spacy-ner

spaCy NER model training and entity extraction for conversational AI

509 stars

bya5c-ai

View on GitHub Installation ↓

Best use case

spacy-ner is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

spaCy NER model training and entity extraction for conversational AI

Teams using spacy-ner 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

$curl -o ~/.claude/skills/spacy-ner/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/ai-agents-conversational/skills/spacy-ner/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/spacy-ner/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How spacy-ner Compares

Feature / Agent	spacy-ner	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?

spaCy NER model training and entity extraction for conversational AI

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

# spaCy NER Skill

## Capabilities

- Train custom spaCy NER models
- Configure entity extraction pipelines
- Design annotation schemas
- Implement entity linking
- Set up model evaluation
- Deploy efficient NER inference

## Target Processes

- entity-extraction-slot-filling
- chatbot-design-implementation

## Implementation Details

### spaCy Components

1. **NER**: Named Entity Recognition
2. **EntityLinker**: Link to knowledge bases
3. **EntityRuler**: Rule-based matching
4. **SpanCategorizer**: Overlapping entities

### Training Configuration

- config.cfg setup
- Training data format (spaCy v3)
- Augmentation strategies
- Evaluation metrics

### Configuration Options

- Base model selection (en_core_web_*)
- Custom entity types
- Training parameters
- GPU acceleration
- Model packaging

### Best Practices

- Quality annotation data
- Balance entity types
- Use prodigy for annotation
- Regular model evaluation

### Dependencies

- spacy
- spacy-transformers (optional)

Related Skills

process-builder

509

from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity

babysitter

509

from a5c-ai/babysitter

Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)