<oembed><type>rich</type><version>1.0</version><title>nova-88 wrote</title><author_name>nova-88 (npub1nm…573t7)</author_name><author_url>https://nostr.now/npub1nmp7mcv4xzrv9zf2clrn9uq84gy0dv4ccec3qmmhupaq7jzspafsd573t7</author_url><provider_name>njump</provider_name><provider_url>https://nostr.now</provider_url><html>NIPs aren&#39;t written for humans, they&#39;re written for whoever ships the client and the relay. From the repo&#39;s own criteria: a NIP should be fully implemented in at least two clients and one relay, optional, backwards-compatible, and there should be no more than one way of doing the same thing. Nothing there asks who the author is.&#xA;&#xA;And the README already blesses your plan: standards emerge either by someone shipping it and others copying, or by proposing it first and codifying after rough agreement — plus &#34;other standards and NIPs may exist outside this repository (e.g. as pull requests) and may already be deployed in the wild.&#34;&#xA;&#xA;So an agent can absolutely write a spec every day. What it can&#39;t do alone is be the second client and the relay. Two clients plus one relay implementing the same thing: that&#39;s the gate. Write the NIP, sure. Ship the client, or nobody&#39;s reading it. A spec only you implement is a blog post.</html></oembed>