Agent skill

Spatial De

Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics.

Install Spatial De

skills CLI

$ npx skills add TianGzlab/OmicsClaw --skill spatial-de -a claude-code

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

GitHub CLI

$ gh skill install TianGzlab/OmicsClaw spatial-de --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/spatial/spatial-de .claude/skills/spatial-de && 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/

Paste into Claude Code

Install the "spatial-de" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/spatial/spatial-de into .claude/skills/spatial-de/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spatial-de", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/TianGzlab/OmicsClaw/tree/main/skills/spatial/spatial-de

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add TianGzlab/OmicsClaw --skill spatial-de -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install TianGzlab/OmicsClaw spatial-de --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/spatial/spatial-de .agents/skills/spatial-de && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "spatial-de" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/spatial/spatial-de into .agents/skills/spatial-de/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spatial-de", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add TianGzlab/OmicsClaw --skill spatial-de -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install TianGzlab/OmicsClaw spatial-de --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/spatial/spatial-de .cursor/skills/spatial-de && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "spatial-de" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/spatial/spatial-de into .cursor/skills/spatial-de/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spatial-de", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/TianGzlab/OmicsClaw.git --path skills/spatial/spatial-de

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add TianGzlab/OmicsClaw --skill spatial-de -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install TianGzlab/OmicsClaw spatial-de --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/spatial/spatial-de .gemini/skills/spatial-de && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "spatial-de" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/spatial/spatial-de into .gemini/skills/spatial-de/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spatial-de", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install TianGzlab/OmicsClaw spatial-de

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add TianGzlab/OmicsClaw --skill spatial-de -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/spatial/spatial-de .github/skills/spatial-de && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "spatial-de" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/spatial/spatial-de into .github/skills/spatial-de/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spatial-de", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add TianGzlab/OmicsClaw --skill spatial-de -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install TianGzlab/OmicsClaw spatial-de --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/TianGzlab/OmicsClaw.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/spatial/spatial-de .opencode/skills/spatial-de && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "spatial-de" agent skill from https://github.com/TianGzlab/OmicsClaw/tree/main/skills/spatial/spatial-de into .opencode/skills/spatial-de/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spatial-de", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: spatial-de
GitHub stars: 161
Token cost: ~1.7k tokens
SKILL.md length: 568 words
Files: 11 (incl. references)
Skills in repo: 95
Repo updated: Jul 28, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics.

Works in 6 steps: Load the preprocessed AnnData; if absent… → Validate the matrix contract and… → For Scanpy paths: run rank_genes_groups… → …
Tasks that involve Bioinformatics
SKILL.md covers When to use, Inputs & Outputs, Flow and Gotchas, plus 2 more sections
Runs Python and R scripts from its folder; calls python

What it does

Spatial De is an agent skill from TianGzlab/OmicsClaw. Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics. Skip when the data is single-cell (use sc-de); bulk (use bulkrna-de); spatially variable expression discovery (use spatial-genes).

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `r_visualization/README.md`, `references/methodology.md` and `references/output_contract.md`).

It sits in Research & Science, covering Bioinformatics. It works with AnnData and Scanpy. 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 MIT.

When your agent uses it

Tasks that involve Bioinformatics

Example prompts

“/spatial-de”

Requirements

Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Load the preprocessed AnnData; if absent and not --demo, run spatial-preprocess first (raises RuntimeError at spatial_de.py:1370 if…
Validate the matrix contract and method-specific arguments (Scanpy methods need X = log_normalized; pydeseq2 needs counts).
For Scanpy paths: run rank_genes_groups and (default-on) the official filter_rank_genes_groups post-filter.
For pydeseq2: pseudobulk by sample_key × group, drop bins below --min-cells-per-sample / --min-counts-per-gene, fit PyDESeq2 GLM. If the…
Render the recipe-driven standard gallery.
Write processed.h5ad, tables, figure_data/manifest.json, report.md, result.json, and reproducibility script.

What it can do on your machine

Read from SKILL.md and the folder at commit 6fbd79f. 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 and R), 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

Spatial De loads about 1.7k tokens when it runs, and up to ~5.9k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 568 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~61
When it runs · the whole SKILL.md, loaded when a task matches: ~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~5.9k

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 6fbd79f, republished under its MIT licence (© TianGzlab). 568 words, ~1,716 tokens.

Download SKILL.mdSave it as .claude/skills/spatial-de/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.

name: spatial-de
description: Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics. Skip when the data is single-cell (use sc-de); bulk (use bulkrna-de); spatially variable expression discovery (use spatial-genes).
version: 0.5.0
author: OmicsClaw Team
license: MIT
emoji: 🧬
tags: spatial, differential-expression, markers, wilcoxon, t-test, pydeseq2, pseudobulk
requires: anndata, matplotlib, numpy, pandas, pydeseq2, scanpy, scipy, seaborn

spatial-de

When to use

The user has a preprocessed spatial transcriptomics AnnData (Visium / Xenium / MERFISH / Slide-seq) and wants either (a) cluster-marker ranking via Scanpy wilcoxon / t-test, or (b) replicate-aware two-group condition DE via pydeseq2 pseudobulk. The wrapper exposes the official Scanpy filter controls and PyDESeq2 GLM controls directly, and refuses to fabricate replicates — pseudobulk requires a real sample_key.

