<div dir="ltr">Hi,<br><br>First, about why it is like this now.<br><br>AGENTS.md: I set it up like this when making web-based hosted `codex` to cleanly implement tasks. It starts with almost empty docker every time and if you don't steer it to install dependencies or run tests it tends to skip those and leave fixes half baked. This is what protects postgis from a storm of bad AI PRs.<br><br>skills: started from <a href="https://lists.osgeo.org/pipermail/postgis-devel/2025-November/030663.html">https://lists.osgeo.org/pipermail/postgis-devel/2025-November/030663.html</a> where Mat Arye requested the input on the skills of postgis to be included into their pg-aiguide mcp. I've pulled up the postgis-related AGENTS lines that I have on my production workflows and added it there. Later they had feedback that some of it was overlapping the postgres skills they have elsewhere, thus the split.<br><br>Now, the concerns I heard:<br><br> - Paul's concern is that AGENTS is too specific. I agree it might be, but it did not cause any problems for me so far - it clearly marks assumptions at the top and agents nowadays (7 months is a lot of time...) seem smart enough to see if it's not their precise case. What happens in practice is that it skips over the parts of installing dependencies if they're available through other means and on the developer machine that ends up fine. If you have observed actual issues, I'd be happy to adjust it. <br><br> - Sandro's concern that skills need to be moved elsewhere. I agree here that location is up for discussion. In general, it is no different from the docs and probably can live under docs. <br><br>The reason we need separate "kind" of docs for LLMs is because they are different kind of consumer: normal users "don't know anything" when starting to work with PostGIS and need basic introduction. LLMs "have seen it all" around the internet, and instead need to rapidly unlearn the bad and obsolete examples and be guided toward latest best practices, while specifically calling out the ones replaced by it. There's too many ST_Buffer(geom,0) on the internet to get it to pick ST_MakeValid as a first option without it. I think it may be useful for humans too, as a cheat sheet or something like that.<br><br>I don't think it belongs in a separate repo any more than docs belong to a separate repo (and I hope this will not trigger "let's move docs out to separate repo").<br><br>Another thing that may be useful to get raised: how tied are we to having docs as xml? I think gdal moved to rst and it has made it a little easier to navigate the sources of the docs on the file level.<br><br>Thanks,<br>Darafei.<br><br></div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Tue, Jun 9, 2026 at 1:36 PM Sandro Santilli <<a href="mailto:strk@kbt.io">strk@kbt.io</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">On Mon, Jun 08, 2026 at 11:01:06AM -0700, Paul Ramsey wrote:<br>
<br>
> I do know I was a little nonplussed to read it and find it spelling out<br>
> in specificity a development setup that… was nothing like what I do,<br>
> and therefore would lead any agent I happened to use absolutely astray.<br>
<br>
That spelling is also present in AGENTS.md since its introduction<br>
in commit d7c5ead4d9998d34b6a7753bf757981ffdefb326 (Sat Oct 18 00:15:20 2025 +0400)<br>
<br>
The file format is documented in <a href="https://agents.md/" rel="noreferrer" target="_blank">https://agents.md/</a>, which rightfully<br>
doesn't mention a specific tool, so I'd be in favor of steering that<br>
file ALSO in a way that is more open-source and local-inference-first<br>
friendly.<br>
<br>
Darafai: what do you think ? Since it was you introducing both AGENTS.md<br>
and the skill/s directory, I'd prefer if was you driving any change.<br>
<br>
--strk;<br>
</blockquote></div>