メニュー
Workflow for managing, structuring, compressing, and orchestrating context effectively for Claude and AI agent systems to improve reasoning quality, execution consistency, and long-term workflow scalability.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Workflow for building scalable messaging systems on Microsoft Azure using queues, event-driven architecture, pub/sub systems, service buses, and cloud-native communication patterns.
Workflow for implementing observability systems on Microsoft Azure using logging, monitoring, tracing, telemetry, metrics, dashboards, and production-grade cloud diagnostics.
Workflow for creating procedural systems in Blender using Geometry Nodes, procedural materials, node-based modeling, and non-destructive generation techniques.
Workflow for creating precise hard surface models in Blender using clean topology, subdivision workflows, bevel systems, and production-ready modeling techniques.
Workflow for using Claude to generate Blender Python scripts, automate 3D workflows, and create procedural scenes, animations, and assets directly inside Blender.
End-to-end workflow for setting up Blender, rigging a character, and creating a simple animation with a clear output (rendered animation).
| name | context-engineering |
| description | Workflow for managing, structuring, compressing, and orchestrating context effectively for Claude and AI agent systems to improve reasoning quality, execution consistency, and long-term workflow scalability. |
This skill enables Claude to manage context as an engineered system instead of treating prompts as isolated interactions.
The workflow focuses on:
The goal is to improve:
Instead of overwhelming Claude with raw information, context should be:
Good context engineering dramatically improves AI execution quality across large and complex workflows.
Before starting:
Recommended structure:
context/
memory/
tasks/
planning/
reviews/
project-summary.md
active-context.md
tasks.md
architecture.md
Recommended tools:
Optional:
Optional:
Use this skill when:
Do NOT use this skill for:
Maintain structured context across a large AI engineering repository with multiple active workflows.
Claude should:
Final result should:
Good AI workflows depend on:
Claude should treat context as:
Avoid:
Structured systems improve:
Not all information matters equally.
Claude should prioritize:
Avoid storing:
Good prioritization improves:
Context should be layered.
Recommended structure:
Long-Term Memory
↓
Project Context
↓
Active Workflow Context
↓
Immediate Task Context
This improves:
Claude should avoid mixing:
Large workflows require compression.
Claude should:
Compression improves:
Good summaries preserve:
The purpose of context engineering is execution quality.
Good context systems improve:
Claude should actively use context to:
Start by identifying:
Create foundational summaries for:
Keep summaries:
Separate:
Recommended structure:
memory/
active-context/
planning/
reviews/
This improves:
Claude should:
Avoid:
Good compression improves:
Maintain:
Claude should continuously update:
This improves:
In multi-agent workflows:
Claude should:
Good coordination improves:
As projects grow:
Context systems should evolve continuously.
Avoid:
Before finalizing:
Good context systems should feel:
The final output should include:
The workflow itself should remain:
The agent should:
The workflow should optimize for: