sc-markers

sc-markers is a skill for Claude Code, Codex from TianGzlab/OmicsClaw. It costs 61 tokens per session (1,350 once invoked), scanned C, original, Apache-2.0.

A tool that ranks genes that distinguish each existing cell cluster or cell-type group. These marker genes provide evidence for understanding what each group represents.

In plain words
What is it for?
Finding marker genes for clusters or labelled cell groups using statistical tests or specificity scoring.
Why use it?
It turns clustered single-cell data into an ordered list of characteristic genes, without requiring you to inspect every gene manually.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tiangzlab/omicsclaw/sc-markers
Any agent
npx skills add TianGzlab/OmicsClaw --skill sc-markers
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 sc-markers

README.md
[![agentmods](https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-markers.svg)](https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-markers)
Your own site
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-markers"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-markers.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,350 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00061 $0.01350
Opus 5 $0.00030 $0.00675
Sonnet 5 $0.00012 $0.00270
Haiku 4.5 $0.00006 $0.00135

Measured 2d ago against content hash 42658b2004b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

sc-markers scanned grade C with 1 finding 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 2d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (sc_markers.py, tests/test_sc_markers.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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

- **`--mu` is `cosg`-only.** `sc_markers.py:373` sets `result.json["mu"] = args.mu if method == 'cosg' else None`. Passing `--mu` with another method silently records `None`.
skills/singlecell/scrna/sc-markers/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sc-markers

When to use

The user already has clustering / cell-type labels in obs (typically leiden, louvain, or cell_type) and wants ranked marker genes per group as evidence for downstream annotation or interpretation. Four methods: wilcoxon (default rank-sum), t-test (Welch), logreg (multinomial logistic regression — discriminative ranking), cosg (fast cosine-specificity scoring without p-values). This is for cluster markers, not condition contrasts — for treatment-vs-control DE with replicates use sc-de.

Inputs & Outputs

Inputs

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

Outputs

  • tables/cell_metadata.csv
  • tables/cluster_summary.csv
  • tables/markers_all.csv
  • tables/markers_top.csv
  • figures/r_feature_violin.png
  • figures/r_marker_heatmap.png
  • analysis_summary.txt
  • processed.h5ad
  • report.md
  • result.json
  • Processed AnnData (saves_h5ad)

Flow

  1. Load AnnData; resolve --groupby (auto-detect from leiden / louvain / cell_type if unset).
  2. Validate parameters (n_top ≥ 1, fractions in [0, 1], mu in [0, 1]).
  3. Run the selected ranker against adata.X (treated as normalised expression).
  4. Apply post-filters (--min-in-group-fraction, --min-fold-change, --max-out-group-fraction).
  5. Build top-N table, per-cluster summary, and figure-data CSVs.
  6. Save processed.h5ad (with rank_genes_groups* purged from uns), tables/, figures/, report.md, result.json.

Gotchas

  • --groupby auto-detection requires a recognised column. sc_markers.py:135 raises ValueError("Grouping column '...' not found in adata.obs") for an explicit-but-missing key; :137 raises ValueError('No cluster/cell-type grouping column available for marker discovery.') when nothing among leiden / louvain / cell_type exists. Run sc-clustering first or pass --groupby <real-obs-column>.
  • cosg returns no p-values. sc_markers.py:91-94 registers cosg as a cosine-similarity specificity scorer — tables/markers_all.csv will lack pvals / pvals_adj columns. Downstream filters that branch on adjusted p-value must handle the method == cosg case.
  • --mu is cosg-only. sc_markers.py:373 sets result.json["mu"] = args.mu if method == 'cosg' else None. Passing --mu with another method silently records None.
  • adata.X is treated as normalised expression with no guard. sc_markers.py sets expression_source = 'adata.X' without verifying .X is log-normalised. If .X still holds raw counts (e.g., the user skipped sc-preprocessing), the Wilcoxon / t-test runs on counts and the rankings are unreliable.
  • --input is mandatory unless --demo. sc_markers.py:316 raises ValueError('--input required when not using --demo').

Read the full file on GitHub · 111 lines

Files

What ships with it

7 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. 2d ago First seen · 111 lines · 61 tokens per session scan C 42658b2004b6

Subscribe to this mod's changes

sc-markers is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,350 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

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 Analysis Skills Index

Core skills for single-cell RNA-seq analysis: quality control, cell type annotation, and trajectory inference. These are high-priority actionable workflows — load them first for common single-cell tasks.

aristoteleo/PantheonOS · 48 tokens

spatial-de

Differential expression analysis — find marker genes for clusters or compare two groups. Supports Wilcoxon rank-sum, t-test, and PyDESeq2 methods with publication-ready figures and CSV tables.

ShangBioLab/SpatialClaw · 44 tokens

uniprot

Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence…

zongtingwei/Bioclaw_Skills_Hub · 79 tokens

uniprot

Access UniProt for protein sequence and annotation retrieval. Use this skill when: (1) Looking up protein sequences by accession, (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence…

BioTender-max/awesome-bio-agent-skills · 79 tokens

differential_expression_helper

Interpret a differential expression result with replicate-aware context, likely confounders, and the next analysis decision.

Azealoo/miniAgent · 27 tokens