spatial-data-validation

spatial-data-validation is a skill for Claude Code from Rebell-Leader/SpatialAI_MCP. It costs 54 tokens per session (465 once invoked), scanned A, original, Apache-2.0.

A checking workflow for spatial transcriptomics data, which records gene activity together with tissue locations. It examines SpatialData, Zarr, and AnnData files before analysis.

In plain words
What is it for?
Checking spatial-data files, reading their metadata, distinguishing raw counts from processed values, and deciding whether multiple files can be combined.
Why use it?
It catches wrong file formats, damaged structures, missing locations, unsuitable raw or processed values, and incompatibilities between files before they cause analysis errors.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

Part of the openproblems-spatial plugin — 4 skills, 1 MCP server shipped together

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/rebell-leader/spatialai_mcp/spatial-data-validation
Any agent
npx skills add Rebell-Leader/SpatialAI_MCP --skill spatial-data-validation
Clone the repo
git clone --depth 1 https://github.com/Rebell-Leader/SpatialAI_MCP

Made for: Claude Code.

Or install openproblems-spatial, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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 spatial-data-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/rebell-leader/spatialai_mcp/spatial-data-validation.svg)](https://agentmods.dev/skills/rebell-leader/spatialai_mcp/spatial-data-validation)
Your own site
<a href="https://agentmods.dev/skills/rebell-leader/spatialai_mcp/spatial-data-validation"><img src="https://agentmods.dev/badge/skills/rebell-leader/spatialai_mcp/spatial-data-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00054 $0.00465
Opus 5 $0.00027 $0.00233
Sonnet 5 $0.00011 $0.00093
Haiku 4.5 $0.00005 $0.00047

Measured 6d ago against content hash 5643a94df974, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spatial-data-validation 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.

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.

.agents/skills/spatial-data-validation/SKILL.md · 46 lines

What it actually says

Spatial data validation

Validate first, reason second. Never assume a file's format or contents from its extension.

Steps

  1. Detect & validate format. Call the MCP tool validate_spatial_data with the file path. Choose validation_level:

    • basic — extension/existence only.
    • structure (default) — format + structural integrity.
    • integrity — deeper content checks.
    • domain — spatial-biology-specific expectations. For several files, use validate_multiple_spatial_files.
  2. Read the metadata. Call analyze_spatial_metadata to extract dimensions, spatial coordinates, and gene/feature info. Confirm obsm['spatial'] (AnnData) or coordinate systems (SpatialData) are present when spatial analysis is intended.

  3. Check raw vs. processed. Integer-valued matrices are likely raw counts; non-integer/log-scaled values are processed. State which the downstream method expects and flag a mismatch.

  4. Check compatibility when combining files: check_spatial_data_compatibility (coordinate systems + gene overlap).

Key facts (see context/data-formats.md)

  • A .zarr store is SpatialData only if it has SpatialData markers or ≥2 of images/ labels/ points/ shapes/ tables/. Otherwise it's a plain zarr array.
  • iST datasets can be terabytes. Default to lightweight structural checks; avoid loading whole objects. The heavy scientific stack (pip install -e ".[spatial]") is optional — the validators degrade gracefully without it.

Don't

  • Don't claim a file is valid SpatialData without inspecting contents.
  • Don't call execution tools (e.g. run_nextflow_workflow) — they aren't implemented. Drive local CLIs directly if execution is needed.
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 · 46 lines · 54 tokens per session scan A 5643a94df974

Subscribe to this mod's changes

spatial-data-validation is a skill published in the GitHub repository Rebell-Leader/SpatialAI_MCP (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 465 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

arboreto

Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…

K-Dense-AI/scientific-agent-skills · 66 tokens

pyhealth

Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…

K-Dense-AI/scientific-agent-skills · 216 tokens

torchdrug

Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.

K-Dense-AI/scientific-agent-skills · 61 tokens

deepspot-m

Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…

K-Dense-AI/scientific-agent-skills · 80 tokens

pick-a-pii-model

Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.

maziyarpanahi/openmed · 64 tokens

esm

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…

synthetic-sciences/openscience · 86 tokens