  • “/sc-pseudotime”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 90a3bec. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sc Pseudotime loads about 1.9k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 69 tokens; SKILL.md has 695 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from TianGzlab/OmicsClaw at commit 90a3bec, republished under its Apache-2.0 licence (© TianGzlab). 695 words, ~1,851 tokens.

Download SKILL.mdSave it as .claude/skills/sc-pseudotime/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
sc-pseudotime
description
Load when ordering cells along a developmental trajectory in a normalised scRNA AnnData via DPT, Palantir, VIA, CellRank, Slingshot (R), or Monocle3 (R). Skip when ranking marker genes per cluster (use sc-markers); RNA velocity vector fields (use sc-velocity).
trigger
pseudotime, trajectory, lineage, diffusion pseudotime, palantir, via, cellrank, monocle3, slingshot
tags
singlecell, scrna, pseudotime, trajectory, dpt, palantir, via, cellrank, slingshot, monocle3

sc-pseudotime

Use from a step

python
trajectory = load_skill("sc-pseudotime")
result = trajectory.pseudotime(read_input("clustered.h5ad"), cluster_key="leiden",
                                use_rep="X_pca", root_cluster="0")
write_output(trajectory.pseudotime_table(result), "tables/pseudotime.csv")
write_output(trajectory.trajectory_genes(result), "tables/trajectory_genes.csv")
write_output(trajectory.pseudotime_figure(result), "figures/pseudotime.png")
write_output(result, "intermediate/adata_pseudotime.h5ad")

The input is not changed. The PBMC example in examples/example_step.py demonstrates the API; PBMC labels do not validate a differentiation trajectory.

API

<!-- api:begin generated from _api.py; regenerate with run.py api <skill dir> --write -->
pseudotime(adata, *, method: str='dpt', cluster_key: str='leiden', use_rep: str | None=None, root_cluster: str | None=None, root_cell: str | int | None=None, end_clusters: list[str] | None=None, n_neighbors: int=15, n_pcs: int=50, n_dcs: int=10, palantir_knn: int=30, palantir_n_components: int=10, palantir_num_waypoints: int=1200, palantir_max_iterations: int=25, palantir_seed: int | None=None, via_knn: int=30, via_seed: int | None=None, cellrank_n_states: int=3, cellrank_schur_components: int=20, cellrank_frac_to_keep: float=0.3, cellrank_use_velocity: bool=False, random_state: int=20)

Return a copy with pseudotime and backend diagnostics.

The default representation prefers X_pca; UMAP remains the preferred display embedding, not the default inference graph. This function does not disable numba JIT. Roots express an analysis assumption, not a direction inferred from the pseudotime values.

:param method: dpt, palantir, via, cellrank, slingshot_r or monocle3_r. :param cluster_key: Existing obs grouping column; default leiden. :param use_rep: Existing obsm representation; None prefers X_pca. :param root_cluster: Optional root group for the selected backend. :param root_cell: Optional obs name or integer position. :param end_clusters: Optional Slingshot terminal groups. :param n_neighbors: DPT/CellRank neighbors; default 15. :param n_pcs: PCs for those neighbors; default 50. :param n_dcs: Diffusion components used for DPT; default 10. :param palantir_knn: Palantir neighbors, default 30. :param palantir_n_components: Palantir diffusion components, default 10. :param palantir_num_waypoints: Palantir waypoints, default 1200. :param palantir_max_iterations: Palantir iterations, default 25. :param palantir_seed: Overrides random_state for Palantir; default None. :param via_knn: VIA neighbors, default 30. :param via_seed: Overrides random_state for VIA; default None. :param cellrank_n_states: CellRank states, default 3. :param cellrank_schur_components: CellRank Schur components, default 20. :param cellrank_frac_to_keep: CellRank state-cell fraction, default 0.3. :param cellrank_use_velocity: Couple CellRank to existing velocity; default False. :param random_state: Palantir/VIA seed, default 20. DPT retains Scanpy's deterministic defaults; R wrappers do not expose a seed. :returns: New AnnData with obs['pseudotime']; run_info names the backend and original pseudotime column. R curves remain available separately. :raises ValueError: The method, grouping, expression contract or embedding is invalid. :raises ImportError: An optional backend is missing.

run_info(adata, *, keep: bool=True) -> dict

Read method, root and representation diagnostics; keep=False removes the record.

trajectory_genes(adata, *, n_genes: int=50, method: str='pearson') -> pd.DataFrame

Rank genes by correlation with pseudotime; method is pearson or spearman.

pseudotime_table(adata) -> pd.DataFrame

Return cell, display coordinates, group and pseudotime columns.

fate_probability_table(adata) -> pd.DataFrame

Return backend fate probabilities averaged by group, or an empty table.

trajectory_curves(adata) -> pd.DataFrame

Return retained R trajectory curves, or an empty table for Python methods.

pseudotime_figure(adata)

Return a matplotlib Figure colored by pseudotime on the display embedding.

