context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
Best for AI-assisted development pro…Works with GitHubLow risk
⌘source
- author
@addyosmani- language
- Shell
★17kstars
2.2kforks
Apr 18, 2026
✦overview.md
Key Features
- ·Optimizes agent context setup for new sessions
- ·Improves output quality by curating information
- ·Structures context using a hierarchical model
- ·Defines when to apply context engineering
- ·Manages rules files and project conventions
Use Cases
- →Starting a new coding session with an AI agent
- →Agent output quality declines with wrong patterns or hallucinations
- →Switching between different parts of a large codebase
- →Setting up a new project for AI-assisted development
- →Agent is not following established project conventions
Best for
- ✓AI-assisted development projects
- ✓Teams using agents for coding
Not ideal for
- !One-off simple queries
- !Projects without established conventions
FAQs
name
context-engineering
description
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
Context Engineering
Overview
Feed agents the right information at the right time. Context is the single biggest lever for agent output quality — too little and the agent hallucinates, too much and it loses focus. Context engineering is the practice of deliberately curating what the agent sees, when it sees it, and how it's structured.
When to Use
- Starting a new coding session
- Agent output quality is declining (wrong patterns, hallucinated APIs, ignoring conventions)
- Switching between different parts of a codebase
- Setting up a new project for AI-assisted development
- The agent is not following project conventions
The Context Hierarchy
Structure context from most persistent to most transient:
┌─────────────────────────────────────┐
│ 1. Rules Files (CLAUDE.md, etc.) │ ← Always loaded, project-wide
├─────────────────────────────────────┤
│ 2. Spec / Architecture Docs │ ← Loaded per feature/session
├─────────────────────────────────────┤
│ 3. Relevant Source Files │ ← Loaded per task
├─────────────────────────────────────┤
│ 4. Error Output / Test Results │ ← Loaded per iteration
├─────────────────────────────────────┤
$install
1-click copynpx skills add addyosmani/agent-skills --skill context-engineeringSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.