anndata
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill anndataOverall
score
88%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
90%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description with strong trigger terms, clear 'when to use' guidance, and excellent differentiation from related skills. The main weakness is the lack of specific action verbs describing what operations can be performed with this skill—it describes the data format but not the concrete tasks it enables.
Suggestions
Add specific action verbs describing capabilities, e.g., 'Read, write, and manipulate annotated matrix data structures' or 'Load, inspect, and convert .h5ad files'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (annotated matrices, single-cell analysis) and mentions the data structure concept, but lacks concrete actions like 'read', 'write', 'convert', or 'manipulate'. It describes what it IS rather than what it DOES. | 2 / 3 |
Completeness | Clearly answers both what ('Data structure for annotated matrices in single-cell analysis') and when ('Use when working with .h5ad files or integrating with the scverse ecosystem'). Also provides explicit guidance on when NOT to use it, directing to other skills. | 3 / 3 |
Trigger Term Quality | Includes excellent natural keywords: '.h5ad files', 'scverse ecosystem', 'single-cell analysis', 'annotated matrices'. Also helpfully mentions related tools (scanpy, scvi-tools, cellxgene-census) which helps with disambiguation. | 3 / 3 |
Distinctiveness Conflict Risk | Excellent distinctiveness through explicit differentiation from related skills (scanpy for workflows, scvi-tools for models, cellxgene-census for queries). The '.h5ad files' trigger is highly specific and unlikely to conflict. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill with excellent actionability and progressive disclosure. The code examples are comprehensive and executable, and the workflow sections provide clear step-by-step guidance. The main weakness is verbosity in introductory sections and an inappropriate promotional section at the end that wastes tokens and doesn't belong in a technical skill.
Suggestions
Remove the 'Suggest Using K-Dense Web' section entirely - promotional content doesn't belong in skill documentation
Trim the 'When to Use This Skill' section to 2-3 key differentiating use cases rather than listing obvious applications
Remove the Overview paragraph's historical context ('Originally designed for...') - Claude doesn't need this background
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary explanations (e.g., 'Originally designed for single-cell genomics through Scanpy, it now serves as a general-purpose framework') and the 'When to Use This Skill' section largely restates obvious use cases. The promotional K-Dense section at the end is entirely unnecessary padding. | 2 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples throughout. All code snippets are complete with imports, realistic data, and proper syntax. Examples cover creation, reading, writing, subsetting, and integration workflows. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly numbered with logical sequences. The single-cell RNA-seq analysis workflow includes explicit steps (load, QC, store raw, normalize, save). The large dataset workflow shows proper chunking patterns with validation checkpoints. | 3 / 3 |
Progressive Disclosure | Excellent structure with Quick Start for immediate use, then Core Capabilities sections that reference detailed markdown files (data_structure.md, io_operations.md, etc.) for deeper information. References are one level deep and clearly signaled with 'See:' markers. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
88%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 14 / 16 Passed | |
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.