<!-- api:end -->
Show full SKILL.md (293 more words)Show less

Methods and parameters

Six methods remain available: DPT, Palantir, VIA, CellRank, Slingshot R and Monocle3 R. DPT uses Scanpy. Other methods require their named backend; missing packages raise errors rather than selecting a different method.

use_rep=None now prefers X_pca, consistent with preflight. UMAP is still preferred for display, not the inference graph. Root cells accept obs names or integer positions. Root and terminal choices are biological assumptions the caller must justify.

Neighbor/component defaults retain the CLI behavior: 15 neighbors, 50 PCs and 10 DPT components. Palantir defaults to 30 neighbors, 10 diffusion components, 1200 waypoints and 25 iterations; VIA uses 30 neighbors. random_state=20 supplies the Palantir/VIA seed unless their explicit overrides are given. DPT retains Scanpy's deterministic defaults.

Gotchas

  • The API does not set NUMBA_DISABLE_JIT; the compatibility CLI retains its existing setting (sc_pseudotime.py:15).
  • run_info reports the chosen representation and root. Check finite obs["pseudotime"] values; disconnected graphs can produce infinity (_api.py:183).
  • Existing matrix contracts must identify normalized expression. Root choice does not prove direction or causality (_api.py:28).
  • R wrappers still exchange temporary H5AD, requiring zellkonverter and its R/Python setup. This migration does not convert them to MTX. Slingshot and Monocle3 have separate explicit package checks (_api.py:482, _api.py:556).
  • VIA applies its existing NumPy compatibility aliases only when invoked (_api.py:230).
  • fate_probability_table is a group mean, not per-cell fate probabilities; the per-cell matrix is obsm["trajectory_fate_probabilities"] (_api.py:204).

Inputs & Outputs

The API needs normalized expression, an obs grouping and an obsm representation. It returns an annotated copy plus table/Figure helpers. R curves can be read through trajectory_curves.

CLI files include processed.h5ad, tables/pseudotime_cells.csv, tables/trajectory_genes.csv, tables/trajectory_summary.csv, report.md and result.json. Fate-probability and curve tables are conditional on backend output. Figures and figure-data manifests describe the plots actually produced.

Key CLI

bash
python skills/singlecell/scrna/sc-pseudotime/sc_pseudotime.py --demo --use-rep X_pca --output /tmp/sc_pt_demo
python skills/singlecell/scrna/sc-pseudotime/sc_pseudotime.py --input clustered.h5ad --cluster-key leiden --root-cluster 0 --use-rep X_pca --output results/

Dependencies

anndata, cellrank, matplotlib, numpy, palantir, pandas, pyVIA, scanpy, scipy, scvelo, seaborn

© TianGzlab, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in skills/singlecell/scrna/sc-pseudotime of TianGzlab/OmicsClaw.

  • SKILL.md
  • _api.py
  • examples/example_step.py
  • references/methodology.md
  • references/output_contract.md
  • references/parameters.md
  • references/r_visualization.md
  • sc_pseudotime.py
  • tests/scagentbench_paga.py
  • tests/test_pseudotime_api.py
  • tests/test_sc_pseudotime_methods.py
  • tests/test_scagentbench_paga.py

Open the folder on GitHubat commit 90a3bec

Compare with similar skills

Sc Pseudotime next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Sc Pseudotime compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sc Pseudotime this skillTianGzlab/OmicsClaw161—~1.9kAutomated safety check: PassApache-2.0
Scanpy Single-Cell Analysisdavila7/claude-code-templates32k15 repos~2.8kAutomated safety check: PassMIT
PyDESeq2 Differential Expressiondavila7/claude-code-templates32k11 repos~4kAutomated safety check: PassMIT
Single-Cell Initial AnalysisLigphiDonk/Oh-my--paper7381 repos~1.4kAutomated safety check: PassMIT
Anndataaipoch/medical-research-skills2k—~1.7kAutomated safety check: PassMIT
Multiomics StatisticsVectorSpaceLab/AREX-Skill330—~1kAutomated safety check: PassGPL-3.0

Similar skills

  • Scanpy Single-Cell Analysis

    davila7/claude-code-templates

    Walks through single-cell RNA-seq analysis with Scanpy: loading .h5ad and 10X data, QC, normalization, PCA and UMAP, Leiden clustering, marker genes and cell type annotation.

    32k GitHub starsUsed in 15 repos~2.8k tokens
    Research & ScienceAuto-check passed
  • PyDESeq2 Differential Expression

    davila7/claude-code-templates

    Runs differential gene expression analysis on bulk RNA-seq counts with PyDESeq2: design formulas, Wald tests, FDR correction and volcano or MA plots.

