Show HN：意圖層：AI代理的上下文工程技能

Hacker News·3 個月前

新推出的「意圖層」技能旨在為AI代理提供層級化的上下文，使其能像資深工程師一樣導航程式碼庫。此工具透過提供超越原始程式碼的結構化資訊，以提升AI代理的效能。

Context Engineering Skills: Intent Layer

A skill that sets up hierarchical AGENTS.md files so AI agents navigate your codebase like senior engineers.

Today I’m releasing /intent-layer, the first skill from Crafter Station .

Works with Claude Code, Codex, Cursor, Copilot, and 10+ more agents .

I’ve been using Claude Code daily for months. Same model, same prompts, completely different results depending on the repo.

On a large codebase I watched Claude:

Reasonable search. Wrong places. Bug still there.

Your best engineers don’t grep randomly. They have a mental map:

That map took years to build. Your agents don’t have it.

Context engineering is designing the full information an agent needs to perform reliably:

Intent Layer solves the first piece: system prompt infrastructure.

The skill helps you set up AGENTS.md files at folder boundaries. Simple markdown that gives agents the context they can’t get from code alone:

Run /intent-layer on your project and it:

Run it again later to audit existing nodes or find new candidates as your codebase grows.

Same bug, with AGENTS.md in place:

Intent Layer is the first of several context engineering skills I’m building. More coming soon.

Open Source

All skills are open source at crafter-station/skills .

Built on The Intent Layer by Tyler Brandt. His AI Adoption Roadmap maps the stages most teams are stuck at. Start there for the full methodology.

Context engineering framework from DAIR.AI and LangChain .

Also related to my earlier AI-First Manifesto where I proposed LLMS.md files. Intent Layer is the evolved version of that idea.

Follow @RaillyHugo for more on context engineering.