skills.rest
jaydubya818
jaydubya818COMMUNITY
Explore all skills by this author →
GitHub

context-compression

Design and evaluate context compression strategies for long-running agent sessions.

Updated Feb 4, 2026
Search Tags:#llm evaluation#token optimization#agent memory#context compression#long-running sessions#conversation summarization
One-click install
npx skills add https://github.com/jaydubya818/Dental_Agent --skill context-compression-jaydubya818
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-compression
Source: https://github.com/jaydubya818/Dental_Agent/tree/main/.claude/skills/context-compression
Command: npx skills add https://github.com/jaydubya818/Dental_Agent --skill context-compression-jaydubya818

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of managing large conversation histories in AI agents, preventing memory exhaustion and ensuring efficient token usage for long-running tasks.

Core Features & Use Cases

  • Context Summarization: Compresses extensive conversation logs into manageable summaries.
  • Token Optimization: Reduces token consumption per task, not just per request, by intelligently preserving critical information.
  • Use Case: When an AI agent is working on a complex coding task that spans thousands of messages, this Skill can summarize the history to prevent it from exceeding its context window, allowing it to continue working without losing track of previous steps or decisions.

Quick Start

Use the context-compression skill to summarize the last 100 messages in the current conversation.

Frequently Asked Questions about context-compression

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

FAQPage Schema
How do I optimize token usage for long-running agent sessions?▼

Context compression strategies like anchored iterative summarization and regenerative full summaries optimize token usage for long-running agent sessions by compressing extensive conversation logs while preserving critical information.

What is the best way to summarize conversation history when an agent exhausts memory?▼

Regenerative full summaries and opaque compression effectively summarize conversation history when an agent exhausts memory, compressing extensive logs into manageable summaries to prevent context window exhaustion.

How does context compression handle tokens-per-task optimization for complex coding tasks?▼

Context compression handles tokens-per-task optimization for complex coding tasks by intelligently preserving critical information across thousands of messages, reducing overall token consumption rather than just per-request limits.

Can I evaluate context summarization strategies using probe-based frameworks?▼

Yes, you can evaluate context summarization strategies using probe-based evaluation frameworks, which assess how effectively anchored iterative summarization and regenerative full summaries retain necessary information.

When should I use opaque compression over anchored iterative summarization for agent memory?▼

Use opaque compression over anchored iterative summarization for agent memory when maximizing token reduction without exposing internal summary structures, whereas anchored summarization prioritizes retaining explicit reference points.

Related Skills

Explore More Software Engineering Skills→
galeepgaleep

caveman-stats

Analyze Claude Code session logs for actual token usage and savings.

Community
Basic
CxxxxDxxxFCxxxxDxxxF

context-compression

Compress LLM conversational context using iterative summarization and opaque compression.

Community
Advanced
bthillerupbthillerup
1

context-compression

Compress large conversation histories and codebases exceeding context window limits.

Community
Advanced
mhismail3mhismail3

context-compression

Compress long-running agent session contexts into structured persistent summaries.

Community
Advanced