Update agent skills to e0647ba6804a08bc727c2c58a0f4cd9774da1313 (#214)

databricks-ci-ghec-1[bot] · web-flow · commit 11298facf5a4 · 2026-07-16T05:55:07.000Z
Automated update of the agent skills content.

Co-authored-by: databricks-ci-ghec-1[bot] &lt;184311507+databricks-ci-ghec-1[bot]@users.noreply.github.com&gt;
diff --git a/.gen.json b/.gen.json
@@ -1,3 +1,3 @@
 {
-  "source_commit": "acb84dd139848f31215fafe966bd15615119286a"
+  "source_commit": "e0647ba6804a08bc727c2c58a0f4cd9774da1313"
 }
diff --git a/README.md b/README.md
@@ -97,6 +97,7 @@ exposes experimental skills.
 Stable skills shipped from [`skills/`](./skills/):
 
 - **databricks-core** — CLI, authentication, profile selection, data exploration. Parent skill for all product skills.
+- **databricks-data-discovery** — Find, explore, and query data via Genie One (natural-language data Q&A and SQL generation); falls back to manual `information_schema` exploration.
 - **databricks-apps** — Build full-stack TypeScript apps on Databricks using AppKit.
 - **databricks-app-design** — Design the UX of data apps: dashboards, KPI pages, reports, charts, and Genie/chat surfaces, mapped to AppKit components.
 - **databricks-dabs** — Declarative Automation Bundles (formerly Asset Bundles) for deploying and managing Databricks resources.
diff --git a/experimental/README.md b/experimental/README.md
@@ -59,7 +59,8 @@ Promoted skills include `databricks-ai-functions`, `databricks-agent-bricks`,
 `databricks-mlflow-evaluation`, `databricks-python-sdk`,
 `databricks-spark-structured-streaming`, `databricks-synthetic-data-gen`,
 `databricks-unity-catalog`, `databricks-unstructured-pdf-generation`, and
-`databricks-zerobus-ingest`.
+`databricks-zerobus-ingest`. `databricks-data-discovery` (Genie One data
+discovery / NL data Q&A / SQL generation) was also promoted to stable.
 
 Earlier experimental copies of `databricks-bundles`, `databricks-lakebase-autoscale`,
 and `databricks-config` were merged into the stable
diff --git a/experimental/databricks-data-discovery/assets/databricks.png b/experimental/databricks-data-discovery/assets/databricks.png
diff --git a/metaplugin/plugin.meta.json b/metaplugin/plugin.meta.json
@@ -84,6 +84,7 @@
   "//skills": "Per-skill plugin metadata. Insertion order defines the keyword order in plugin.json: keywords = keywords_lead + [each skill's keyword] + keywords_tail. Repo-owned (does NOT live in SKILL.md frontmatter, which syncs from the internal source). Prompt-routing config lives in the separate routing block below.",
   "skills": {
     "databricks-core": { "keyword": "cli" },
+    "databricks-data-discovery": { "keyword": "data-discovery" },
     "databricks-apps": { "keyword": "apps" },
     "databricks-app-design": { "keyword": "app-design" },
     "databricks-lakebase": { "keyword": "lakebase" },
@@ -144,7 +145,12 @@
       "\\bserverless\\s+(compute|warehouse|migration)\\b",
       "\\bmedallion\\s+(architecture|tables?)\\b",
       "\\bsql\\s+warehouse\\b",
-      "\\bauto\\s+loader\\b"
+      "\\bauto\\s+loader\\b",
+      "\\bwhat\\s+tables?\\b",
+      "\\bwhich\\s+(catalog|schema)\\b",
+      "\\b(list|show|find)\\s+(the\\s+)?tables?\\b",
+      "\\bwhere\\s+does\\s+.{1,40}\\s+(data|table|live)\\b",
+      "\\binformation_schema\\b"
     ],
     "suppress": [
       "\\bbigquery\\b",
@@ -170,7 +176,7 @@
       { "label": "Lakebase / Postgres", "skill": "databricks-lakebase" },
       { "label": "Vector Search / RAG", "skill": "databricks-vector-search" },
       { "label": "Classic-to-serverless migration", "skill": "databricks-serverless-migration" },
-      { "label": "Genie / natural-language data Q&A", "skill": "databricks-core", "note": " (Genie CLI support is experimental)" },
+      { "label": "Data discovery / finding & exploring data / natural-language data Q&A / SQL generation (Genie)", "skill": "databricks-data-discovery" },
       { "label": "Agent Bricks / Knowledge Assistants / Genie Spaces / Multi-Agent Supervisor", "skill": "databricks-agent-bricks" },
       { "label": "AI Functions (ai_query, ai_classify, ai_extract, ai_parse_document)", "skill": "databricks-ai-functions" },
       { "label": "AI/BI dashboards", "skill": "databricks-aibi-dashboards" },
diff --git a/skills/databricks-core/SKILL.md b/skills/databricks-core/SKILL.md
@@ -21,9 +21,9 @@ For specific products, use dedicated skills:
 
