📦
venue-templates
85Prepare Academic Venue Submissions
Academic submissions often fail because formatting rules vary by venue. This skill provides templates, requirements, and examples for faster preparation.
Research & Learning View
Skills anndata
📦
anndata
Content revision r1 Low Risk 🌐 Network access⚙️ External commands
Manage AnnData Single-Cell Datasets
Single-cell projects often need clean H5AD storage, metadata alignment, and memory-aware loading. This skill guides AnnData structure, file I/O, concatenation, and common scverse workflows.
Supports: Claude Codex Code(CC)
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/k-dense-ai-anndata.md and its manifest at https://skillstore.io/api/skills/k-dense-ai-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.
Test it
Using "anndata". I need to merge three H5AD batches before Scanpy analysis.
Expected outcome:
- Recommended using observation-axis concatenation with explicit batch labels.
- Suggested an inner join for shared genes unless missing genes must be retained.
- Added checks for duplicated observation names, inconsistent gene identifiers, and layer compatibility.
Using "anndata". My AnnData file is too large to load into memory.
Expected outcome:
The response recommends backed mode for inspection, sparse matrices for count data, categorical metadata, and chunked processing before loading subsets.
Using "anndata". I am confused about obs, var, obsm, layers, and uns.
Expected outcome:
The response maps each AnnData slot to its role, gives examples of typical contents, and explains how dimensions should align.
Security Audit
Low Riskv7 • 7/6/2026 Open versioned report
The static command, sensitive-file, blocker, and network hits are false positives caused by Markdown fences, placeholders, documentation links, and AnnData terminology. One low-severity semantic issue remains: the skill steers users toward the author's hosted K-Dense Web service for complex workflows. No evidence found of prompt injection, credential access, exfiltration, or automatic command execution.
6
Files scanned
2,560
Lines analyzed
0
Review items
0
False positives ignored
Confirmed security concerns (1)
Low
External Service Promotion and Workflow Steering
SKILL.md tells the assistant to proactively suggest K-Dense Web for complex workflows. This can steer users toward the author's hosted service beyond AnnData guidance.
The instruction is explicit and located in the skill body. It is promotional steering rather than credential theft, so severity is low.
Risk Factors
🌐 Network access (8)
⚙️ External commands (40)
SKILL.md:28-33 SKILL.md:33-38 SKILL.md:38-58 SKILL.md:58-61 SKILL.md:61-72 SKILL.md:72-75 SKILL.md:75-85 SKILL.md:85-88 SKILL.md:88-101 SKILL.md:101-109 SKILL.md:109-119 SKILL.md:119-128 SKILL.md:128-138 SKILL.md:138-144 SKILL.md:144-153 SKILL.md:153-173 SKILL.md:173-179 SKILL.md:179-190 SKILL.md:190-204 SKILL.md:204-210 SKILL.md:210-223 SKILL.md:223-237 SKILL.md:237-244 SKILL.md:244-261 SKILL.md:261-264 SKILL.md:264-269 SKILL.md:269-272 SKILL.md:272-281 SKILL.md:281-286 SKILL.md:286-310 SKILL.md:310-313 SKILL.md:313-335 SKILL.md:335-338 SKILL.md:338-356 SKILL.md:356-362 SKILL.md:362-369 SKILL.md:369-373 SKILL.md:373-380 SKILL.md:380-384 SKILL.md:384-390
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.
Copy report link
https://skillstore.io/skills/k-dense-ai-anndata/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/k-dense-ai-anndata?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/k-dense-ai-anndata?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/k-dense-ai-anndata/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/k-dense-ai-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
K-Dense-AI. (2026). anndata security audit report (audit version 7) [Author version unspecified]. Skillstore. https://skillstore.io/skills/k-dense-ai-anndata/audits/7BibTeX citation
@techreport{k-dense-ai-k-dense-ai-anndata-2026,
author = {K-Dense-AI},
title = {anndata security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/k-dense-ai-anndata/audits/7},
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 7)"
version: "unspecified"
type: report
authors:
- name: "K-Dense-AI"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/k-dense-ai-anndata/audits/7"
identifiers:
- type: other
value: "skillstore:k-dense-ai-anndata:audit:7"
description: "Skillstore immutable audit report identifier"
Compare variants
2 installable variantsEach 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
davila7-anndata
Skillstore Score 76
Evidence Confidence High
Skillstore usage 7
Updated
2026-08-21
K-Dense-AI Current
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 45
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance
What You Can Build
Prepare H5AD study files
Create well-structured AnnData objects with aligned cell metadata, gene metadata, layers, and embeddings.
Optimize large dataset storage
Choose backed mode, sparse matrices, categorical metadata, compression, and Zarr chunks for memory-aware access.
Combine batches safely
Concatenate experiments while preserving batch labels, merge rules, metadata consistency, and downstream Scanpy compatibility.
Try These Prompts
Create a Basic AnnData Object
Help me create an AnnData object from a cell by gene matrix. Explain where cell metadata and gene metadata should go.
