docs: add generated agent prompt catalog section (UAX-192) (#4945)

Add an automated prompt catalog section to the agentic skills page. The
combined docs build fills its insertion marker from the evaluation
source, avoiding a manually maintained prompt list. Keep the evaluation
context and fixture guidance in this page so docs reviewers can edit it
independently of the generator. Existing workflow examples remain in
place.

Part of UAX-192.

Depends on https://github.com/lancedb/docs/pull/434; merge that docs
pipeline change first. Validation: combined assembly and Mintlify
validation pass.

docs/web/basics/agentic-skills.mdx

@@ -78,6 +78,24 @@ Not every agent supports project scope; `npx plugins targets` lists what it
 found and what each target supports.
 </Accordion>
 
+## Automated prompt catalog {#automated-prompts}
+
+Explore the prompts covered by automated agent evaluations. Each prompt uses
+example data and may require existing tables,
+indexes, metadata, branches, version history, or running jobs. Replace the test
+fixtures and connection details with your own before using a prompt.
+
+The evaluations run against a LanceDB Enterprise test database, with and
+without the agent plugin. Evaluation coverage does not guarantee success for
+every agent or model.
+
+Prompts are reproduced verbatim, including the answer formats used by automated
+grading. Table names, local files, and placeholders in these prompts refer to
+test fixtures. Supply your own data, database connection, and timestamps when
+adapting them.
+
+{/* agent-eval-catalog */}
+
 ## Example prompts {#example-prompts}
 
 These prompts show the kind of work the plugin helps an agent get right on