agentmods.dev

scatac-preprocessing

scatac-preprocessing is a skill for Claude Code, Codex from TianGzlab/OmicsClaw. It costs 63 tokens per session (2,053 once invoked), scanned A, original, Apache-2.0.

A tool for processing a single-cell ATAC-seq dataset, where ATAC-seq measures which parts of DNA are accessible in individual cells. It applies standard transformations, reduces the data to a few dimensions, groups similar cells, and prepares UMAP results.

In plain words
What is it for?
Use it with a peak-by-cell AnnData file to produce cell metadata, clusters, UMAP coordinates, quality metrics, and a processed dataset.
Why use it?
It combines common preprocessing steps so accessibility data can be explored as cell groups without running each step separately.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 161repo changed 14d ago A scan SkillSpector: warn 63 tokens original Apache-2.0

Good fit Use it with a peak-by-cell AnnData file to produce cell metadata, clusters, UMAP coordinates, quality metrics, and a processed dataset.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tiangzlab/omicsclaw/scatac-preprocessing
View source ↗ TianGzlab/OmicsClaw tiangzlab.github.io
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add TianGzlab/OmicsClaw --skill scatac-preprocessing
Clone the repo
git clone --depth 1 https://github.com/TianGzlab/OmicsClaw

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for scatac-preprocessing

README.md
[![agentmods](https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/scatac-preprocessing/github.svg)](https://agentmods.dev/skills/tiangzlab/omicsclaw/scatac-preprocessing)
Your own site
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/scatac-preprocessing"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/scatac-preprocessing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for scatac-preprocessing

Your own site · 80×15
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/scatac-preprocessing"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/scatac-preprocessing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,053 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 3
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.02053
Opus 5.5 $0.00025 $0.00821
Sonnet 5.5 $0.00013 $0.00411
Haiku 4.5 $0.00006 $0.00205

Measured 14d ago against content hash 626b1b624b38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scatac-preprocessing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (_api.py, examples/example_step.py, scatac_preprocessing.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/singlecell/scatac/scatac-preprocessing/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

scatac-preprocessing

Use from a step

from skills._sdk.notebook import load_skill, read_input, write_output

atac = load_skill("scatac-preprocessing")
adata = read_input("data/peaks.h5", reader=atac.read_10x_peaks)
adata = atac.preprocess(adata, random_state=0)
write_output(adata, "intermediate/accessibility.h5ad")
write_output(atac.cluster_summary(adata), "tables/clusters.csv")

For H5AD use read_input without a reader. The API returns a copy and does not write files. examples/example_step.py recovers three planted groups from load_demo("atac_synthetic"); that tests computation, not biological validity.

When to use

The user has a cell × peak scATAC AnnData (raw-count-like accessibility matrix in .X) and wants the standard "filter → TF-IDF → LSI → graph → UMAP → Leiden" pipeline in one shot. Currently a single backend: tfidf_lsi (Signac-style). The skill stops at clustered UMAP — no fragment QC, no peak calling, no motif / gene-activity scoring, no multi-sample integration. For scRNA preprocessing use sc-preprocessing.

Inputs & Outputs

Inputs

  • Input kinds: file, directory
  • Modalities: scatac
  • File types: .h5ad, .h5, .loom, .csv, .tsv

Outputs

  • tables/cluster_summary.csv
  • tables/lsi_variance_ratio.csv
  • tables/peak_summary.csv
  • tables/preprocess_summary.csv
  • tables/qc_metrics_per_cell.csv
  • tables/umap_points.csv
  • figures/umap_leiden.png
  • figures/lsi_variance.png
  • figures/qc_violin.png
  • figures/top_accessible_peaks.png
  • processed.h5ad
  • report.md
  • result.json
  • figures/manifest.json, figure_data/manifest.json, plot-data CSV files
  • reproducibility/commands.sh, reproducibility/requirements.txt
  • Processed AnnData (saves_h5ad) — adds obs: leiden; obsm: X_lsi, X_umap; layers: counts
  • AnnData processing state after success: preprocessed

Flow

  1. Read cell × peak counts. The 10x reader uses gex_only=False and keeps Peaks in multiome inputs; other CLI formats use smart_load.
  2. Validate .X is present, non-empty, non-negative.
  3. Compute per-cell n_peaks_by_counts / total_counts; filter cells by --min-peaks and peaks by --min-cells.
  4. Retain the globally most accessible peaks up to --n-top-peaks.
  5. Run Signac-style TF-IDF (--tfidf-scale-factor); truncated-SVD LSI to --n-lsi components.
  6. Build neighbour graph (--n-neighbors), UMAP, Leiden (--leiden-resolution).
  7. Save processed.h5ad, tables, figures, report.md, result.json.

Read the full file on GitHub · 175 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 14d ago Changed · +51 lines 626b1b624b38
  2. 1mo ago First seen · 124 lines · 63 tokens per session scan A b73ed231996e

Subscribe to this mod's changes

scatac-preprocessing is a skill published in the GitHub repository TianGzlab/OmicsClaw (161 stars, last pushed 14d ago), licensed Apache-2.0. It adds 63 tokens to every session and 2,053 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

ATACClusteringScientificbioinformaticsknowledge-graphleidenllm-agentlsimulti-agentspreprocessingscatacsinglecelltfidf
Related

Other skills, from other repositories

scanpy

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…

synthetic-sciences/openscience · 68 tokens

Virtual Embryo — atlas data + knowledge graph

Query the Virtual Embryo knowledge graph (mouse/human developmental biology: genes, anatomy, Theiler/Carnegie stages, gene expression, diseases, papers) and its 3D atlas catalog (anatomical OPT/light-sheet volumes + 3D spatial- transcriptomics datasets), and visualise those datasets in 3D with the volume3d / spatial3d…

aristoteleo/PantheonOS · 170 tokens

single-cell-scrna-seq-analysis-scanpy

Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type…

PharMolix/OpenBioMed · 85 tokens

spatial-domain-identification

Identify tissue regions and spatial niches from preprocessed spatial transcriptomics data using Leiden, Louvain, SpaGCN, STAGATE, GraphST, or BANKSY.

ShangBioLab/SpatialClaw · 40 tokens

spatial-preprocessing

Load spatial transcriptomics data (Visium, Xenium, MERFISH, Slide-seq, generic h5ad), perform QC filtering, normalization, HVG selection, PCA, UMAP, and Leiden clustering.

ShangBioLab/SpatialClaw · 49 tokens

neuropixels-analysis

Analyzes Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when…

K-Dense-AI/scientific-agent-skills · 99 tokens