rasa-nlu-integration

Rasa NLU pipeline configuration and training for intent and entity extraction

509 stars

Best use case

rasa-nlu-integration is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Rasa NLU pipeline configuration and training for intent and entity extraction

Teams using rasa-nlu-integration 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/rasa-nlu-integration/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/ai-agents-conversational/skills/rasa-nlu-integration/SKILL.md"

Manual Installation

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

How rasa-nlu-integration Compares

Feature / Agent	rasa-nlu-integration	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?

Rasa NLU pipeline configuration and training for intent and entity extraction

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

# Rasa NLU Integration Skill

## Capabilities

- Configure Rasa NLU pipelines
- Design training data in Rasa format
- Set up intent classification components
- Configure entity extraction (DIETClassifier)
- Implement pipeline optimization
- Set up model evaluation and testing

## Target Processes

- intent-classification-system
- chatbot-design-implementation

## Implementation Details

### Pipeline Components

1. **Tokenizers**: WhitespaceTokenizer, SpacyTokenizer
2. **Featurizers**: CountVectorsFeaturizer, SpacyFeaturizer
3. **Classifiers**: DIETClassifier, FallbackClassifier
4. **Entity Extractors**: DIETClassifier, SpacyEntityExtractor

### Configuration Files

- config.yml: Pipeline configuration
- nlu.yml: Training data
- domain.yml: Intents and entities

### Configuration Options

- Pipeline component selection
- Featurizer settings
- Classifier parameters
- Entity extraction rules
- Fallback thresholds

### Best Practices

- Start with recommended pipelines
- Tune based on domain
- Balance complexity vs performance
- Regular model retraining

### Dependencies

- rasa

Related Skills

Debugger Integration Skill

509

from a5c-ai/babysitter

Advanced debugging integration for vulnerability research

ros-integration

509

from a5c-ai/babysitter

Deep integration with ROS/ROS2 middleware for node development, launch files, package management, and robot communication. Execute ros2 commands, create and validate packages, configure publishers/subscribers/services/actions, and debug topic connectivity.

maya-integration

509

from a5c-ai/babysitter

Maya to engine pipeline skill for FBX export and rigging workflows.

blender-integration

509

from a5c-ai/babysitter

Blender to engine pipeline skill for GLTF/FBX export.

freertos-integration

509

from a5c-ai/babysitter

Expert skill for FreeRTOS configuration, debugging, and optimization

mixed-methods-integration

509

from a5c-ai/babysitter

Design and execute convergent, explanatory sequential, and exploratory sequential mixed methods research designs

health-data-integration

509

from a5c-ai/babysitter

Facilitate interoperability between health IT systems including EHR, HIE, and clinical decision support through HL7, FHIR, and other healthcare data standards