From nimble
Builds Databricks data products from live web data: discovers Nimble agents, scrapes into Delta tables, produces AI/BI dashboards or Databricks Apps.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nimble:nimble-databricks-data-productsThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn a natural-language brief like
Turn a natural-language brief like
pricing analysis on dog products from walmart and amazon into working Databricks data products:
discover agents → ingest live web search data into Delta → build dashboard and/or app → deliver links.
Equally at home for a quick demo or a real, reusable data product.
You are the orchestrator. Databricks mechanics are delegated to the official databricks-*
skills (see references/databricks-skills.md); this skill owns the Nimble glue and the gaps
(agent discovery, ingestion-from-agents, the AI/BI dashboard JSON, branding).
nimble_agent_list(), input params via
nimble_agent_describe('<agent>'), and output fields by probing one call (to_json(parsing[0])) —
never hardcode from memory (Amazon search takes keyword, not query).;-separated statements in one call are a parse error.cd don't persist — set them inline. See references/preflight.md.references/branding.md.Track these as todos so nothing is skipped.
Lean on the databricks-core skill for the generic checks.
databricks current-user me → confirm auth; capture the username (for the default schema).databricks warehouses list. Prefer one already RUNNING; if none, offer to start one.nimble_integration.tools.{nimble_search, nimble_extract, nimble_agent_run, nimble_agent_list, nimble_agent_describe}.
Quick check: databricks functions list nimble_integration tools.
If missing → STOP and walk the user through references/install-nimble-integration.md
(Nimble cookbook). Do not try to auto-install.catalog.schema
(default users.<username>). Verify writability — some shared catalogs deny CREATE TABLE.
Present the recommendation and let the user confirm or override before writing.Details + exact commands: references/preflight.md.
Parse the brief into: domain/entity · search terms · sources · analysis goal. Then ask (batch into one AskUserQuestion call):
Keep the brief's intent (the "analysis goal") — it picks the Phase 4 template and the headline.
See references/nimble-agents.md.
nimble_agent_list() via SQL, filter by the source/domain keywords.nimble_agent_describe('<name>') → read its input params (required ones,
exact names, localization/pagination flags). Output fields come from the §2.5 probe, not here.source column + a normalized core
(product_name, price, currency, rating, review_count, brand, url, …), keeping only fields the
chosen agents actually emit. Multi-source comparison hinges on the shared columns.See references/nimble-agents.md for the full SQL. Drive ingestion from a control table, not
per-keyword files — it's reproducible and expandable (add a row, re-run).
0. Probe ONE call per source first (fail fast). Before fanning out, run a single
nimble_agent_run per source and check: status, the real field names, the localization flag, and
whether a price casts cleanly. This catches the Walmart-class surprises (localization, currency-
string prices, product_price vs price) in ~40s instead of after a wasted full round. Highest-
leverage step — see nimble-agents.md §2.5.
<schema>.<table>_queries (source, agent, keyword,
params_json, localization, enabled) and seed one row per (source × term). params_json uses each
agent's real param name (from input_properties); set localization per agent (e.g.
amazon_serp true, walmart_serp false).source column + normalized core + raw VARIANT).nimble_agent_run(q.agent, q.params_json, q.localization) via a
correlated LATERAL join over the control table, with a /*+ REPARTITION(N) */ hint (N ≈ enabled
rows, kept modest — high parallelism can trip API rate limits) so the agent calls run in parallel.
It's one long statement → run it async with bash scripts/ingest.sh <WH> ingest.sql.nimble-agents.md §6 for the diagnostic order.Choose a template from the matched agents' vertical/entity_type:
| Vertical | Dashboard/app shape |
|---|---|
| Ecommerce (SERP/PDP/CLP) | KPIs; listings & avg price by source/keyword; sponsored share; price-vs-rating scatter; product table with Open links; multi-source → comparison bars + best-effort item-level price gap |
| Social | volume/engagement by account/post; top-content table; like/follower distributions |
| Real Estate | price & price/sqft; listings by location; beds/baths breakdowns |
| Maps / Local | avg rating; review counts; places table |
| LLM / AEO | source/answer presence; share-of-voice; citation table |
| fallback | KPIs + 2 categorical bars + the raw table (works off any output_schema) |
Comparison depth (hybrid): always build the aggregate/category comparison; additionally try best-effort item-level matching across sources (normalize brand + key tokens). If confident matches exist, add a "same-product price gap" view; otherwise keep the aggregate comparison and note that item-level matching wasn't confident.
scripts/build_dashboard.py (compact spec → valid serialized_dashboard,
create + publish). It bakes in every Lakeview gotcha. Read references/dashboard-cookbook.md for
the spec format and recipes.references/app-cookbook.md (delegates scaffold/deploy to databricks-apps;
adds the Nimble-specific SQL, branding, and the numeric-string / light-mode gotchas).references/branding.md (always applied).RUNNING; collect URLs.competitor-intel / company-deep-dive for
business signals on the brands surfaced, or nimble-web-expert for a one-off deeper pull.references/databricks-skills.md — which official databricks-* skill to use per phase.references/install-nimble-integration.md — setup when the integration gate fails.references/preflight.md — auth, warehouse, writable-schema discovery (exact commands).references/nimble-agents.md — discovery, schema mapping, ingestion SQL + gotchas.references/dashboard-cookbook.md — Lakeview JSON recipes + every gotcha (authoritative).references/app-cookbook.md — AppKit demo app glue + gotchas.references/branding.md — "Powered by Nimble", logo, colors.scripts/ingest.sh — async statement fan-out + poll.scripts/build_dashboard.py — compact spec → create + publish a dashboard.assets/nimble-logo.png — the Nimble mark for app branding.npx claudepluginhub nimbleway/agent-skills --plugin nimbleBuilds apps on Databricks Apps platform for dashboards, data apps, analytics tools, and visualizations. Evaluates analytics vs Lakebase data access patterns before scaffolding.
Creates, updates, deploys Databricks AI/BI (Lakeview) dashboards with mandatory SQL query testing via execute_sql before deployment.
Expert guidance for Azure Databricks covering troubleshooting, best practices, architecture, deployment, Unity Catalog, Delta Live Tables, Model Serving, and Databricks SQL. Activates when working with Azure Databricks tools and services.