context-engineering

Structures rules files, specs, and source context for AI coding agents.

Updated Mar 14, 2026
One-click install
npx skills add https://github.com/yourlabpt/yourlabpt_website --skill context-engineering-yourlabpt
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-engineering
Source: https://github.com/yourlabpt/yourlabpt_website/tree/main/projects/skills/context-engineering
Command: npx skills add https://github.com/yourlabpt/yourlabpt_website --skill context-engineering-yourlabpt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI coding agents hallucinate APIs, ignore project conventions, and degrade in quality during long sessions because they receive too little, too much, or stale context. This Skill provides a systematic method for curating what the agent sees at every stage of a session. ## Core Features & Use Cases - Context Hierarchy: Organizes context into five levels from persistent rules files (CLAUDE.md, .cursorrules, AGENTS.md) down to transient conversation history, with templates for each. - Context Budget Management: Defines when to trim (at 75% capacity), what to cut first, what to protect, and how to compress history into summaries instead of deleting it. - Confusion Management: Provides patterns for surfacing spec conflicts and missing requirements instead of silently guessing, plus an inline planning pattern for multi-step tasks. - Use Case: When starting a new project for AI-assisted development, use this Skill to write a rules file covering tech stack, commands, conventions, and boundaries so the agent follows your patterns from the first prompt. ## Quick Start Ask the agent to create a CLAUDE.md rules file for your project covering tech stack, commands, conventions, and boundaries using the context engineering guidelines.

Frequently Asked Questions about context-engineering

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

FAQPage Schema
How do I write a CLAUDE.md rules file for my project?▼

A CLAUDE.md file should cover your tech stack, build and test commands, code conventions, and boundaries such as never committing secrets. Include one short example of a well-written component so the agent follows your existing style.

How much context should I give an AI coding agent?▼

Aim for under 2,000 lines of focused, task-relevant context per task. Loading more than about 5,000 lines of non-specific context causes the agent to lose focus, so include only the files, spec sections, and one pattern example relevant to the current task.

What is the equivalent of CLAUDE.md for Cursor or GitHub Copilot?▼

Cursor uses .cursorrules or .cursor/rules/*.md files, Windsurf uses .windsurfrules, GitHub Copilot uses .github/copilot-instructions.md, and OpenAI Codex uses AGENTS.md. All serve the same purpose of persistent project-wide rules.

Why does agent output quality degrade during long sessions?▼

Long sessions accumulate failed attempts, replaced drafts, and verbose tool output that fragment the model's attention. Start trimming at 75 percent context capacity, compress old exploration into one-sentence summaries, and keep the active task and current error last in context.

When should I start a fresh session instead of continuing?▼

Start a fresh session when switching between major features or when the agent references outdated patterns and deleted code. Stale context causes drift that correction cannot reliably fix, so a clean session with a structured brain dump is more effective.