The Exchanges

Every argument clarity score on this site is built from rows on this page. Each question and answer was assessed with names hidden, the host's own answers included, on four things from 1 to 5: directness (does it answer the question asked), coherence (do the ideas follow), precision (concrete details and clear references), compression (says a lot per word). The weighted mix (30/30/25/15) is the exchange score. A person's published score averages their exchange scores on raw tape only, at least 8 of them, shrunk toward the cohort mean. Full method →

Nevo David no published score: no usable exchanges on raw tape, and a fair score needs 8+ record → ← everyone

Every exchange below was scored with names hidden, four dimensions each from 1 to 5. An exchange's score is 0.30·directness + 0.30·coherence + 0.25·precision + 0.15·compression. The published score averages the raw tape exchange scores and shrinks small samples toward the cohort mean, so five great answers can't beat twenty good ones. Produced feed rows count only toward coarse estimates, never toward a full score.

clear all ✕
1exchanges match
0on raw tape
0redirected or not addressed
Answered produced feed D 5 · C 4 · P 4 · Cm 4 4.30

Q zooming out and understanding this clearly. What you're saying is, Agents really need good documentation. You didn't write it yourself. You didn't leave it to them to figure it out for themselves. You used Claude to say, you know, my software document what other agents are going to need to know in order to use it. And then you packaged it up as a skill. Am I understanding that right?

A Yes, but it's not only that. So I could create two types of skills. I could just, like, say to Claude, listen, you see that my docs, just create a skill around it, and actually docs are already kind of a skill, because docs are MD file already, apparently, so. But I wanted to do something better, because if you actually, like, let's, let's take, for example, um, the actual docs. And in the actual docs, let's say I'm going here to the public API. In order to create a post, you need to send a post request to this URL. Here, like tons of different things you can send and so on. That's a lot of content. So I could definitely just take it like that. But we simplified it a lot. I just told Claude, because let's face the truth, who is writing code these days? Uh, I just told Claude, take all my public API and create and turn it into a CLI. Um, so this is the first thing he did, and then I pushed it to npm.js. So if you've been, like, if you see in the top of the skill here, you first need to install the post is command line before you even, before you even start to, to write, like, to do whatever is inside the skill. Okay. And then, because now everything is so short, because imagine this, post is integration list, give you all the list of integrations that you have. If you don't do this, if you do it with the API, you need to do list integrations. So you need, like, all this API, lon…

AI assessment note: “Yes, but it's not only that. So I could create two types of skills.”

page 1
Made with StarZero

Turn any episode into a week of clips.

This entire site, about 40 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.