OpenSkillIndex ← back to search

claude-code productivity

Babysitter prompt-compression

Token-efficient prompt compression techniques for cost optimization

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 "$T/library/specializations/ai-agents-conversational/skills/prompt-compression" ~/.claude/skills/a5c-ai-babysitter-prompt-compression && rm -rf "$T"

manifest: library/specializations/ai-agents-conversational/skills/prompt-compression/SKILL.md

tags

#prompt-optimization #token-efficiency #llm-cost #context-pruning #compression-techniques

source content

Prompt Compression Skill

Capabilities

Implement token-efficient prompt compression
Design context pruning strategies
Configure selective context inclusion
Implement LLMLingua-style compression
Design summary-based compression
Create compression quality metrics

Target Processes

cost-optimization-llm
agent-performance-optimization

Implementation Details

Compression Techniques

LLMLingua: Token-level compression
Summary Compression: LLM-based summarization
Selective Context: Relevant section extraction
Token Pruning: Remove low-importance tokens
Document Filtering: Pre-retrieval filtering

Configuration Options

Compression ratio targets
Quality threshold settings
Token budget constraints
Compression model selection
Evaluation metrics

Best Practices

Monitor quality vs compression tradeoff
Test with representative prompts
Set appropriate compression ratios
Validate compressed prompt quality
Track cost savings

Dependencies

llmlingua (optional)
tiktoken
transformers