llm-classifier

LLM-based zero-shot and few-shot classification for flexible intent detection

509 stars

Best use case

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

LLM-based zero-shot and few-shot classification for flexible intent detection

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

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/llm-classifier/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How llm-classifier Compares

Feature / Agentllm-classifierStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

LLM-based zero-shot and few-shot classification for flexible intent detection

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

# LLM Classifier Skill

## Capabilities

- Implement zero-shot classification with LLMs
- Design few-shot classification prompts
- Configure structured output for labels
- Implement confidence scoring
- Design classification taxonomies
- Handle multi-label classification

## Target Processes

- intent-classification-system
- dialogue-flow-design

## Implementation Details

### Classification Patterns

1. **Zero-Shot**: No examples, description-based
2. **Few-Shot**: Example-based classification
3. **Structured Output**: JSON schema for labels
4. **Chain-of-Thought**: Reasoning before classification
5. **Ensemble**: Multiple prompts/models

### Configuration Options

- LLM model selection
- Label descriptions
- Example selection strategy
- Output format specification
- Confidence calibration

### Best Practices

- Clear label descriptions
- Representative examples
- Consistent output format
- Calibrate confidence scores
- Test with edge cases

### Dependencies

- langchain-core
- LLM provider

Related Skills

kraken2-taxonomic-classifier

509
from a5c-ai/babysitter

Kraken2 taxonomic classification skill for rapid metagenomic read assignment

acmg-variant-classifier

509
from a5c-ai/babysitter

ACMG/AMP variant classification skill for systematic pathogenicity assessment

abc-xyz-classifier

509
from a5c-ai/babysitter

Multi-dimensional inventory classification skill combining value (ABC) and demand variability (XYZ) analysis for differentiated policies

huggingface-classifier

509
from a5c-ai/babysitter

Hugging Face transformer model fine-tuning and inference for intent classification

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.)

yolo

509
from a5c-ai/babysitter

Run Babysitter autonomously with minimal manual interruption.

user-install

509
from a5c-ai/babysitter

Install the user-level Babysitter Codex setup.

team-install

509
from a5c-ai/babysitter

Install the team-pinned Babysitter Codex workspace setup.

retrospect

509
from a5c-ai/babysitter

Summarize or retrospect on a completed Babysitter run.

resume

509
from a5c-ai/babysitter

Resume an existing Babysitter run from Codex.

project-install

509
from a5c-ai/babysitter

Install the Babysitter Codex workspace integration into the current project.