agentmods.dev

sc-standardize-input

sc-standardize-input is a skill for Claude Code, Codex from TianGzlab/OmicsClaw. It costs 73 tokens per session (1,055 once invoked), scanned A, original, Apache-2.0.

A workflow for converting an external single-cell expression file into the standard AnnData format expected by downstream analyses. AnnData is a structured file format for storing expression matrices together with cell and gene information.

In plain words
What is it for?
Use it once before single-cell quality control or preprocessing when the data came from outside the system.
Why use it?
It handles differences between h5ad, loom, mtx, CSV, and TSV inputs and records the resulting data contract. This prevents later workflows from failing because counts or feature names are stored differently.

Skill for Claude CodeCodex

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

not rated 160repo 1mo ago A scan SkillSpector: warn 73 tokens original Apache-2.0

Good fit Use it once before single-cell quality control or preprocessing when the data came from outside the system.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tiangzlab/omicsclaw/sc-standardize-input
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 sc-standardize-input
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-standardize-input

README.md
[![agentmods](https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-standardize-input/github.svg)](https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-standardize-input)
Your own site
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-standardize-input"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-standardize-input/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 sc-standardize-input

Your own site · 80×15
<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/sc-standardize-input"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/sc-standardize-input.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,055 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 $0.00073 $0.01055
Opus 5 $0.00036 $0.00528
Sonnet 5 $0.00015 $0.00211
Haiku 4.5 $0.00007 $0.00105

Measured 6d ago against content hash e018f34b0d01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sc-standardize-input 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (sc_standardize_input.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/scrna/sc-standardize-input/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sc-standardize-input

When to use

The user has a single-cell expression file from outside OmicsClaw (a public .h5ad, a 10X mtx directory, a .loom, etc.) and needs the canonical AnnData contract every downstream scRNA skill assumes: raw counts in layers["counts"] and adata.raw, harmonised feature names, and a uns["omicsclaw_matrix_contract"] provenance record. Run this once before sc-qc / sc-preprocessing / etc.

Inputs & Outputs

Inputs

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

Outputs

  • tables/cell_metadata.csv
  • analysis_summary.txt
  • processed.h5ad
  • report.md
  • result.json
  • Processed AnnData (saves_h5ad) — adds layers: counts

Flow

  1. Load via the shared multi-format single-cell loader.
  2. Pre-flight: validate non-empty input; auto-detect species from gene name case (UPPER → human, Title → mouse).
  3. Pick the best count-like matrix among layers["counts"], adata.raw, and adata.X (orchestrated by canonicalize_singlecell_adata in skills/singlecell/_lib/adata_utils.py:389, which calls the matrix_looks_count_like heuristic at _lib/adata_utils.py:255).
  4. Harmonise feature names (Ensembl ↔ symbol, deduplicate).
  5. Persist uns["omicsclaw_input_contract"] + uns["omicsclaw_matrix_contract"].
  6. Save processed.h5ad; emit report.md + result.json.

Gotchas

  • --r-enhanced is accepted but produces no R plots. sc_standardize_input.py:250 declares the flag for CLI consistency; this skill is input canonicalisation, not visualisation. Pass it freely, but expect no R Enhanced figures.
  • Count-source selection is heuristic, not declarative. The skill scans layers["counts"] → adata.raw → adata.X and picks the first that passes a matrix_looks_count_like check. If the input is already log-normalised everywhere, the heuristic can mis-classify and fall through to adata.X; verify result.json["summary"]["warnings"] after every run.
  • Species auto-detect is gene-case-based. UPPER-case symbols → human, Title-case → mouse. Non-standard gene-name conventions (Ensembl IDs only, lowercase) silently fall through to the auto default. Pass --species human or --species mouse explicitly when working with non-symbol matrices.
  • No filtering, no normalisation, no clustering. Even if result.json looks complete, the output is still raw counts in canonical form — run sc-qc and sc-preprocessing next.

Read the full file on GitHub · 90 lines

Files

What ships with it

6 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. 6d ago First seen · 90 lines · 73 tokens per session scan A e018f34b0d01

Subscribe to this mod's changes

sc-standardize-input is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,055 once invoked, about $0.0004 per session on Opus 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.

ScientificSingle-Cellanndatabioinformaticsinputknowledge-graphllm-agentmulti-agentsmulti-omicsscrnasinglecellstandardization
Related

Other skills, from other repositories

celltypepilot

Single-cell cell-type annotation with evidence, conservative abstention, and reviewable drafts. Use this whenever the user wants to annotate, label, or identify cell types for pre-clustered single-cell or spatial transcriptomics data (.h5ad), or says things like "annotate my clusters", "what cell types are these?"…

HERRY423/CellTypePilot · 151 tokens

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

cellxgene-census-query

Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…

PharMolix/OpenBioMed · 105 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

single-cell-multi-omics-analysis-scvi

Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…

PharMolix/OpenBioMed · 94 tokens