 For **data discovery, exploration, and query generation** — finding tables,
 answering natural-language questions about the data, or generating SQL — use
-**databricks-data-discovery** if it is installed (experimental; it asks Genie One
-first, then falls back to manual exploration). If it isn't installed, use the
-AI-tool commands below and [Manual Data Exploration](manual-data-exploration.md).
+**databricks-data-discovery** (it asks Genie One first, then falls back to manual
+exploration). If it isn't installed, use the AI-tool commands below and
+[Manual Data Exploration](manual-data-exploration.md).
 
 ## Prerequisites
 
diff --git a/skills/databricks-data-discovery/SKILL.md b/skills/databricks-data-discovery/SKILL.md
@@ -1,9 +1,9 @@
 ---
 name: databricks-data-discovery
-description: "Discover, explore, and query Databricks data via Genie — the CLI equivalent of the Genie One MCP. MUST be invoked whenever the user asks to find or locate data ('what tables are in X', 'where does X live', 'which catalog/schema has Y'), explore or profile a table, answer a natural-language question about the data, or write a SQL query."
+description: "Discover, explore, and query Databricks data via Genie — the CLI equivalent of the Genie One MCP. MUST be invoked whenever the user asks to find or locate data ('what tables are in X', 'where does X live', 'which catalog/schema has Y'), answer a natural-language question about the data, or write a SQL query."
 compatibility: Requires databricks CLI with the experimental genie command (databricks experimental genie ask)
 metadata:
-  version: "0.0.1"
+  version: "0.1.0"
 parent: databricks-core
 ---
 
@@ -109,11 +109,15 @@ set up.
 
 ## If Genie One isn't available — manual fallback
 
+Only fall back if Genie One is genuinely unavailable — first **verify** with
+`databricks experimental genie ask --help`; don't assume the command is missing.
 When Genie One isn't enabled, the CLI is too old to have `experimental genie ask`,
 or Genie can't cover the question, do the discovery yourself with the parent skill's
-commands — see **[Manual Data Exploration](../../skills/databricks-core/manual-data-exploration.md)**
+commands — see **[Manual Data Exploration](../databricks-core/manual-data-exploration.md)**
 (keyword search via `information_schema`, `discover-schema`, and `tools query`).
 Running known SQL or profiling a known table that way is perfectly fine on its own.
+Do **not** default to `databricks tables list` or raw UC REST for data-location
+questions — invoke this skill and ask Genie first.
 
 ## Relationship to the Genie One MCP
 
@@ -126,8 +130,8 @@ the same Genie backend.
 
 ## Related Skills
 
-- **[databricks-genie](../databricks-genie/SKILL.md)** — build and manage **Genie
-  Agents**: curated agents that let you or a group ask questions of specific data
-  (create, configure, import/export).
+- **databricks-genie** (experimental) — build and manage **Genie Agents**: curated
+  agents that let you or a group ask questions of specific data (create, configure,
+  import/export).
 - **databricks-core** (parent) — CLI auth, profiles, and the manual data exploration
   reference used as the fallback.
diff --git a/skills/databricks-data-discovery/agents/openai.yaml b/skills/databricks-data-discovery/agents/openai.yaml
diff --git a/skills/databricks-data-discovery/assets/databricks.png b/skills/databricks-data-discovery/assets/databricks.png
diff --git a/skills/databricks-data-discovery/assets/databricks.svg b/skills/databricks-data-discovery/assets/databricks.svg
diff --git a/skills/databricks-jobs/references/triggers-schedules.md b/skills/databricks-jobs/references/triggers-schedules.md
@@ -98,6 +98,8 @@ Format: `seconds minutes hours day-of-month month day-of-week`
 
 Run jobs at fixed intervals (simpler than cron).
 
