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.
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.
Honestly, this is one of the things OpenAI does pretty well, I think, these tiny design decisions that you wouldn't notice until it becomes super annoying.
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.
simonw is a fine contributor to HN and we're lucky to have him.
I realize that for some people there is too much LLM-related content and (therefore?) too much by certain authors, but that has always been the case for certain topics and certain authors in HN's history. This is a side effect of the frontpage being the same for everyone, and therefore the scarcest resource.
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.
> I haven’t been involved with Django since leaving the Journal-World back in September, but now that the framework is open-sourced I look forward to contributing to its further development—both in terms of documentation and actual code.
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!
If I use Codex in one session on desktop can I then resume it for cloud and mobile sessions as Work? Or do I have to make separate sessions each time? Or rather, can Codex in the cloud do the same things, if such a thing exists?
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.
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.
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.
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.
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:
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.
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.
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.
Two sources of truth, if playwright updates?
Honestly, this is one of the things OpenAI does pretty well, I think, these tiny design decisions that you wouldn't notice until it becomes super annoying.
I'm guessing, but can be because then the skill will always fetch the latest docs.
No, that makes too much sense
See this comment for background (and creation prompt): https://news.ycombinator.com/item?id=49504625#49505116
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.
[flagged]
simonw is a fine contributor to HN and we're lucky to have him.
I realize that for some people there is too much LLM-related content and (therefore?) too much by certain authors, but that has always been the case for certain topics and certain authors in HN's history. This is a side effect of the frontpage being the same for everyone, and therefore the scarcest resource.
https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
Simon is not the OP. He’s just commenting on his own work. How is that spam?
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.
Simon, thank you for your comments and the great content you create. I've learned a lot from your blogposts and your experiments.
You don't know, SimonW made Django Python framework?
Chuckling at a Python reference in a comment thread arguing about spam.
Didn't he leave the project before it even had an official release?
https://simonwillison.net/2005/Jul/17/django/
> I haven’t been involved with Django since leaving the Journal-World back in September, but now that the framework is open-sourced I look forward to contributing to its further development—both in terms of documentation and actual code.
Having done a thing does not make a person into a demigod embodiment for life, please remember that guys.
I share the sentiment of the parent (downvoted) commenter.
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!
I don't get how this is different from Codex if Codex can do all the same things.
ChatGPT Work in the ChatGPT desktop app is effectively Codex with a different skin. It can operate on your local files in the same way.
ChatGPT Work in the ChatGPT web and mobile app experience is very different.
If you like, you can think of it as a cloud-hosted version of Codex that's skinned to look more like consumer ChatGPT.
If I use Codex in one session on desktop can I then resume it for cloud and mobile sessions as Work? Or do I have to make separate sessions each time? Or rather, can Codex in the cloud do the same things, if such a thing exists?
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.
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.
Because most AI generated websites are from people who don't know much and as such cannot even articulate the look they want
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.
I told it "Design aesthetic should be technical docs, minimal flare" - full prompt here: https://news.ycombinator.com/item?id=49504625#49505116
[dupe] Discussion on associated blog post: https://news.ycombinator.com/item?id=49504625
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...
Which provider currently lives up to your moral code?