【文章标题】:The /wayfinder Skill: Navigating the “Fog of War” of Planning

/wayfinder 技能:在规划的“战争迷雾”中导航

【文章正文】:

We’re currently developing a new series about skills, with the aim of giving you a regular supply of new skills to use in your projects. We’re kicking things off with an interview — and a super-useful skill — featuring

Matt Pocock

, whose

“AI Skills for Real Engineers”

project has over 220,000 stars

on GitHub

. He also talks about these skills to 347,000 subscribers on

his YouTube channel

.

我们目前正在开发一个关于技能的新系列,目的是定期为你提供可在项目中使用的实用技能。我们以一篇采访——以及一项超级实用的技能——作为开篇,受访者是

Matt Pocock

,他的

“AI Skills for Real Engineers”

项目在 GitHub 上获得了超过 22 万颗星。他还在

他的 YouTube 频道

上向 34.7 万订阅者讲解这些技能。

Pocock recently released a new skill called

/wayfinder

. Its purpose is to help you and your agent figure out a project where the end state isn’t entirely clear. Or as Pocock put it in our interview,

/wayfinder helps you navigate “the fog of war,”

where you have a project but

“you can’t quite decide everything right at the start.”

The following interview has been slightly condensed for readability, so you can read it, absorb Matt’s insights, and then test out /wayfinder for yourself!

Pocock 最近发布了一项名为

/wayfinder

的新技能。它的目的是帮助你和你的智能体理清一个最终状态并不完全清晰的项目。或者正如 Pocock 在我们的采访中所说,

/wayfinder 帮助你在“战争迷雾”中导航,

即你有一个项目,但

“你无法在一开始就确定所有事情。”

为了便于阅读,以下采访略有压缩,因此你可以阅读它,吸收 Matt 的见解,然后亲自试用 /wayfinder!

Latent Space:

What were the goals of wayfinder?

Latent Space:

wayfinder 的目标是什么?

Pocock:

What I noticed is I was doing a lot of work with AFK agents

[Away From Keyboard]

and trying to schedule in a ton of work so that my agents could run virtually overnight. I would just plan a bunch of stuff, and then I would create a spec and then turn that spec into tickets. And I had a really well-developed set of skills for how to turn work into scheduled stuff that agents could just crack on.

But […] I was finding the planning stage really onerous, because I would have to be constantly thinking about my session management. Like, how many tokens am I into my context window? How deep am I going here?

Pocock:

我注意到我做了很多与 AFK 智能体

[Away From Keyboard]

相关的工作,并尝试安排大量工作,以便我的智能体几乎可以整夜运行。我通常会计划一堆事情,然后创建一份规范,再把规范转化为工单。我有一套非常成熟的技能,用于将工作转化为可调度的任务,让智能体直接上手执行。

但是……我发现规划阶段非常繁重,因为我必须时刻思考我的会话管理。比如,我的上下文窗口里有多少 token?我要在这里深入到什么程度?

Matt Pocock’s wayfinder skill, as

documented in GitHub

Matt Pocock 的 wayfinder 技能,见

GitHub 文档

I didn’t want to feel constrained in the planning stage anymore. I wanted an orchestrator layer that would basically say, okay, whatever you want to plan, I’m going to handle the planning sessions for you. I’m going to split this out into multiple different threads, do prototyping, do research and pull it all back together, so that you don’t feel constrained in the planning anymore.

And then your specs can be even more detailed, and you can just whack off an AFK agent to go and do tons more work.

我不想再在规划阶段感到束手束脚。我想要一个编排层,它基本上会说:好的,无论你想规划什么,我都会为你处理规划会话。我会把它拆分成多个不同的线程,进行原型设计、研究,然后汇总到一起,这样你就不再受限于规划了。

然后你的规范可以更加详细,你只需指派一个 AFK 智能体去做更多的工作。

Latent Space:

What was the design process of coming up with this skill?

Latent Space:

你是如何设计出这项技能的?

Pocock:

I had this kernel of an idea of, what if I didn’t have to manage the handoffs? What would that look like? And then, what would it look like to have some kind of centralized document to have all of those pieces together?

Whenever you’re thinking about context management — because that’s really what a skill is, you’re managing the context of the agent you’re working in —

you need to think about the information flow.