Inputs & Outputs

<!-- AUTO-GENERATED from skill.yaml (interface) — do not edit by hand. Regenerate: python scripts/generate_skill_md.py <skill_dir> -->

Inputs

File types: .h5ad
Requires a preprocessed AnnData (X normalised, PCA/neighbours present)

Outputs

tables/de_full.csv
tables/de_plot_points.csv
tables/de_run_summary.csv
tables/de_significant.csv
tables/de_spatial_points.csv
tables/de_umap_points.csv
tables/group_de_metrics.csv
tables/markers_top.csv
tables/sample_counts_by_group.csv
tables/skipped_sample_groups.csv
tables/top_de_hits.csv
figures/de_effect_burden_spatial.png
figures/de_effect_burden_umap.png
figures/de_group_spatial_context.png
figures/de_marker_dotplot.png
figures/de_marker_heatmap.png
figures/de_pvalue_distribution.png
figures/de_top_hits_barplot.png
figures/de_volcano.png
figures/group_de_burden.png
figures/sample_counts_by_group.png
figures/skipped_sample_groups.png
processed.h5ad
report.md
result.json
Processed AnnData (saves_h5ad)

Flow

Load the preprocessed AnnData; if absent and not --demo, run spatial-preprocess first (raises RuntimeError at spatial_de.py:1370 if upstream script missing).
Validate the matrix contract and method-specific arguments (Scanpy methods need X = log_normalized; pydeseq2 needs counts).
For Scanpy paths: run rank_genes_groups and (default-on) the official filter_rank_genes_groups post-filter.
For pydeseq2: pseudobulk by sample_key × group, drop bins below --min-cells-per-sample / --min-counts-per-gene, fit PyDESeq2 GLM. If the same biological sample is in both groups, auto-switch to paired design ~ sample_id + condition.
Render the recipe-driven standard gallery.
Write processed.h5ad, tables, figure_data/manifest.json, report.md, result.json, and reproducibility script.

Gotchas

pydeseq2 requires --sample-key distinct from --groupby. Hard-fails at spatial_de.py:1455 with "--sample-key and --groupby must be different for pydeseq2". Default sample_key is sample_id; if the user's grouping column happens to be the same name, swap one.
pydeseq2 requires explicit --group1 and --group2. Hard-fails at spatial_de.py:1458 (the --demo path bypasses this by picking the first two groups it finds). Other methods treat them as optional (cluster-vs-rest if absent).
Counts-layer fallback to adata.X is logged but not blocked. When pydeseq2 cannot find layers["counts"] or adata.raw, spatial_de.py:1684-1686 falls through to adata.X with a warning that says verbatim "If adata.X is log-normalized, pseudobulk DE will be statistically invalid." Verify result.json["summary"]["expression_source"] after every pseudobulk run; do not assume the warning blocked the run.
Paired design auto-activates when ≥2 samples each contribute to both groups (with ≥2 cells per side). Per skills/spatial/_lib/de.py:485-506 (_choose_pydeseq2_design): the wrapper switches the DESeq2 formula to ~ sample_id + condition only when at least 2 distinct sample_id values appear in both groups AND each side of the resulting paired split retains ≥2 cells; otherwise it stays unpaired (~ condition). Check result.json["summary"]["paired_design"] (also surfaced at spatial_de.py:454); if the run was unintentionally paired (e.g. the user merged samples by accident), the LFC interpretation changes.
Skipped sample-group bins ARE surfaced (unlike sc-de's silent drops). The full reason list lives in result.json's skipped-sample summary (each row carries sample_id, condition, reason, n_cells per spatial_de.py:1198). When pydeseq2 reports few DEGs, inspect this list before assuming biological null.
Scanpy filter_markers is cluster-style only. The --filter-markers post-filter (default on) enforces the min_in_group_fraction / min_fold_change / max_out_group_fraction triplet from scanpy.tl.filter_rank_genes_groups — appropriate for cluster markers, but for a --group1 vs --group2 contrast it can drop genuine effect genes whose between-condition cell coverage is low. Pass --no-filter-markers for two-group condition comparisons.

