universal-single-cell-annotator
A unified interface for annotating single-cell RNA-seq data using Marker Genes, Deep Learning (CellTypist), or LLMs.
Best use case
universal-single-cell-annotator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
A unified interface for annotating single-cell RNA-seq data using Marker Genes, Deep Learning (CellTypist), or LLMs.
Teams using universal-single-cell-annotator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/universal-single-cell-annotator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How universal-single-cell-annotator Compares
| Feature / Agent | universal-single-cell-annotator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
A unified interface for annotating single-cell RNA-seq data using Marker Genes, Deep Learning (CellTypist), or LLMs.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Universal Single-Cell Annotator
This skill wraps multiple cell type annotation strategies into a single Python class. It allows agents to flexibly choose between rule-based (markers), data-driven (CellTypist), or reasoning-based (LLM) approaches depending on the context.
## When to Use This Skill
* **Initial Analysis**: When processing raw AnnData objects.
* **Validation**: When cross-referencing automated labels with known markers.
* **Discovery**: When identifying rare cell types using LLM reasoning on marker lists.
## Core Capabilities
1. **Marker-Based Scoring**: Scores cells based on provided gene lists (e.g., "T-cell": ["CD3D", "CD3E"]).
2. **Deep Learning Reference**: Wraps `celltypist` to transfer labels from massive atlases.
3. **LLM Reasoning**: Extracts top markers per cluster and constructs prompts for LLM interpretation.
## Workflow
1. **Load Data**: Ensure data is in `AnnData` format (standard for Scanpy).
2. **Choose Strategy**:
* Use **Markers** if you have a known gene panel.
* Use **CellTypist** for broad immune/tissue profiling.
* Use **LLM** for novel clusters.
3. **Annotate**: Run the corresponding method.
4. **Inspect**: Check `adata.obs` for the new annotation columns.
## Example Usage
**User**: "Annotate this dataset looking for T-cells and B-cells."
**Agent Action**:
```python
from universal_annotator import UniversalAnnotator
import scanpy as sc
adata = sc.read_h5ad('data.h5ad')
annotator = UniversalAnnotator(adata)
markers = {
'T-cell': ['CD3D', 'CD3E', 'CD8A'],
'B-cell': ['CD79A', 'MS4A1']
}
annotator.annotate_marker_based(markers)
# Results in adata.obs['predicted_cell_type']
```Related Skills
bio-single-cell-cell-annotation
Automated cell type annotation using reference-based methods including CellTypist, scPred, SingleR, and Azimuth for consistent, reproducible cell labeling.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
moai-lang-r
R 4.4+ best practices with testthat 3.2, lintr 3.2, and data analysis patterns.
moai-lang-python
Python 3.13+ development specialist covering FastAPI, Django, async patterns, data science, testing with pytest, and modern Python features. Use when developing Python APIs, web applications, data pipelines, or writing tests.
moai-icons-vector
Vector icon libraries ecosystem guide covering 10+ major libraries with 200K+ icons, including React Icons (35K+), Lucide (1000+), Tabler Icons (5900+), Iconify (200K+), Heroicons, Phosphor, and Radix Icons with implementation patterns, decision trees, and best practices.
moai-foundation-trust
Complete TRUST 4 principles guide covering Test First, Readable, Unified, Secured. Validation methods, enterprise quality gates, metrics, and November 2025 standards. Enterprise v4.0 with 50+ software quality standards references.
moai-foundation-memory
Persistent memory across sessions using MCP Memory Server for user preferences, project context, and learned patterns
moai-foundation-core
MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
moai-cc-claude-md
Authoring CLAUDE.md Project Instructions. Design project-specific AI guidance, document workflows, define architecture patterns. Use when creating CLAUDE.md files for projects, documenting team standards, or establishing AI collaboration guidelines.
moai-alfred-language-detection
Auto-detects project language and framework from package.json, pyproject.toml, etc.
mnemonic
Unified memory system - aggregates communications and AI sessions across all channels into searchable, analyzable memory
mlops
MLflow, model versioning, experiment tracking, model registry, and production ML systems