One-click install
npx skills add https://github.com/jdidion/claude-plugins --skill offload-context
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: /offload:context
Source: https://github.com/jdidion/claude-plugins/tree/main/plugins/offload/skills/context
Command: npx skills add https://github.com/jdidion/claude-plugins --skill offload-context

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Review the current session, preserve important learnings to auto-memory, and compact context for efficient recall.

Core Features & Use Cases

  • Session summarization: generate a concise recap of the ongoing dialogue and actions.
  • Auto-memory: store key feedback, decisions, and references for future conversations.
  • Context compaction: prune and organize memory to keep conversations lean yet informative.

Quick Start

Summarize the current session and save key learnings to auto-memory.

Frequently Asked Questions about /offload:context

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

FAQPage Schema
How do I save session learnings and compact context for long-running conversations?

To save session learnings and compact context, you can summarize the current session and store key decisions in auto-memory. This prunes ongoing dialogue, keeping conversations lean while preserving references for future recall.

What is context compaction and when do I need it for memory management?

Context compaction prunes and organizes auto-memory to keep conversations lean yet informative. You need it during long-running sessions to prevent memory bloat while retaining key feedback, decisions, and references for future conversations.

How do I extract workflow summaries and store them in auto-memory?

You extract workflow summaries by running a session-summary script that reviews ongoing dialogue and actions. The script outputs a concise recap, saving key feedback and references directly into auto-memory for future recall.

Does session summarization require prompt-logging to capture feedback?

Session summarization requires a session-summary script to generate the recap, while prompt-logging is optional. Enabling prompt-logging provides the detailed input history needed to enable precise memory writes and context compaction.

Can I use auto-memory plugins for Claude to preserve decisions across sessions?

Yes, auto-memory plugins for Claude preserve decisions across sessions by capturing feedback and references from the current dialogue. This allows future conversations to recall past learnings without manually re-entering context.

What are the limitations of context compaction for ongoing conversations?

Context compaction relies on the session-summary script to determine what to prune, meaning poorly summarized sessions may lose critical details. It should not be used when verbatim logs are required, as it organizes memory for efficiency rather than exact recall.