docs: clarify create-expert as a published registry expert

README.md

@@ -36,7 +36,7 @@ A game built with these commands: [demo-dungeon-crawler](https://github.com/pers
 
 ## How it works
 
-`create-expert` generates a `perstack.toml` that defines a team of micro-agents. Run it with `npx perstack start create-expert`. Each agent has a single responsibility and its own context window. Complex tasks are broken down and delegated to specialists.
+`create-expert` is a published Expert on the [Perstack registry](https://perstack.ai/). It generates a `perstack.toml` that defines a team of micro-agents. No local config file is needed — the CLI resolves `create-expert` from the registry automatically. Each agent has a single responsibility and its own context window. Complex tasks are broken down and delegated to specialists.
 
 ```toml
 [experts."ai-gaming"]

docs/README.md

@@ -5,7 +5,7 @@ title: "Perstack: The Declarative Runtime for Agentic AI"
 Define AI agents as **Experts** in natural language. Execute them with deterministic, event-derived tracking. Each Expert runs in its own isolated context — no shared state, no prompt bloat, full execution history.
 
 - [Getting Started →](./getting-started/walkthrough.md)
-- [Browse Registry →](https://platform.perstack.ai/)
+- [Browse Registry →](https://perstack.ai/)
 
 ## What Perstack Solves
 
@@ -35,7 +35,7 @@ Collaborate with `pro-trainer` for professional training menus.
 delegates = ["pro-trainer"]
 ```
 
-Or generate one interactively:
+Or generate one interactively using [`create-expert`](https://perstack.ai/), a published Expert on the Perstack registry:
 
 ```bash
 npx perstack start create-expert "Create a fitness assistant that delegates to a pro trainer"

docs/getting-started/walkthrough.md

@@ -23,7 +23,7 @@ Generate an Expert definition interactively:
 npx perstack start create-expert "Create a fitness assistant that delegates to a pro trainer"
 ```
 
-`create-expert` does more than scaffold a file — it:
+`create-expert` is a published Expert on the [Perstack registry](https://perstack.ai/) — no local config file is needed. The CLI resolves it from the registry automatically. It does more than scaffold a file — it:
 - generates Expert definitions in `perstack.toml` based on your description
 - tests them against real-world scenarios
 - analyzes execution history and output to evaluate the definitions

docs/guides/rapid-prototyping.md

@@ -46,7 +46,7 @@ npx perstack start reviewer "Review this login handler"
 
 ## From idea to agent in one command
 
-Writing TOML by hand works, but there's a faster way. `create-expert` is a published Expert that generates Expert definitions from natural language descriptions — it's itself an Expert that builds other Experts.
+Writing TOML by hand works, but there's a faster way. `create-expert` is a published Expert on the [Perstack registry](https://perstack.ai/) that generates Expert definitions from natural language descriptions — it's itself an Expert that builds other Experts. No local config is needed; the CLI resolves it from the registry automatically.
 
 ```bash
 npx perstack start create-expert "A code review assistant that checks for security vulnerabilities, suggests fixes, and explains the reasoning behind each finding"

docs/index.md

@@ -12,7 +12,7 @@ Define AI agents as **Experts** in natural language. Execute them with determini
 Perstack is an open-source runtime for executing AI agents defined as Experts. Define behavior in TOML, run from the CLI or embed in your application.
 
 ```bash
-# Generate an Expert interactively
+# Generate an Expert using create-expert (a published Expert on the Perstack registry)
 npx perstack start create-expert "Create a code-reviewer that delegates to a style-checker"
 
 # Run it

e2e/perstack-cli/create-expert.test.ts

@@ -0,0 +1,22 @@
+import { describe, expect, it } from "bun:test"
+import { assertEventSequenceContains } from "../lib/assertions.js"
+import { runCli, withEventParsing } from "../lib/runner.js"
+
+const LLM_TIMEOUT = 120000
+
+describe("Published create-expert", () => {
+  it(
+    "should resolve from registry and complete a run",
+    async () => {
+      const cmdResult = await runCli(["run", "create-expert", "hello"], {
+        timeout: LLM_TIMEOUT,
+      })
+      const result = withEventParsing(cmdResult)
+      expect(result.exitCode).toBe(0)
+      expect(assertEventSequenceContains(result.events, ["startRun", "completeRun"]).passed).toBe(
+        true,
+      )
+    },
+    LLM_TIMEOUT,
+  )
+})