How do I install the AI Context Engine skill?

Run npx skillmds@latest add ebarti/ai-context-engine in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is AI Context Engine safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with AI Context Engine?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is AI Context Engine free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published AI Context Engine?

ebarti (@ebarti) published this skill. Their other Agent Skills are listed on their SkillMD profile.

AI Context Engine by ebarti — Agent Skill

Name: AI Context Engine
Author: ebarti

AI Context Engine

The full Context Engine architecture: dual RAG (procedural + factual), Pinecone-based ingestion, the Planner / Executor / Tracer triad, specialist agents (Context Librarian, Researcher, Writer), the Agent Registry, production hardening (dependency injection, logging, modularization), plus an appendix-style reference guide. Use this skill when: - Building a context engine from scratch - Choosing between procedural RAG (blueprints) and factual RAG (evidence) - Setting up Pinecone ingestion (chunking, embedding, namespaces) - Designing a Planner-driven execution flow with traceability - Adding or refactoring specialist agents - Building or extending an Agent Registry - Hardening a notebook prototype for production (DI, logging, modularization) - Looking up the engine's commons library reference (helpers/agents/registry/engine/utils)

ebarti f2d8e3e 34 files · 180.8 KB Updated Sep 17, 2026

File contents

AI Context Engine

Knowledge from "Context Engineering for Multi-Agent Systems" (Chapters 3-5 + Appendix A). The full architecture and hardening of the glass-box Context Engine.

Quick Start

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

References

Category	Purpose
`dual-rag`	Procedural vs factual RAG, context library vs knowledge base
`rag-ingestion`	Pinecone setup, token-aware chunking, embeddings, upsert
`engine-components`	Planner, Executor, Execution Tracer (the engine triad)
`specialist-agents`	Context Librarian, Researcher, Writer (initial + hardened)
`agent-registry`	Capability descriptions, get_handler, dependency injection
`hardening`	DI, structured logging, proactive context mgmt, modularization
`engine-reference`	Appendix-style reference guide for the commons library

Workflows

Workflow	Purpose
`workflows/build-context-engine.md`	Full engine build (dual RAG → triad → agents → registry → run)
`workflows/setup-rag-pipeline.md`	Pinecone ingestion (chunk → embed → upsert)
`workflows/harden-engine.md`	Take prototype to production (DI, logging, modularization)

Guidelines

See guidelines.md for task-based file selection.

---name: ai-context-enginedescription: The full Context Engine architecture: dual RAG (procedural + factual), Pinecone-based ingestion, the Planner / Executor / Tracer triad, specialist agents (Context Librarian, Researcher, Writer), the Agent Registry, production hardening (dependency injection, logging, modularization), plus an appendix-style reference guide. Use this skill when: - Building a context engine from scratch - Choosing between procedural RAG (blueprints) and factual RAG (evidence) - Setting up Pinecone ingestion (chunking, embedding, namespaces) - Designing a Planner-driven execution flow with traceability - Adding or refactoring specialist agents - Building or extending an Agent Registry - Hardening a notebook prototype for production (DI, logging, modularization) - Looking up the engine's commons library reference (helpers/agents/registry/engine/utils)---# AI Context EngineKnowledge from "Context Engineering for Multi-Agent Systems" (Chapters 3-5 + Appendix A). The full architecture and hardening of the glass-box Context Engine.## Quick Start1. Check `guidelines.md` to find which files to load2. Load only relevant files (each topic has knowledge.md, rules.md, examples.md)3. Apply guidance to your work## Contents### References| Category | Purpose ||----------|---------|| `dual-rag` | Procedural vs factual RAG, context library vs knowledge base || `rag-ingestion` | Pinecone setup, token-aware chunking, embeddings, upsert || `engine-components` | Planner, Executor, Execution Tracer (the engine triad) || `specialist-agents` | Context Librarian, Researcher, Writer (initial + hardened) || `agent-registry` | Capability descriptions, get_handler, dependency injection || `hardening` | DI, structured logging, proactive context mgmt, modularization || `engine-reference` | Appendix-style reference guide for the commons library |### Workflows| Workflow | Purpose ||----------|---------|| `workflows/build-context-engine.md` | Full engine build (dual RAG → triad → agents → registry → run) || `workflows/setup-rag-pipeline.md` | Pinecone ingestion (chunk → embed → upsert) || `workflows/harden-engine.md` | Take prototype to production (DI, logging, modularization) |## GuidelinesSee `guidelines.md` for task-based file selection.

Frequently asked questions

AI Context Engine

File contents

AI Context Engine

Quick Start

Contents

References

Workflows

Guidelines

Related skills

Frequently asked questions

How do I install the AI Context Engine skill?

What does the AI Context Engine skill do?

Is AI Context Engine safe to use?

Which AI agents work with AI Context Engine?

Is AI Context Engine free to use?

Who published AI Context Engine?