+**Prefer periodic over cron** for a regular fixed cadence (hourly, daily, weekly): it takes just an `interval` and `unit` and does not pin a clock time. Use cron only when the schedule needs a specific time-of-day or day-of-week.
+
 ### DABs YAML
 
 ```yaml
diff --git a/skills/databricks-unstructured-pdf-generation/SKILL.md b/skills/databricks-unstructured-pdf-generation/SKILL.md
@@ -16,7 +16,7 @@ Workflow for producing **synthetic PDF documents + paired test questions** as a
 1. Write HTML files to `./raw_data/html/` (write multiple files in parallel for speed) — domain-shaped to match the documents your retrieval pipeline will see in production.
 2. Convert HTML → PDF using `<SKILL_ROOT>/scripts/pdf_generator.py` (parallel conversion, wraps `plutoprint`).
 3. Upload PDFs to a Unity Catalog volume via `databricks fs cp` — same volume shape your production pipeline will read from.
-4. Generate `doc_questions.json` pairing each document with retrieval-eval questions; this becomes the gold dataset for `mlflow.genai.evaluate()` or comparable retrieval-quality scorers.
+4. Generate `./raw_data/pdf/pdf_eval_questions.json` pairing each document with retrieval-eval questions; this becomes the gold dataset for `mlflow.genai.evaluate()` or comparable retrieval-quality scorers.
 
 > If you only need ad-hoc PDFs (no Databricks workflow), any HTML → PDF tool (`weasyprint`, `wkhtmltopdf`, `playwright pdf`, `plutoprint`) works directly — this skill exists for the synthetic-dataset-on-UC end-to-end shape, not as a general PDF generator.
 
@@ -47,15 +47,15 @@ Skips files where PDF exists and is newer than HTML. Use `--force` to reconvert
 
 ## Step 3: Upload to Volume
 
-`databricks fs` requires the `dbfs:` scheme prefix even for UC Volume paths. `-r` copies the *contents* of the source directory into the target (the source directory name is not preserved), so files land directly under `raw_data/`.
+`databricks fs` requires the `dbfs:` scheme prefix even for UC Volume paths. `-r` copies the *contents* of the source directory into the target (the source directory name is not preserved), so name the target `raw_data/pdf` explicitly to keep the PDFs in their own folder on the volume. They land under `raw_data/pdf/` — i.e. `dbfs:/Volumes/my_catalog/my_schema/raw_data/pdf/report.pdf` — so a Knowledge Assistant or ingest pipeline can point at that single folder.
 
 ```bash
-databricks fs cp -r --overwrite ./raw_data/pdf dbfs:/Volumes/my_catalog/my_schema/raw_data
+databricks fs cp -r --overwrite ./raw_data/pdf dbfs:/Volumes/my_catalog/my_schema/raw_data/pdf
 ```
 
 ## Step 4: Generate Test Questions
 
-Create `./raw_data/pdf/pdf_eval_questions.json` with questions for Knowledge Assistant evaluation or MAS:
+Create `./raw_data/pdf/pdf_eval_questions.json` with questions for Knowledge Assistant (KA) or Multi-Agent Supervisor (MAS) evaluation. It's fine for this file to be uploaded to the volume alongside the PDFs — downstream agents can use it:
 
 ```json
 {
@@ -115,6 +115,16 @@ Subfolder structure is preserved:
     └── terms.html          →           └── terms.pdf
 ```
 
+## Bundled Script
+
+This skill ships one helper script:
+
+| File | Description |
+|------|-------------|
+| [scripts/pdf_generator.py](scripts/pdf_generator.py) | HTML → PDF converter (wraps `plutoprint`); parallel folder conversion with timestamp-skip. Referenced by Step 2 and the CLI Reference. |
+
+The script ships at `<SKILL_ROOT>/scripts/pdf_generator.py`. If it is absent, recreate it from the [CLI Reference](#cli-reference) above (a `convert` subcommand taking `--input`/`--output`/`--force`/`--workers`, wrapping `plutoprint` for HTML → PDF).
+
 ## Troubleshooting
 
 | Issue | Solution |

Original file line number	Diff line number	Diff line change
`@@ -1,3 +1,3 @@`
`1`	`1`	`{`
`2`		`- "source_commit": "acb84dd139848f31215fafe966bd15615119286a"`
	`2`	`+ "source_commit": "e0647ba6804a08bc727c2c58a0f4cd9774da1313"`
`3`	`3`	`}`