site: getting-started scaffolds SIX meta init skills, not five (add metaobjects-audit)

meta init's SKILL_NAMES scaffolds 6 skills (authoring/codegen/runtime-ui/prompts/verify/audit);
getting-started.html + llms-full.txt said five. Fixes the onboarding-page skill count.

Author: dmealing

www/getting-started.html

@@ -84,12 +84,13 @@ <h3>Set up the project and the agent context</h3>
 ├── metaobjects.config.ts        <span class="c"># ← targets: dialect + what to generate</span>
 ├── CLAUDE.md                    <span class="c"># wired to auto-load the context below</span>
 ├── .metaobjects/                <span class="c"># tool state + agent docs (AGENTS.md, CLAUDE.md)</span>
-└── .claude/skills/              <span class="c"># five skills your agent now has:</span>
+└── .claude/skills/              <span class="c"># six skills your agent now has:</span>
     ├── metaobjects-authoring/   <span class="c">#   write &amp; edit models</span>
     ├── metaobjects-codegen/     <span class="c">#   run codegen</span>
     ├── metaobjects-runtime-ui/  <span class="c">#   wire up runtime + UI</span>
     ├── metaobjects-prompts/     <span class="c">#   typed LLM prompts</span>
-    └── metaobjects-verify/      <span class="c">#   drift checks</span></pre>
+    ├── metaobjects-verify/      <span class="c">#   drift checks</span>
+    └── metaobjects-audit/       <span class="c">#   check adoption depth</span></pre>
         </div>
       </div>
     </section>

www/llms-full.txt

@@ -34,7 +34,7 @@ If you are an AI assistant helping someone adopt MetaObjects, do this **first**
    - Java / Kotlin: add `com.metaobjects:metaobjects-metadata`, `com.metaobjects:metaobjects-codegen-spring` (Java) or `com.metaobjects:metaobjects-codegen-kotlin` (Kotlin), and `com.metaobjects:metaobjects-maven-plugin`, all at `7.11.3`.
    - Python: `pip install metaobjects`
    - C#: install the MetaObjects .NET tool (invoked as `dotnet meta`).
-2. **Run `meta init`** (the Node `meta` CLI). It works in any project that has Node — including a JVM or Python project with a TypeScript frontend. It scaffolds a slim always-on `.metaobjects/AGENTS.md` + `.metaobjects/CLAUDE.md` (auto-wired via an `@.metaobjects/AGENTS.md` import line into the project's root `CLAUDE.md`/`AGENTS.md`, so it loads automatically) plus five `metaobjects-*` Claude Code skills under `.claude/skills/`, carrying only the project's language reference fragments. Re-run `meta init --refresh-docs` to update the agent docs after a CLI upgrade. (The Node `meta` CLI is the single agent-context scaffolder for every backend, by design — ADR-0033; the JVM/Python/C# CLIs deliberately redirect to it. For a non-Node project, scaffold just the agent context with `npx meta agent-docs --server <lang>`.)
+2. **Run `meta init`** (the Node `meta` CLI). It works in any project that has Node — including a JVM or Python project with a TypeScript frontend. It scaffolds a slim always-on `.metaobjects/AGENTS.md` + `.metaobjects/CLAUDE.md` (auto-wired via an `@.metaobjects/AGENTS.md` import line into the project's root `CLAUDE.md`/`AGENTS.md`, so it loads automatically) plus six `metaobjects-*` Claude Code skills under `.claude/skills/`, carrying only the project's language reference fragments. Re-run `meta init --refresh-docs` to update the agent docs after a CLI upgrade. (The Node `meta` CLI is the single agent-context scaffolder for every backend, by design — ADR-0033; the JVM/Python/C# CLIs deliberately redirect to it. For a non-Node project, scaffold just the agent context with `npx meta agent-docs --server <lang>`.)
 3. **Load `.metaobjects/AGENTS.md` and the `.claude/skills/metaobjects-*` skills.** They teach metadata authoring, codegen, runtime/UI, prompt construction, and `verify` — for this project's exact stack and version.
 
 This file is the short corpus; the deep, version-matched how-to is the scaffolded local context.