Profile My skills Saved Collections Edit profile Submit a skill

AI Context Engineering

Foundational context engineering theory and practice for LLM applications. Covers the 5 levels of context (zero/linear/goal-oriented/role-based/semantic blueprint), semantic role labeling (SRL) for visualizing structured prompts, and the layered (scope → investigation → action) analysis pattern. Use this skill when: - Choosing between prompt engineering and context engineering for a task - Designing context that includes role, goals, and structured intent - Building a meeting / document / interview analysis pipeline - Visualizing the semantic structure of a prompt with SRL - Deciding when to upgrade a prompt's "context level"

ebarti 339c460 16 files · 71.9 KB Updated
DevOps & Infra

File contents

AI Context Engineering

Knowledge from "Context Engineering for Multi-Agent Systems" (Chapter 1). Foundational theory for moving from prompts to engineered context.

Quick Start

  1. Check guidelines.md to find which files to load
  2. Load only relevant files (each topic has knowledge.md, rules.md, examples.md)
  3. Apply guidance to your work

Contents

References

Category Purpose
semantic-blueprint The 5 levels of context, semantic blueprint definition, SRL theory
srl-implementation Python implementation of SRL with matplotlib visualization
meeting-analysis The 3-layer (scope/investigation/action) analysis pattern with worked example

Workflows

Workflow Purpose
workflows/build-3-layer-pipeline.md End-to-end build of a scope→investigation→action analysis pipeline

Guidelines

See guidelines.md for task-based file selection.

ebarti/skills/tree/main/ai-context-engineering commit 339c4603b7

Browse category

Frequently asked questions

npx skillmds@latest add ebarti/ai-context-engineering