context-engineering

Load rules files and relevant specs to configure agent context.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/pyoclaw/agent-skills --skill context-engineering-pyoclaw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: context-engineering
Source: https://github.com/pyoclaw/agent-skills/tree/main/skills/context-engineering
Command: npx skills add https://github.com/pyoclaw/agent-skills --skill context-engineering-pyoclaw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Curates and structures the information fed to AI assistants to prevent hallucinations, reduce irrelevant output, and ensure adherence to project conventions when working on code or specs.

Core Features & Use Cases

  • Rules Files & Persistent Context: Establishes project-wide rules files (CLAUDE.md, .github/copilot-instructions.md, etc.) so agents always follow team conventions and constraints.
  • Selective Context Loading: Guides which spec sections, source files, and test outputs to include per task to keep focus and avoid context flooding.
  • Conversation & Confusion Management: Provides patterns for summarizing long histories, surfacing conflicts between spec and code, and emitting inline plans before execution.
  • Use Case: Onboarding a new feature, load the rules file, the feature's spec excerpt, example implementations, and tests to let the agent implement a change without inventing APIs.

Quick Start

Load the project's rules file, the relevant spec section, and the specific source and test files for the task, then ask the agent to propose a short implementation plan.

Frequently Asked Questions about context-engineering

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

FAQPage Schema
How do I optimize agent context to reduce AI hallucinations when coding?

To reduce hallucinations, curate agent context by loading persistent rules files, selectively including relevant spec sections and source files, and managing conversation history to keep the context window focused.

How do I set up persistent context rules for AI coding assistants?

Set up persistent context by establishing project-wide rules files like CLAUDE.md or copilot-instructions.md, ensuring agents always follow team conventions and constraints across development sessions.

What is the best way to manage conversation history for long coding sessions?

Manage long conversation histories by applying summarization patterns, surfacing conflicts between specs and code, and emitting inline plans before execution to prevent agent behavior degradation.

When should I use selective context loading for software engineering tasks?

Use selective context loading when onboarding a project, starting new sessions, or switching tasks to guide which spec sections, source files, and test outputs are included, preventing context flooding.

Why does my AI assistant invent APIs instead of following project conventions?

AI assistants invent APIs when lacking structured context; loading the project's rules file, feature spec excerpts, example implementations, and tests provides the necessary constraints to ensure adherence to conventions.

Can I use context engineering techniques without installing external dependencies?

Yes, you can apply context engineering without external dependencies by structuring existing project files, managing rules files, and organizing conversation histories to guide agent behavior natively.