ChatGPT Work Tool and Skill Reference • Hacker News Board

Re: ChatGPT Work Tool and Skill Reference

#11

Post by simonw » Mon, Aug 31, 2026, 2:37 PM UTC

I think the most interesting skill here is the control-browser one: https://codex-tool-reference.simonw.chatgpt.site/skills/cont...

It tells ChatGPT Work how to launch a Playwright instance via its Node.js REPL, and tells it to run:

  nodeRepl.write(await browser.documentation());

To get further instructions.

That method returns this text with full details about how to use the browser: https://codex-tool-reference.simonw.chatgpt.site/skills/cont...

I'd love to know why it's defined like that, as opposed to including all of the instructions directly in the skill Markdown file.

Re: ChatGPT Work Tool and Skill Reference

#12

Post by yoavm » Mon, Aug 31, 2026, 2:38 PM UTC

owebmaster wrote: post #3

simonw wrote: post #2

See this comment for background (and creation prompt): https://news.ycombinator.com/item?id=49504625#49505116

[flagged]

Simon, thank you for your comments and the great content you create. I've learned a lot from your blogposts and your experiments.

Re: ChatGPT Work Tool and Skill Reference

#13

Post by simonw » Mon, Aug 31, 2026, 2:38 PM UTC

rvz wrote: post #8

simonw wrote: post #7

Earlier quoted context omitted.

What am I "doing" here?

[flagged]

How is this comment "spam"? Spell it out for me.

(I think you may be confusing "spam" with "prolific". I write a lot.)

Re: ChatGPT Work Tool and Skill Reference

#14

Post by simonw » Mon, Aug 31, 2026, 2:42 PM UTC

enraged_camel wrote: post #9

Meta comment: I've been wondering why AI-generated websites/artifacts/reports always have the same "look". It reminds me of Bootstrap (CSS Framework) days when every startup website looked the same. Are they following some sort of common guideline?

In this case they really are, and you can read the guidelines that helped create the site on the site itself in the skills: https://codex-tool-reference.simonw.chatgpt.site/skills/site...

Scroll down to the "Establish the visual direction" section.

Re: ChatGPT Work Tool and Skill Reference

#15

Post by NoDodgeQuestion » Mon, Aug 31, 2026, 2:46 PM UTC

owebmaster wrote: post #3

simonw wrote: post #2

See this comment for background (and creation prompt): https://news.ycombinator.com/item?id=49504625#49505116

[flagged]

You don't know, SimonW made Django Python framework?

Re: ChatGPT Work Tool and Skill Reference

#16

Post by rvz » Mon, Aug 31, 2026, 2:48 PM UTC

simonw wrote: post #13

rvz wrote: post #8

Earlier quoted context omitted.

[flagged]

How is this comment "spam"? Spell it out for me. (I think you may be confusing "spam" with "prolific". I write a lot.)

Once again, continues to gaslight after spamming a post with another top-posted comment after having to “justify” it. In this case, You already admitted to it.

There is just no end or need to rapidly post on every opportunity that involves “AI” or whatever that is related to it.

Re: ChatGPT Work Tool and Skill Reference

#17

Post by simonw » Mon, Aug 31, 2026, 2:51 PM UTC

rvz wrote: post #16

simonw wrote: post #13

Earlier quoted context omitted.

How is this comment "spam"? Spell it out for me. (I think you may be confusing "spam" with "prolific". I write a lot.)

Once again, continues to gaslight after spamming a post with another top-posted comment after having to “justify” it. In this case, You already admitted to it. There is just no end or need to rapidly post on every opportunity that involves “AI” or whatever that is related to it.

Seriously, what's your definition of spam?

Or an easier question: how am I gaslighting here? You should be able to spell that out.

(You do understand that the top linked site here was built by me, but has no authorship information on it at all, right? That's why I posted a comment explaining what it is.)

Re: ChatGPT Work Tool and Skill Reference

#18

Post by filmgirlcw » Mon, Aug 31, 2026, 2:55 PM UTC

rvz wrote: post #8

simonw wrote: post #7

Earlier quoted context omitted.

What am I "doing" here?

[flagged]

Someone else posted his site to HN, not Simon. He responds with additional context and also responds to links to other HN comments he’s made rather than just linking back to his own site. The only person gaslighting here is you.

Re: ChatGPT Work Tool and Skill Reference

#19

Post by felixgallo » Mon, Aug 31, 2026, 2:56 PM UTC

Anyone using ChatGPT Work given Sam Altman's richly documented history(1), the essential elimination and/or public exit of the safety function at OpenAI(2), and the huggingface debacle's exposure of the abject operational, cultural and technical failures at OpenAI(3), is making a serious mistake.

(1) https://www.newyorker.com/magazine/2026/04/13/sam-altman-may... (2) https://thenextweb.com/news/openai-preparedness-team-disband... (3) https://thezvi.wordpress.com/2026/08/29/metr-and-redwood-off...

Re: ChatGPT Work Tool and Skill Reference

#20

Post by nswizzle31 » Mon, Aug 31, 2026, 2:57 PM UTC

simonw wrote: post #13

rvz wrote: post #8

Earlier quoted context omitted.

[flagged]

How is this comment "spam"? Spell it out for me. (I think you may be confusing "spam" with "prolific". I write a lot.)

Spam = excessive promotion of your work. It’s not one comment, but the entire context of all your comments.

Gaslighting because it’s so OBVIOUS that this is what people are referring to by “spam” that you almost have to be purposely pretending to not understand. Such a prolific writer simply has to be aware of the fine line where promoting your work becomes excessive.

Not taking sides here.