So what I wanted to think about is, what if a grilling session could manage other grilling sessions? What would that look like?

Well, the first step to that is, what does the grilling session that’s being managed need? What does the child need in that situation? So the child probably needs to understand a vague overview of what else is happening, and they need their specific task.

So there, you’ve got two documents. You’ve got a

map

— which is all of the rest of the stuff, all the decisions that have already been made. And then you’ve got the specific

ticket

that goes into the actual session. And what you notice there is that those words are very precise.

From

wayfinder documentation

You’ve got the map, and you’ve got the ticket, and you’ve got the

session

. And once you’ve got the kernel of an idea, you then need to come up with the words for that idea. Because once you’ve figured out the words, then those entities can be really clearly mapped out by the agent.

Because if you just call everything a ticket, or if you just refer to it in different ways in different places, then it’s going to be really confused and you’re going to get strange behavior. Whereas if you use these very specific, what I call leading words, to lead the agent to understand exactly what each part is, and you’ve understood what the information flow is, then you’ve got your skill.

Pocock:

我有一个想法的内核:如果我不必管理交接会怎样?那会是什么样子?然后,如果有一个集中的文档把这些碎片都放在一起,又会是什么样子?

每当你考虑上下文管理——因为那才是技能的本质,你是在管理你所使用的智能体的上下文——

你需要考虑信息流。

所以我想思考的是,如果一个“盘问”会话能够管理其他的“盘问”会话,那会是什么样子?

那么,第一步是,被管理的“盘问”会话需要什么?在这种情境下,子会话需要什么?子会话可能需要了解其他事项的模糊概览,并且需要明确自己的具体任务。

所以,你有两份文档。你有一份

地图(map)

——它包含了所有其他内容,所有已经做出的决策。然后你还有一份具体的

工单(ticket)

,它会进入实际的会话。你会注意到,这些词语非常精准。

来自

wayfinder 文档

你有了地图,有了工单,还有了

会话(session)

。一旦你有了一个想法的内核,你就需要为这个想法找到合适的措辞。因为一旦你弄清了措辞,这些实体就能被智能体非常清晰地映射出来。

因为如果你把所有东西都称为工单,或者在不同的地方用不同的方式称呼它,那么它就会变得非常混乱,你会得到奇怪的行为。而如果你使用这些非常具体的、我称之为“引导词”的词语,引导智能体准确理解每个部分是什么,并且你已经理解了信息流,那么你就拥有了你的技能。

Latent Space:

What kind of use cases do you think wayfinder would be useful for?

Latent Space:

你认为 wayfinder 适用于哪些用例?

Pocock:

Well, I’ve been using it for all sorts of stuff. I’ve been using it to actually plan courses as well. In wayfinder, there are different types of tickets.

So you’ve got

grilling

tickets, which are just a grilling session. Then you’ve got

prototype

tickets for creating prototypes,

research

tickets for creating [and doing] research, and then

task

tickets — which are really broad…basically, just anything the human needs to do that the agent can’t do. And so once you think about that, you realize, OK, I can apply that to anything.

One really key idea in wayfinder is the ‘fog of war’. So this is the concept of, you can’t quite decide everything right at the start.

I decided to test /wayfinder on a project to rearchitect my personal website. Here’s the initial project set-up, in this case using Claude Code.

You can make certain decisions, and those certain decisions sort of lead you there and push further out into the fog of war — kind of like Warcraft III style, exploring the map. And once I had the idea of ‘fog of war’ and ‘map’, I realized those two terms actually work really nicely together, and it really leads the agent into the right idea. So I’ve been using it for engineering, for non-engineering stuff, for course planning, all sorts.

Pocock:

嗯,我一直在用它处理各种各样的事情。我也用它来规划课程。在 wayfinder 中,有不同类型的工单。

你有

盘问(grilling)

工单,也就是一个“盘问”会话。然后你有

原型(prototype)

工单,用于创建原型;

研究(research)

工单,用于创建和进行研究;还有

任务(task)

工单——它们非常宽泛……基本上,就是任何需要人类去做而智能体无法完成的事情。一旦你这样思考,你就会意识到,好吧,我可以把它应用到任何事情上。

wayfinder 的一个关键概念是“战争迷雾”。这个概念的意思是,你无法在一开始就确定所有事情。

我决定在一个重构个人网站的项目上测试 /wayfinder。这是初始项目设置,在这里使用的是 Claude Code。

你可以做出某些决定,而这些决定会引导你前进,并进一步推进到“战争迷雾”中——有点像《魔兽争霸 III》那样探索地图。一旦我有了“战争迷雾”和“地图”的想法,我意识到这两个词实际上配合得很好,它真的能引导智能体走向正确的思路。所以我一直在将它用于工程、非工程事务、课程规划等等。

Latent Space:

This concept of the fog of war — it’s weird to consider what you don’t know that you don’t know. Maybe LLMs are good at capturing that.