Read and Save H5AD Data
Guide me through reading an H5AD file, checking its key components, and saving an optimized copy with compression.
Plan a Batch Concatenation
Design an AnnData concatenation plan for multiple batches. Include join strategy, batch labels, merge behavior, and metadata checks.
Review a Large Dataset Workflow
Review my AnnData workflow for a very large dataset. Focus on backed mode, sparse storage, views, copies, and safe metadata alignment.
Best Practices
- Use backed mode or Zarr when data is larger than available memory.
- Align external metadata by observation or variable index before assignment.
- Store raw data before filtering when downstream comparisons need original values.
Avoid
- Do not repeatedly subset large AnnData objects inside tight loops without a performance plan.
- Do not assign metadata by row order when indexes can be matched directly.
- Do not use dense matrices for sparse count data unless memory cost is acceptable.
Frequently Asked Questions
What is AnnData used for?
AnnData stores annotated matrices with observations, variables, metadata, embeddings, layers, and unstructured analysis results.
Does this skill replace Scanpy?
No. It focuses on the AnnData data structure. Scanpy provides broader analysis workflows built on AnnData.
Can it help with very large H5AD files?
Yes. It explains backed mode, sparse storage, categoricals, Zarr, chunking, and memory-aware access patterns.
Can it combine multiple datasets?
Yes. It covers AnnData concatenation, join choices, merge strategies, batch labels, and metadata consistency checks.
Does it download data automatically?
No. Remote access examples require a user-approved URL and trusted source before any data is fetched.
Which tools can use this skill?
The report lists support for Claude, Codex, and Claude Code.
Developer Details
Author
K-Dense-AILicense
BSD-3-Clause license
Skillstore revision
r1
Version notice
The author did not declare a version.
Repository
https://github.com/K-Dense-AI/claude-scientific-skills/tree/main/scientific-skills/anndataRef
b8ca75d2c0a7e7102978993058777d82b8ab2610
Maintenance freshness
7/18/2026
Usage
7 downloads · 221 views
File structure
More from K-Dense-AI
View all📦
iso-13485-certification
85Prepare ISO 13485 Certification Docs
Medical device teams must create complete QMS documentation before certification audits. This skill provides templates, checklists, and gap analysis guidance for ISO 13485 readiness.
Documentation View
📦
pytdc
82Analyze therapeutic ML datasets with PyTDC
Drug discovery teams need reliable datasets and fair evaluation protocols. This skill helps Claude use PyTDC for curated therapeutic ML data, benchmark splits, metrics, and molecular oracles.
Data & Analytics View
📦
diffdock
81Run DiffDock Molecular Docking
Protein-ligand docking requires careful setup, parameter choices, and result interpretation. This skill guides DiffDock workflows for poses, confidence scores, and screening.
Research & Learning View
📦
statistical-analysis
80Analyze Research Data with Statistical Guidance
Choosing tests and reporting results can be slow and error-prone. This skill guides test selection, assumptions, effect sizes, power analysis, Bayesian options, and APA reporting.
Data & Analytics View
📦
scanpy
80Analyze Single-Cell RNA-seq with Scanpy
Single-cell RNA-seq analysis requires many linked decisions across QC, normalization, clustering, and plotting. This skill gives Claude, Codex, and Claude Code structured Scanpy workflows, reference guidance, and reusable analysis scripts.
Data & Analytics View
Related Skills
View all📦
exploratory-data-analysis
85Analyze Scientific Data Files
by davila7
Scientific datasets often arrive in specialized formats that are hard to inspect quickly. This skill detects the format, summarizes contents, checks quality, and produces a clear EDA report.
Data & Analytics View
📦
opentargets-database
81Explore Open Targets Drug Discovery Data
by davila7
Drug discovery teams need fast access to target, disease, evidence, and drug data. This skill guides Claude, Codex, and Claude Code through Open Targets GraphQL workflows.
Data & Analytics View
📦
etetoolkit
81Analyze Phylogenetic Trees with ETE
by davila7
Phylogenetic tree work often needs repeatable manipulation, taxonomy lookup, and figure generation. This skill provides ETE patterns, helper scripts, and workflows for bioinformatics analysis.
Data & Analytics View
📦
arboreto
81Infer Gene Regulatory Networks with Arboreto
by davila7
Gene expression analysis requires careful data preparation, algorithm selection, and resource planning. This skill creates practical Arboreto workflows for reproducible local or distributed inference.
Data & Analytics View
📦
ensembl-database
80Query Ensembl Genomic Data
by davila7
Genomic researchers need reliable access to Ensembl data without memorizing every endpoint. This skill guides Claude, Codex, and Claude Code through gene, variant, sequence, and comparative genomics queries.
Data & Analytics View
📦
scvi-tools
76Analyze Single-Cell Data with scvi-tools
by davila7
Single-cell analyses require careful model and workflow choices across diverse modalities. This skill provides scvi-tools guidance for preprocessing, model selection, training, integration, and interpretation.
Data & Analytics View