skills.rest
mortenbroesby
mortenbroesbyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

context-engineering

Load persistent repo rules from AGENTS.md and .agents/rules/ at task start.

1|Updated Apr 5, 2026
Search Tags:#context-engineering#memory-management#code-tasks#task-switching#repo-context#ai-context-engine#obsidian-memory
One-click install
npx skills add https://github.com/mortenbroesby/playground --skill context-engineering-mortenbroesby
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-engineering
Source: https://github.com/mortenbroesby/playground/tree/main/.skills/context-engineering
Command: npx skills add https://github.com/mortenbroesby/playground --skill context-engineering-mortenbroesby

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Curate the right repo context at the right time to keep agent outputs aligned with repository conventions, decisions, and memory.

Core Features & Use Cases

  • Load and apply persistent repo context rules (e.g., AGENTS.md, .agents/rules/) at task start.
  • Use specialized context tools like ai-context-engine, query_code, and obsidian-memory to surface relevant files and decisions.
  • Maintain a narrow, task-focused context when switching workspaces or concerns to reduce drift.

Quick Start

Load the persistent repo context and begin querying the code context tools for the current task.

Frequently Asked Questions about context-engineering

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

FAQPage Schema
How do I load persistent repo context to improve AI agent task accuracy?▼

To load persistent repo context, apply context-engineering at task start to read rules from AGENTS.md and .agents/rules/, which aligns agent outputs with your repository conventions and decisions.

Why does my agent output drift from repository conventions when switching workspaces?▼

Agent output drifts during task switching because context becomes stale; refresh repo context using context-engineering to maintain a narrow, task-focused scope and query relevant files.

How do I use Obsidian memory to surface relevant code decisions for AI tasks?▼

You can surface relevant code decisions by applying context-engineering, which uses obsidian-memory alongside ai-context-engine and query_code to extract and load past repository decisions.

What is the best way to maintain focused context scope when switching code tasks?▼

The best way to maintain focused context scope is applying context-engineering when switching tasks, refreshing context to narrow scope and querying only files relevant to the active concern.

Do I need AGENTS.md to use context-engineering for memory management?▼

You need AGENTS.md and .agents/rules/ files to provide the persistent repo rules that context-engineering loads at task start to ensure accurate memory management and task alignment.

Can I use query_code with ai-context-engine to load repository context?▼

Yes, context-engineering integrates query_code and ai-context-engine to surface relevant files and decisions, loading persistent repository context to maintain accurate task alignment.

Related Skills

Explore More Software Engineering Skills→
mayervcmayervc

create-rule

Create Cursor rules with YAML frontmatter and save them under .cursor/rules/.

Community
Intermediate
theowenyoungtheowenyoung

get-qodo-rules

Load repository-scoped coding rules from the Qodo platform before code tasks.

Community
Advanced
ConaryLabsConaryLabs
8

recap

Summarize current session context, decisions, preferences, and active goals.

Official
Basic
marinvchmarinvch

filesystem-context

Offload tool outputs and context to the filesystem for persistent agent workflows.

Community
Advanced