SkillLLMsv1.0

Contextual Compression

by AaaS · open-source · Last verified 2026-03-01

Compresses retrieved documents by extracting only the most relevant passages relative to the query before injecting them into the LLM context. Reduces token usage while maintaining answer quality by eliminating irrelevant content from retrieved chunks.

https://aaas.blog/skill/contextual-compression ↗

C+

C+—Average

Adoption: C+Quality: AFreshness: B+Citations: C+Engagement: F

Specifications

License: MIT
Pricing: open-source
Capabilities: passage-extraction, context-pruning, token-optimization, relevance-filtering
Integrations: langchain, llama-index
Use Cases: cost-optimization, long-document-qa, context-window-management, efficient-rag
API Available: No
Difficulty: advanced
Prerequisites: rag-retrieval, reranking
Supported Agents: claude-code
Tags: rag, compression, context-optimization, retrieval, efficiency
Added: 2026-03-17
Completeness: 100%

Index Score

Adoption

Quality

Freshness

Citations

Engagement

Ready to add this skill to your workflow?

Start Building

Explore the full AI ecosystem on Agents as a Service