context-ranking
CommunitySurface the best information.
Authorseb1n
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill refines raw search results by prioritizing the most relevant, diverse, and useful information, ensuring that AI agents receive the highest quality context for their tasks.
Core Features & Use Cases
- Multi-stage Scoring: Combines lightweight algorithms (BM25, cosine similarity) with powerful cross-encoder reranking for precise relevance.
- Diversity Enhancement: Utilizes Maximal Marginal Relevance (MMR) to ensure a broad coverage of topics within the retrieved context.
- Use Case: When answering a complex user query, this skill ensures the AI agent receives a concise set of the most pertinent document snippets, rather than a long list of loosely related information.
Quick Start
Rank the provided candidate text chunks for the query "explain the impact of quantum computing on cryptography" using the context-ranking skill.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: context-ranking Download link: https://github.com/seb1n/awesome-ai-agent-skills/archive/main.zip#context-ranking Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.