Content updates

Author: Pabl0cks

packages/nextjs/content/blog/ai-native-ethereum-stack.md

@@ -24,23 +24,21 @@ We added Cursor rules to Scaffold-ETH 2 as an early way to give agents project c
 
 ### Skills over scripts
 
+We've started stripping out custom skills wherever we find that a model just naturally handles the task better.
+
 **/add-extension** Adding a Scaffold-ETH extension used to mean resolving `package.json` conflicts through hundreds of lines of template processing code. We replaced it with `/add-extension`, a simple agent skill built to work across different harnesses. `Node.js` handles the deterministic operations (fetching, copying), while the AI handles the judgment calls (merging).
 
-**/pr-create** Same pattern for developer workflow. `/pr-create` is a markdown file that tells an agent how to inspect the diff, format the PR body, and open it via `gh`. No custom script. No alias. Just context.
+**/pr-create** Same pattern for developer workflow. `/pr-create` is a markdown file that tells an agent how to inspect the diff, format the PR body, and open it via `gh`. No custom script, no alias, just context.
 
-We've started stripping out custom scripts wherever we find that a model just naturally handles the task better.
+The same pattern extends to Ethereum protocol knowledge. SE-2 now has a library of domain skills: `erc-20`, `erc-721`, `eip-5792`, `cip-712`, `siwe`, `ponder`, `solidity-security`, `defi-protocol-templates`. Each is a focused context file the agent loads before touching that part of the stack. No hunting for docs or hallucinated ABIs. The agent knows the protocol before it writes the first line.
 
 ### AI-assisted code review
 
 Code review is a perfect fit for AI judgment.
 
 Take [Grumpy Carlos](https://github.com/technophile-04/grumpy-carlos-personality-fetcher): a Claude Code subagent with a review personality inferred from scraped BuidlGuidl PR history. Drop it in `.claude/agents/`, ask for a review, and it responds exactly the way Carlos would: specific, strict, no vague feedback.
 
----
-
-The right context, structured for an AI to use, produces better output than general AI applied to problems without context.
-
-Security stays deterministic. Wallet interactions, transaction signing, and key management require hard boundaries. An agent making onchain transactions autonomously is an attack surface. That problem isn't solved yet.
+> Human review is still important, but AI review is a great first pass.
 
 ## Rethinking How We Teach
 

packages/nextjs/pages/blog/[slug].tsx

@@ -12,9 +12,12 @@ const components: Record<string, any> = {
     <h2 className="text-secondary font-bold text-lg sm:text-xl mt-10 mb-1">{children}</h2>
   ),
   h3: ({ children }: { children?: React.ReactNode }) => (
-    <h3 className="text-white/90 font-semibold text-base sm:text-lg mt-8 mb-1 pl-3 border-l-2 border-secondary/40">
+    <h3 className="text-white/90 font-semibold text-base sm:text-lg mt-8 mb-1">{children}</h3>
+  ),
+  blockquote: ({ children }: { children?: React.ReactNode }) => (
+    <blockquote className="border-l-2 border-secondary/40 pl-4 py-1 my-4 bg-white/[0.03] rounded-r text-white/50 italic">
       {children}
-    </h3>
+    </blockquote>
   ),
   a: ({ href, children }: { href?: string; children?: React.ReactNode }) => {
     const isExternal = href?.startsWith("http");