OpenSkillIndex← back to search
claude-codedevelopment

Babysitter llm-classifier

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

install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/specializations/ai-agents-conversational/skills/llm-classifier" ~/.claude/skills/a5c-ai-babysitter-llm-classifier && rm -rf "$T"
manifest: library/specializations/ai-agents-conversational/skills/llm-classifier/SKILL.md
tags
#llm-classification#intent-detection#prompt-engineering#classification-taxonomy#structured-output
source content

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