agentsclimarketplace
Sign in

Prompt compression

Skill a5c-ai/babysitter/library/specializations/ai-agents-conversational/skills/prompt-compression

Token-efficient prompt compression techniques for cost optimizationFrom its SKILL.md

Install
npx -y skills add a5c-ai/babysitter --skill prompt-compression

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.5 KB, 218 tokens by cl100k_base, as published. Nobody here has run it

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

  1. LLMLingua: Token-level compression
  2. Summary Compression: LLM-based summarization
  3. Selective Context: Relevant section extraction
  4. Token Pruning: Remove low-importance tokens
  5. 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

What ships with it: 1 file

556 B alongside SKILL.md

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.