Latent Space:

这个“战争迷雾”的概念——去思考你不知道自己不知道的东西,这很奇怪。也许 LLM 很擅长捕捉这一点。

Pocock:

I feel like with the grilling stuff that I’m still working on, that captures an idea that you don’t know stuff, but maybe the agent can contribute something and illuminate a part of the room that you don’t quite understand yet.

And wayfinder is just sort of an extra layer on top of that.

Working through my website rearchitecture project using /wayfinder. There’s 20+ years of content to re-organize!

Pocock:

我觉得,对于我仍在完善的“盘问”机制,它捕捉到了这样一个想法:你有些东西不知道,但也许智能体能贡献一些东西,照亮你尚未理解的房间的某个角落。

而 wayfinder 只是在它之上多加了一层。

使用 /wayfinder 推进我的网站重构项目。这里有 20 多年的内容需要重新组织!

Latent Space:

Yeah, and there’s all these artifacts. How much time do you spend teaching the model all this terminology?

Latent Space:

是的,还有所有这些工件。你花了多少时间教模型这些术语?

Pocock:

For the last few months, I’ve been pretty obsessed with terminology — and finding the right terms for certain things. I’ve put together, I haven’t actually put it out yet, but it’s an AI coding dictionary — of basically all the terms in AI coding. It’s in this beautiful graph that you can explore and understand exactly what an agent is, exactly what a harness is, exactly what a model is, blah blah blah.

I’ve redone all my courses to use that dictionary and make it really solid. And then all of my skills use a consistent dictionary as well. So they’re all working off the [same] assumptions, the same leading words.

I realized that I needed a ubiquitous language between me and the agent. Between me and the agent, there is a communication barrier. And that’s what I’m trying to do with my skills all the time, is try to find the right words.

And agents are really good at showing you the opportunities for different wording — really good at domain modeling, actually.

Pocock:

在过去的几个月里,我一直非常痴迷于术语——以及为特定事物找到正确的术语。我整理了一本(实际上还没有发布)AI 编程词典——基本上涵盖了 AI 编程中的所有术语。它是一张漂亮的图,你可以探索并准确理解什么是智能体、什么是 harness、什么是模型,等等等等。

我重做了我所有的课程,以使用这本词典,使其非常扎实。然后我所有的技能也都使用了一致的词典。所以它们都基于相同的假设、相同的引导词。

我意识到我需要一种在我和智能体之间的通用语言。在我和智能体之间存在着沟通障碍。这正是我一直在努力通过我的技能去做的事情,就是找到正确的措辞。

而且智能体非常擅长向你展示不同措辞的机会——实际上非常擅长领域建模。

Latent Space:

When do we directly use the grill-me skill, versus wayfinder?

Latent Space:

我们什么时候直接使用 grill-me 技能,而不是 wayfinder?

Pocock:

Use ‘grill me’ in cases where you feel like you can plan the whole thing in a single session, and you need to align before you go.

So most small features will fit into this. Most stuff where you can see the path ahead of you, but you just want to make sure the agent is on board, ‘grill me’ will work with that.

Via

wayfinder documentation

For stuff where you don’t know the path ahead, for stuff where you can feel the fog of war in front of you, use wayfinder. You’re gonna find your way with wayfinder. So that’s how it works.

Pocock:

当你觉得可以在单个会话中规划整个事情,并且在开始之前需要对齐时,使用“grill me”。

所以大多数小功能都适合这种方式。大多数你能看清前路、但只是想确保智能体理解到位的情况,“grill me”都能胜任。

经由

wayfinder 文档

对于你不知道前路的情况,对于你能感受到前方“战争迷雾”的情况,请使用 wayfinder。你会用 wayfinder 找到你的路。就是这样运作的。