Individual skill

context-window-management

Manage LLM context windows deliberately — budgeting, prioritization, summarization, and retrieval instead of dumping everything in. Use when prompts grow long, costs rise, or the model loses track of key details.

skills/context-window-management/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: Yes
Observed behavior: Not checked yet
Last checked: Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 54
Repository last updated: Oct 10, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

agent-skills Repository topic
ai-agents Repository topic
ai-agents-automation Repository topic
ai-skills Repository topic
awesome Repository topic
awesome-list Repository topic
chatgpt Repository topic
claude-skills Repository topic
meta-ai Repository topic
muse-ai Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 4,151 bytes

Read excerpt


# Context Window Management

The context window is the model's working memory: finite, expensive, and subject to attention 
dilution. Managing it means deciding what deserves space, in what form, and for how long.

## Overview

Bigger windows tempt you to dump everything in — full documents, entire histories, all tool 
outputs. But models attend unevenly: information in the middle gets lost, irrelevant content 
distracts, and every token costs money and latency. The skill is curation: budget the window like a 
budget, put the most decision-relevant content where attention is strongest (start and end), and 
move the rest into retrieval or summaries.

## When to use