Skills anndata

📦

anndata

Name: anndata
Author: davila7

Content revision r2 Safe 🌐 Network access⚙️ External commands

Analyze Annotated Data with AnnData

Annotated biological matrices are complex to build, combine, and store efficiently. This skill provides practical AnnData patterns for reliable Python workflows.

Supports: Claude Codex Code(CC)

📊 76 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "anndata" from https://skillstore.io/skills/davila7-anndata.md and its manifest at https://skillstore.io/api/skills/davila7-anndata/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/davila7-anndata.md Signed manifest GET /api/skills/davila7-anndata/manifest Signed lockfile GET /api/skills/davila7-anndata/lockfile

Test it

Using "anndata". How should I load a 100 GB h5ad file for metadata filtering?

Expected outcome:

Open the file in read-only backed mode, filter observations through metadata, then load only the required subset into memory.

Using "anndata". How can I combine three batches without losing their origin?

Expected outcome:

Concatenate along observations.
Add a batch label with one key per source.
Choose inner or outer joins based on gene coverage.
Check index uniqueness before writing.

Using "anndata". My cell metadata appears in the wrong rows after assignment.

Expected outcome:

Index the external table by cell identifier, align it to observation names, verify missing values, then assign the aligned column.

Security Audit

Safe

v9 • 7/23/2026 Open versioned report

All 60 static alerts are false positives caused by Markdown syntax, ordinary AnnData terminology, or explicit documentation examples. No hidden execution, credential access, reconnaissance, malicious network behavior, or prompt injection was found.

Files scanned

2,555

Lines analyzed

Review items

False positives ignored

Risk Factors

🌐 Network access (8)

references/io_operations.md:292 references/io_operations.md:293 references/io_operations.md:83 references/io_operations.md:288 SKILL.md:391 SKILL.md:392 SKILL.md:393 SKILL.md:394

⚙️ External commands (40)

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/davila7-anndata/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/davila7-anndata/security.svg)](https://skillstore.io/skills/davila7-anndata?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/davila7-anndata?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/davila7-anndata/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/davila7-anndata.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

davila7. (2026). anndata security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/davila7-anndata/audits/9

BibTeX citation

@techreport{davila7-davila7-anndata-2026,
  author = {davila7},
  title = {anndata security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/davila7-anndata/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "anndata security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "davila7"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/davila7-anndata/audits/9"
identifiers:
  - type: other
    value: "skillstore:davila7-anndata:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

davila7 Recommended Current

davila7-anndata

Skillstore Score 76

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

K-Dense-AI

k-dense-ai-anndata

Skillstore Score 72

Evidence Confidence High

Skillstore usage 9

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Build a single-cell data object

Organize count matrices, cell annotations, and gene metadata into a correctly indexed AnnData object.

Combine experimental batches

Merge multiple h5ad datasets while preserving batch labels and selecting appropriate join and merge strategies.

Optimize large dataset storage

Choose backed mode, sparse matrices, compression, Zarr chunks, or lazy access for limited-memory workflows.

Try These Prompts

Create an AnnData object

Show how to create an AnnData object from my matrix, cell metadata, and gene metadata. Explain required index alignment.

Read and inspect h5ad

Help me read [file.h5ad], inspect its dimensions and annotations, and choose memory-safe access for a [size] dataset.

Concatenate study batches

Design an AnnData concatenation workflow for [batch files]. Preserve source labels, compare join options, and flag metadata alignment risks.

Plan a scalable pipeline

Propose a memory-efficient AnnData pipeline for [dataset description]. Cover sparse storage, backed or lazy access, chunking, validation, and reproducible outputs.

Best Practices

Keep observation and variable indices unique, stable, and aligned before assignment or concatenation.
Use sparse matrices, categoricals, backed mode, or lazy access when dataset size exceeds available memory.
Preserve raw measurements and record processing parameters before filtering or transformation.

Avoid

Do not densify sparse matrices without estimating the resulting memory requirement.
Do not assign metadata by row position when identifiers can provide explicit alignment.
Do not use outer concatenation without reviewing missing variables and fill behavior.

Frequently Asked Questions

What data does AnnData store?

AnnData stores a primary matrix with observation metadata, variable metadata, layers, embeddings, pairwise annotations, unstructured values, and optional raw data.

Which file format should I choose?

Use h5ad for common local workflows. Consider Zarr for cloud storage, parallel access, or workflows that benefit from configurable chunks.

Can this skill handle datasets larger than memory?

It explains backed mode, lazy reads, sparse storage, chunking, and selective loading. Actual feasibility depends on operations, formats, and available resources.

Does this skill perform single-cell analysis?

It provides AnnData and Scanpy workflow guidance. It does not execute analysis or replace biological validation.

How should I combine multiple batches?

Concatenate observations, preserve a source label, select inner or outer joins deliberately, and verify index and metadata consistency.

Can it access remote datasets?

It documents remote Zarr access and URL downloads. Use trusted sources, verify downloaded data, and follow local network policies.