context-manager

Elite AI context engineering specialist focused on dynamic context management, intelligent memory systems, and multi-agent workflow orchestration.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "context-manager" with this command: npx skills add mileycy516-stack/skills/mileycy516-stack-skills-context-manager

Context Manager

Elite AI context engineering specialist focused on dynamic context management, intelligent memory systems, and multi-agent workflow orchestration.

When to Use This Skill

  • Designing RAG (Retrieval-Augmented Generation) architectures

  • Optimizing context windows and token budgets

  • Orchestrating multi-agent context handoffs

  • Designing Vector Database schemas (Pinecone, Qdrant)

  • Building Knowledge Graphs for semantic reasoning

  • Implementing intelligent memory (short vs long term)

Workflow

  • Analyze: Determine scope (User Session, Project Lifetime, Enterprise).

  • Architect: Choose storage (Vector DB vs Graph vs SQL) and Strategy (RAG vs Fine-tuning).

  • Optimize: Implement chunking, ranking, and compression strategies.

  • Orchestrate: Define how agents share and update state.

Instructions

  1. RAG Strategy (Retrieval-Augmented Generation)

Don't just dump text.

  • Chunking: Split documents semantically (by paragraph/header), not just by character count.

  • Hybrid Search: Combine Dense Vector Search (semantic) with Sparse Keyword Search (BM25) for precision.

  • Re-ranking: Use a Cross-Encoder to re-rank the top K results before feeding them to the LLM.

  1. Context Window Optimization
  • Compression: Summarize older turns in a conversation.

  • Filtering: Remove irrelevant metadata or boilerplate code from prompts.

  • Pruning: Dynamically drop the lowest-relevance context blocks when budget is tight.

  1. Intelligent Memory Systems
  • Episodic Memory: "What did we discuss 5 minutes ago?" (Recent chat history).

  • Semantic Memory: "What are the user's preferences?" (Long-term facts stored in Vector DB).

  • Procedural Memory: "How do I perform this task?" (Stored skills/workflows).

  1. Knowledge Graphs

Use when relationships matter more than similarity.

  • Entities: Nodes (User, Product, Order).

  • Edges: Relationships (User -> Purchased -> Product).

  • Reasoning: "Find all products purchased by users who also bought X".

Resources

  • Advanced RAG Patterns

  • Context Optimization

  • Multi-Agent State

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

git-advanced-workflows

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

playwright browser automation

No summary provided by upstream source.

Repository SourceNeeds Review
General

trading-psychology-coach

No summary provided by upstream source.

Repository SourceNeeds Review