skills.rest
reubenjohn
reubenjohnCOMMUNITY
Explore all skills by this author →
Website𝕏@reubenvjohnGitHub

context-engineering

Guides content placement decisions across CLAUDE.md, skills, and knowledge files.

Updated Jan 24, 2026
Search Tags:#workflow#documentation#context#organization#engineering#knowledge-management
One-click install
npx skills add https://github.com/reubenjohn/reeve-desk --skill context-engineering-reubenjohn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-engineering
Source: https://github.com/reubenjohn/reeve-desk/tree/main/.claude/skills/context-engineering
Command: npx skills add https://github.com/reubenjohn/reeve-desk --skill context-engineering-reubenjohn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Guidelines for structuring the Desk when making changes to core behaviors. Invoke when adding new capabilities, restructuring documentation, or optimizing context loading.

Core Features & Use Cases

  • Decision-tree driven placement of information (CLAUDE.md, Auto-memory, Skills, Knowledge files) to balance always-loaded vs on-demand data.
  • Clear criteria for when to split content into skills vs CLAUDE.md, enabling lean operation and scalable growth.
  • Size and maintenance patterns to keep core files succinct and minimizes drift.

Quick Start

Invoke this skill to guide decisions when adding capabilities or restructuring documentation to optimize context loading.

Frequently Asked Questions about context-engineering

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

FAQPage Schema
How do I structure documentation to keep AI context lean and effective?▼

To keep context lean, use a decision-tree to place information across CLAUDE.md, auto-memory, or dedicated skill files. This balances always-loaded data with on-demand loading to preserve operational efficiency.

When should I split documentation into a dedicated skill versus CLAUDE.md?▼

Split documentation into a dedicated skill instead of CLAUDE.md when content represents specific capabilities that can be loaded on-demand. This keeps core files succinct and minimizes drift during restructuring.

What is the best way to organize knowledge files when adding new engineering capabilities?▼

The best way to organize knowledge files when adding capabilities is applying load-on-demand principles with clear content ownership criteria. This ensures scalable organization across CLAUDE.md, skills, and knowledge directories.

Does context engineering work for restructuring core behaviors and feature additions?▼

Yes, context engineering works for restructuring core behaviors and feature additions. It guides decision-making for structuring the Desk to decide whether content belongs in auto-memory or a dedicated skill file.

Why does my CLAUDE.md context become bloated when adding new capabilities?▼

Your CLAUDE.md context becomes bloated because content ownership is not properly defined. Apply formalized load-on-demand principles to move capabilities into dedicated skills or knowledge files to maintain lean operation.

Related Skills

Explore More Software Engineering Skills→
daymadedaymade
1.3k

claude-md-progressive-disclosurer

Audit CLAUDE.md sections and migrate content to references or skills.

Community
Advanced
severity1severity1
154

memory-processor

Update AUTO-MANAGED sections in CLAUDE.md files after code changes.

Community
Basic
zxdxjtuzxdxjtu
8

steward

Enforce module ownership and contract boundaries for code changes against AGENT.md.

Community
Advanced
Jurel89Jurel89

remember

Classify project knowledge into memory surfaces for future reference.

Community
Intermediate