    32k GitHub starsUsed in 11 repos~4k tokens
    Research & ScienceAuto-check passed
  • Single-Cell Initial Analysis

    LigphiDonk/Oh-my--paper

    Runs a seven-step quality-control and exploration pipeline on scRNA-seq, CyTOF or flow cytometry data and writes a plain-language report of what it found.

    738 GitHub starsUsed in 1 repo~1.4k tokens
    Research & ScienceAuto-check passed
  • Anndata

    aipoch/medical-research-skills

    Data structure for annotated matrices in single-cell analysis; use when reading/writing .h5ad (or zarr) and exchanging data with the scverse ecosystem.

    2k GitHub stars~1.7k tokensUpdated 22 days ago
    Research & ScienceAuto-check passed
  • Multiomics Statistics

    VectorSpaceLab/AREX-Skill

    A skill your agent uses for OmicVerse bulk RNA-seq, enrichment/signature scoring, metabolomics, proteomics, microbiome, and statistical table workflows.

    330 GitHub stars~1k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed
  • Scgpt

    JimLiu/science-skills

    Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology.

    227 GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed

More from TianGzlab/OmicsClaw

All 88 skills in this repo
  • Bulkrna Cosinor Rhythm

    TianGzlab/OmicsClaw

    Load when the user needs Deterministic fixed-period 24-hour single-component cosinor OLS rhythm analysis for a bulk RNA time-course CSV.

    161 GitHub stars~840 tokensUpdated yesterday
    Auto-check passed
  • Bulkrna Batch Correction

    TianGzlab/OmicsClaw

    Load when correcting batch effects in bulk expression using R sva ComBat or the legacy Python parametric approximation.

    161 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Bulkrna Coexpression

    TianGzlab/OmicsClaw

    Load when discovering bulk gene co-expression modules and hub genes with R WGCNA.

    161 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Bulkrna De

    TianGzlab/OmicsClaw

    Load when comparing gene expression between two conditions in bulk RNA-seq count data.

    161 GitHub stars~867 tokensUpdated yesterday
    Auto-check passed
  • Bulkrna Deconvolution

    TianGzlab/OmicsClaw

    Load when estimating cell-type proportions in bulk RNA-seq samples from a single-cell or signature-matrix reference.

    161 GitHub stars~757 tokensUpdated yesterday
    Auto-check passed
  • Bulkrna Enrichment

    TianGzlab/OmicsClaw

    Load when running pathway / GO term enrichment on a bulk RNA-seq DE result list.

    161 GitHub stars~860 tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Sc Pseudotime

What does Sc Pseudotime do?

Load when ordering cells along a developmental trajectory in a normalised scRNA AnnData via DPT, Palantir, VIA, CellRank, Slingshot (R), or Monocle3 (R). Sc Pseudotime is an agent skill from TianGzlab/OmicsClaw. Load when ordering cells along a developmental trajectory in a normalised scRNA AnnData via DPT, Palantir, VIA, CellRank, Slingshot (R), or Monocle3 (R).

When should I use Sc Pseudotime?

Sc Pseudotime fits situations like: tasks that involve Bioinformatics.

How do I install Sc Pseudotime in Claude Code?

Run `npx skills add TianGzlab/OmicsClaw --skill sc-pseudotime -a claude-code`. Or copy the skill folder (skills/singlecell/scrna/sc-pseudotime in TianGzlab/OmicsClaw) into .claude/skills/sc-pseudotime in your project. Claude Code loads it when a task matches its description.

How do I install Sc Pseudotime in Codex?

Run `npx skills add TianGzlab/OmicsClaw --skill sc-pseudotime -a codex`. Or copy the skill folder (skills/singlecell/scrna/sc-pseudotime in TianGzlab/OmicsClaw) into .agents/skills/sc-pseudotime in your project. Codex loads it when a task matches its description.

Can I use Sc Pseudotime in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add TianGzlab/OmicsClaw --skill sc-pseudotime -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sc-pseudotime, .gemini/skills/sc-pseudotime, .github/skills/sc-pseudotime and .opencode/skills/sc-pseudotime in your project.

What does Sc Pseudotime need to run?

Going by SKILL.md and its folder, Sc Pseudotime needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Sc Pseudotime access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Sc Pseudotime safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sc Pseudotime use?

Sc Pseudotime is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sc Pseudotime use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Sc Pseudotime?

Skills that share tags, products or a category with Sc Pseudotime: Scanpy Single-Cell Analysis (davila7/claude-code-templates, 32k stars), PyDESeq2 Differential Expression (davila7/claude-code-templates, 32k stars), Single-Cell Initial Analysis (LigphiDonk/Oh-my--paper, 738 stars) and Anndata (aipoch/medical-research-skills, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sc Pseudotime?

TianGzlab (a GitHub organization) maintains it in TianGzlab/OmicsClaw, which has 161 GitHub stars. The repository holds 88 skills in this directory. The repository was last updated on October 7, 2026.

Source: TianGzlab/OmicsClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.