ChatGPT Work Tool and Skill Reference

iijidak about 2 hours ago 39 commentsRead Article on codex-tool-reference.simonw.chatgpt.site

FR version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

100% Positive

Analyzed from 715 words in the discussion.

Discussion (39 Comments)Read Original on HackerNews

simonw•about 2 hours ago

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.

jw1224•4 minutes ago

I've used a similar technique with my own tools. It helps to save context overall, by deferring the detailed instructions not only to when they're needed, but also to where they're needed.

Simply loading the browser Skill alone, doesn't always mean a browser is actually necessary (or supported). The user might've want them to control their main desktop browser; or the user might be pointing them toward a read-only HTML file that doesn't need rendering; or the sandbox might prevent network access; etc...

Codex is especially 'keen' to use Skills (especially by comparison to Claude), I often see it load Skills which it doesn't go on to use, because the main Skill content says "when not to use this". So I'm sure this is a product design decision to help with those kinds of circumstances.

lanyard-textile•about 1 hour ago

It's runtime dependent on the browser being used! A skill file wouldn't be able to have this dynamically injected for the browser that's about to be used.

Skill file could indicate general instructions for all browsers. This provides guidance for the browser that's about to actually be used.

newswasboring•about 1 hour ago

I'm guessing, but can be because then the skill will always fetch the latest docs.

ChrisGreenHeur•about 1 hour ago

No, that makes too much sense

simonw•about 2 hours ago

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

cebert•5 minutes ago

Simon, thanks for all the great work you do. I definitely appreciate your contributions to discussion threads here as well as your blog. I learned so much from you.

owebmaster•about 2 hours ago

Simon, stop using this forum to spam on every opportunity.

roseway4•about 1 hour ago

Simon is not the OP. He’s just commenting on his own work. How is that spam?

yoavm•about 2 hours ago

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

NoDodgeQuestion•about 2 hours ago

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

rob•about 1 hour ago

Didn't he leave the project before it even had an official release?

Cheyana•about 1 hour ago

Chuckling at a Python reference in a comment thread arguing about spam.

bewareofscams•33 minutes ago

Having done a thing does not make a person into a demigod embodiment for life, please remember that guys.

simonw•about 2 hours ago

My comment here is entirely justified in this case.

Someone else submitted my vibe-coded slop site to the front page without any context, and it accumulated enough votes to show up at the top.

I could have linked to my blog post about it, but instead I linked to a Hacker News comment precisely because I anticipated complaints about "spamming" if I linked to my blog.

bewareofscams•33 minutes ago

I share the sentiment of the parent (downvoted) commenter.

bingemaker•about 2 hours ago

I totally agree!

infecto•about 2 hours ago

I just tune out every post that says “I wrote about this already” and then links to it. Simon is great and kudos for his self promotion but it’s interesting to see as it’s often called out for anyone else.

The guy is good but he certainly stretches the limit. I just auto ignore his stuff but I know others enjoy!

satvikpendem•41 minutes ago

I don't get how this is different from Codex if Codex can do all the same things.

ChrisArchitect•about 1 hour ago

[dupe] Discussion on associated blog post: https://news.ycombinator.com/item?id=49504625

felixgallo•about 1 hour ago

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...

nickthegreek•15 minutes ago

Which provider currently lives up to your moral code?

enraged_camel•about 2 hours ago

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?

simonw•about 2 hours ago

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.

tsunamifury•44 minutes ago

This can be replaced, you just have to do the work of building a design library yourself and the guidance components. Then building skills around their use.

Almondsetat•24 minutes ago

Because most AI generated websites are from people who don't know much and as such cannot even articulate the look they want

newswasboring•about 1 hour ago

I think these guideline are built into the llms. After all with llms, any decision you don't take will be taken for you. For a so called slop site (Simon's words, not mine :P) I don't think they specified a style so the llm just decided the default it knows. One day I will run experiments (when I can afford it) trying to identify the "taste" of different llms.