context-engineering

Curate AI knowledge with memory banks and specification files.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/ecnepsyroc-bot/Dejavara --skill context-engineering-ecnepsyroc-bot
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: context-engineering
Source: https://github.com/ecnepsyroc-bot/Dejavara/tree/main/deploy/skills/context-engineering
Command: npx skills add https://github.com/ecnepsyroc-bot/Dejavara --skill context-engineering-ecnepsyroc-bot

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Curating what an AI knows to get quality, consistent output across complex tasks, projects, and cross-domain prompts.

Core Features & Use Cases

  • Memory bank design and governance: structuring CLAUDE.md, memory-bank/, activeContext.md, architecture.md, and a .claude/commands folder for persisted context.
  • Specification-driven development: using feature/spec documents to drive planning, validation, and end-to-end outcomes.
  • Progressive disclosure strategy: layering information from metadata to core instructions to reference files to balance context and capability.

Quick Start

Create a CLAUDE.md following the template and seed your memory bank with a projectBrief, activeContext, and architecture notes.

Frequently Asked Questions about context-engineering

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

FAQPage Schema
How do I structure a CLAUDE.md memory bank for consistent AI output?

To structure a CLAUDE.md memory bank, create a root file alongside a memory-bank/ directory containing activeContext.md and architecture.md to curate persisted context and enforce reliable AI collaboration.

What is progressive disclosure in prompt engineering?

Progressive disclosure in prompt engineering is a strategy that layers information from metadata to core instructions and reference files, balancing AI context window limits with project capability requirements.

How do I use specification files for spec-driven AI development?

Using specification files for spec-driven AI development involves creating feature/spec documents to drive planning, validation, and end-to-end outcomes, ensuring robust guardrails for reproducible results.

Can I manage complex project contexts without losing AI reliability?

Managing complex project contexts requires enforcing layered context and structured prompting across domains, ensuring the AI maintains precise, reliable results without drifting from original specifications.

What is the best way to organize a .claude/commands folder for AI context?

Organizing a .claude/commands folder involves structuring custom instructions within the directory to complement the memory bank, governing how the AI processes layered context and specification files.