docs: point generator references at the content collection

The build-skill-review.mjs command now regenerates skill-reviews/improved/
from src/content/reviews/*.md, not from skills-review/catalog.js. Update the
essential-commands line in AGENTS.md and the review desk footer in
skills-review/index.html to match. Until task 16 rewires the review desk page
to read the collection, new submissions still need a mirrored entry in the
legacy catalog.js — the footer spells that out explicitly.

Co-Authored-By: Claude Code <noreply@anthropic.com>

AGENTS.md

@@ -26,7 +26,7 @@ labs are dependency-free HTML/CSS/JS that workshop attendees point an agent at.
 ```bash
 pnpm run verify     # content + interaction contracts (scripts/verify.mjs) — the gate
 node scripts/audit-ui.mjs          # responsive / no-external-dependency audit
-node scripts/build-skill-review.mjs # regenerate skill-reviews/improved/ from catalog.js
+node scripts/build-skill-review.mjs # regenerate skill-reviews/improved/ from src/content/reviews/
 pnpm run serve      # python3 -m http.server 4173
 ```
 
@@ -52,7 +52,7 @@ so.
   _is_ that they are dependency-free vanilla HTML/CSS/JS an attendee can hand to
   an agent. Componentizing them destroys the lesson. They ship as static assets.
 - `submitted-skills/` — other people's submitted work, reproduced verbatim
-- `skill-reviews/improved/` — generated; edit `skills-review/catalog.js` instead
+- `skill-reviews/improved/` — generated; edit `src/content/reviews/*.md` instead
 - `vote-service/` — separate deploy lifecycle; do not fold into the site build
 - `dist/`, `node_modules/` — build output, never committed
 - `pnpm-lock.yaml` — **committed, but never hand-edited.** Change it only as a

skills-review/index.html

@@ -38,7 +38,7 @@
       <p>The recommendations follow the open Agent Skills format: valid frontmatter for discovery, progressive disclosure for context economy, deterministic scripts for fragile repeated mechanics, and behavioral evaluation rather than a checklist of pretty headings.</p>
       <div><a href="https://agentskills.io/specification" target="_blank" rel="noreferrer">Format specification ↗</a><a href="https://agentskills.io/skill-creation/best-practices" target="_blank" rel="noreferrer">Writing practices ↗</a><a href="https://agentskills.io/skill-creation/evaluating-skills" target="_blank" rel="noreferrer">Evaluation loop ↗</a><a href="https://agentskills.io/skill-creation/using-scripts" target="_blank" rel="noreferrer">Scripts guide ↗</a></div>
     </section>
-    <footer>Share an author with <code>?author=Name</code>, or one review with <code>?author=Name&amp;skill=skill-id&amp;view=improved</code>. To add a submission later: drop a package under <code>submitted-skills/</code>, add a tailored entry in <code>skills-review/catalog.js</code>, then run <code>node scripts/build-skill-review.mjs</code>. Votes call a separate service — see <code>vote-service/</code> — one per visitor, tracked by network source.</footer>
+    <footer>Share an author with <code>?author=Name</code>, or one review with <code>?author=Name&amp;skill=skill-id&amp;view=improved</code>. To add a submission later: drop a package under <code>submitted-skills/</code>, add an entry under <code>src/content/reviews/{new-id}.md</code> (and mirror it into <code>skills-review/catalog.js</code> until task 16 rewires the page to read the collection), then run <code>node scripts/build-skill-review.mjs</code>. Votes call a separate service — see <code>vote-service/</code> — one per visitor, tracked by network source.</footer>
   </main>
   <script type="module" src="app.js?v=20260904-vote-widget"></script>
 </body>