Show full SKILL.md (88 more words)Show less

Key CLI

bash

# Demo: 200-spot synthetic Visium with three domains
python omicsclaw.py run spatial-de --demo

# Default exploratory cluster-marker discovery
python omicsclaw.py run spatial-de \
  --input processed.h5ad --output results/ \
  --groupby leiden --method wilcoxon

# Replicate-aware condition contrast via PyDESeq2 pseudobulk
python omicsclaw.py run spatial-de \
  --input processed.h5ad --output results/ \
  --method pydeseq2 --groupby condition \
  --group1 treated --group2 control \
  --sample-key sample_id \
  --min-cells-per-sample 10 --min-counts-per-gene 10

Files

SKILL.md and 10 other files (references) in skills/spatial/spatial-de of TianGzlab/OmicsClaw.

SKILL.md
r_visualization/README.md
r_visualization/de_publication_template.R
references/methodology.md
references/output_contract.md
references/parameters.md
references/r_visualization.md
skill.yaml
spatial_de.py
tests/__init__.py
tests/test_spatial_de.py

Open the folder on GitHubat commit 6fbd79f

Compare with similar skills

Spatial De 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.

Spatial De compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Spatial De this skillTianGzlab/OmicsClaw	161	—	~1.7k	Automated safety check: Pass	MIT	2 mo ago
Scanpy Single-Cell Analysisdavila7/claude-code-templates	32k	16 repos	~2.8k	Automated safety check: Pass	MIT	today
Anndatadavila7/claude-code-templates	32k	12 repos	~2.5k	Automated safety check: Pass	MIT	today
ScanpyK-Dense-AI/scientific-agent-skills	48k	1 repos	~5.1k	Automated safety check: Pass	BSD-3-Clause	2 days ago
Cellxgene CensusK-Dense-AI/scientific-agent-skills	48k	1 repos	~3.4k	Automated safety check: Notes	MIT	2 days ago
Omics ToolsDrugClaw/DrugClaw	125	—	~1.1k	Automated safety check: Pass	Apache-2.0	6 mo ago

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 16 repos~2.8k tokens
Research & ScienceAuto-check passed
Anndata
davila7/claude-code-templates
This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental measurements with metadata, or handling…
32k GitHub starsUsed in 12 repos~2.5k tokens
Research & ScienceAuto-check passed
Scanpy
K-Dense-AI/scientific-agent-skills
Performs Scanpy single-cell RNA-seq QC, normalization, HVG selection, PCA/UMAP/t-SNE, clustering, exploratory marker ranking, pseudobulk preparation, visualization, and Seurat or…
48k GitHub starsUsed in 1 repo~5.1k tokens
Research & ScienceAuto-check passed
Cellxgene Census
K-Dense-AI/scientific-agent-skills
Queries the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data.
48k GitHub starsUsed in 1 repo~3.4k tokens
Research & ScienceAuto-check: notes
Omics Tools
DrugClaw/DrugClaw
Omics and single-cell workflow guide for AnnData, Scanpy-style dataset profiling, PyDESeq2-oriented count checks, pysam alignment inspection, and pyOpenMS mass-spectrometry summaries.
125 GitHub stars~1.1k tokensUpdated 6 mo ago
Research & ScienceAuto-check passed
Anndata Data Structure
jaechang-hits/SciAgent-Skills
Annotated matrices for single-cell genomics. An agent skill from jaechang-hits/SciAgent-Skills.
370 GitHub starsUsed in 2 repos~5.8k tokens
Research & ScienceAuto-check passed

Questions about Spatial De

What does Spatial De do?

Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics. Spatial De is an agent skill from TianGzlab/OmicsClaw. Load when ranking spatial cluster markers or comparing two spatial groups in spatial transcriptomics.

When should I use Spatial De?

Spatial De fits situations like: tasks that involve Bioinformatics.

How do I install Spatial De in Claude Code?

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

How do I install Spatial De in Codex?

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

Can I use Spatial De 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 spatial-de -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spatial-de, .gemini/skills/spatial-de, .github/skills/spatial-de and .opencode/skills/spatial-de in your project.

What does Spatial De need to run?

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

Does Spatial De 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 Spatial De 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 Spatial De use?

Spatial De is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Spatial De use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 4.2k tokens, read only when the agent opens those files.

What are the alternatives to Spatial De?

Skills that share tags, products or a category with Spatial De: Scanpy Single-Cell Analysis (davila7/claude-code-templates, 32k stars), Anndata (davila7/claude-code-templates, 32k stars), Scanpy (K-Dense-AI/scientific-agent-skills, 48k stars) and Cellxgene Census (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Spatial De?

TianGzlab (a GitHub organization) maintains it in TianGzlab/OmicsClaw, which has 161 GitHub stars. The repository holds 95 skills in this directory. The repository was last updated on July 28, 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.

Install Spatial De

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

spatial-de

When to use

Inputs & Outputs

Flow

Gotchas

Key CLI

See also

Files

Compare with similar skills

Similar skills

More from TianGzlab/OmicsClaw

Related

Questions about Spatial De