llm-classifier

基于 LLM 的零样本与少样本分类技术，灵活实现意图识别

SKILL.md

--- frontmatter

name: llm-classifier
description: LLM-based zero-shot and few-shot classification for flexible intent detection
allowed-tools:
  - Read
  - Write
  - Edit
  - Bash
  - Glob
  - Grep

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

•Zero-Shot: No examples, description-based
•Few-Shot: Example-based classification
•Structured Output: JSON schema for labels
•Chain-of-Thought: Reasoning before classification
•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