context-manager

Capture and distribute context across agents in multi-agent workflows.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/LPDigital-Agent/galderma-demo-trackwise --skill context-manager-lpdigital-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: context-manager
Source: https://github.com/LPDigital-Agent/galderma-demo-trackwise/tree/main/.claude/skills/context-manager
Command: npx skills add https://github.com/LPDigital-Agent/galderma-demo-trackwise --skill context-manager-lpdigital-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Context management is essential for long-running, multi-agent workflows where decisions, rationale, and session state must be preserved across agents and handoffs. This skill centralizes capture, distribution, and storage of context to prevent drift and repetition.

Core Features & Use Cases

  • Context Capture: extract and store key decisions and rationale from agent outputs.
  • Context Distribution: generate agent-specific briefings and maintain a central context index for quick retrieval.
  • Memory Management: interface with MCP Memory tools to create entities, add observations, and search nodes for fast lookup.
  • Faiston NEXO Templates: provide quick and full context templates for various interaction modes.

Quick Start

Activate the context-manager skill, review the current conversation, and use the templates to extract and store critical context. Generate a brief for the next agent and update the context memory accordingly.

Frequently Asked Questions about context-manager

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I maintain context across multiple agents during long-running workflows?

Multi-agent context maintenance is achieved by centralizing the capture, distribution, and storage of session state to prevent drift. This skill extracts key decisions and rationale from agent outputs, then stores them for consistent reuse across handoffs.

How does MCP Memory integration work for agent session coordination?

MCP Memory integration works by interfacing with memory tools to create entities, add observations, and search nodes for fast context lookup. This allows agents to quickly retrieve stored decisions and maintain a centralized context index during workflows.

What is the best way to generate briefings for agent handoffs?

The best way to generate agent briefings is to review the current conversation, extract critical context using provided templates, and compile it into an agent-specific brief. This ensures the next agent receives the necessary session state without repetition.

Can I use context management templates for Faiston NEXO deployments?

Yes, you can use context management templates for Faiston NEXO deployments. The skill provides quick and full context templates specifically designed to support various interaction modes and session coordination within NEXO environments.

Why does context drift occur in multi-agent workflows and how can it be prevented?

Context drift occurs in multi-agent workflows when decisions and rationale are not preserved across agent handoffs. It can be prevented by capturing key outputs into a centralized memory system and distributing agent-specific briefings before each handoff.

Do I need a centralized context index for cross-agent session coordination?

Yes, a centralized context index is needed for cross-agent session coordination to prevent repetition and ensure state consistency. It serves as the single source of truth for retrieving past decisions and generating accurate agent briefings.