databricks-ai-bi-genie

databricks-ai-bi-genie is a skill for Claude Code from VincentChuWaiChow/vanguard-frontier-agentic. It costs 112 tokens per session (3,233 once invoked), scanned A, original, Apache-2.0.

A review method for Databricks AI/BI Genie agents and dashboards. Genie lets people ask questions about business data in natural language; the method checks its data scope, metric definitions, benchmarks, rendering limits, caching, and permissions.

In plain words
What is it for?
Use it to review Genie agent scope, metric views, benchmark results, dashboard behavior, and the choice between individual and shared data access.
Why use it?
It helps prevent unreliable answers, poorly scoped data access, and dashboard settings that expose data beyond intended users. It also supports more honest interpretation of accuracy tests.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the vanguard-frontier-agentic plugin — 193 skills shipped together

Good fit Use it to review Genie agent scope, metric views, benchmark results, dashboard behavior, and the choice between individual and shared data access.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vincentchuwaichow/vanguard-frontier-agentic/databricks-ai-bi-genie
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add VincentChuWaiChow/vanguard-frontier-agentic --skill databricks-ai-bi-genie
Clone the repo
git clone --depth 1 https://github.com/VincentChuWaiChow/vanguard-frontier-agentic

Made for: Claude Code.

Or install vanguard-frontier-agentic, the plugin that ships this one along with the rest of its 193 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for databricks-ai-bi-genie

README.md
[![agentmods](https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/databricks-ai-bi-genie/github.svg)](https://agentmods.dev/skills/vincentchuwaichow/vanguard-frontier-agentic/databricks-ai-bi-genie)
Your own site
<a href="https://agentmods.dev/skills/vincentchuwaichow/vanguard-frontier-agentic/databricks-ai-bi-genie"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/databricks-ai-bi-genie/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for databricks-ai-bi-genie

Your own site · 80×15
<a href="https://agentmods.dev/skills/vincentchuwaichow/vanguard-frontier-agentic/databricks-ai-bi-genie"><img src="https://agentmods.dev/badge/skills/vincentchuwaichow/vanguard-frontier-agentic/databricks-ai-bi-genie.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,233 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 69
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 61
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.03233
Opus 5 $0.00056 $0.01617
Sonnet 5 $0.00022 $0.00647
Haiku 4.5 $0.00011 $0.00323

Measured 8d ago against content hash eced35b14376, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

databricks-ai-bi-genie scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/databricks/databricks-ai-bi-genie/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

databricks-ai-bi-genie

Purpose

This skill decides whether a Genie agent and dashboard are correctly scoped, semantically grounded via metric views, and configured with data permissions that match their intended audience. A Genie agent is usable only when it is scoped to <= 30 tables, backed by correct metric-view definitions, and has been benchmarked honestly with LLM-judge confidence reported with its margin of error. A dashboard is safe only when rendering caps are respected, caching policies are documented, and the 'Individual data' versus 'Share data' permission choice is made explicitly with security review. The 'Share data' setting completely bypasses row-level security — this is the single highest-consequence configuration decision.

When to use

  • A Genie agent or dashboard configuration is being reviewed before deployment, or when an agent is performing unexpectedly.
  • A user asks whether a Genie agent is scoped correctly (table count, instruction count, throughput), or whether metric views are defining the semantic layer correctly.
  • A user is interpreting benchmark results and wants to know whether the LLM-judge accuracy is sufficient for production.
  • A user is deciding between 'Individual data' and 'Share data' permissions and needs to understand the row-filter/column-mask consequences.

When NOT to use

  • No agent or dashboard configuration is provided — ask for it rather than assuming.
  • The concern is query speed or warehouse tuning — route to databricks-sql-performance-agent.
  • The concern is row-filter or column-mask implementation in Unity Catalog — route to databricks-unity-catalog-governance-agent.
  • The concern is data privacy or compliance — route to databricks-data-protection-privacy-agent.
  • A request to execute a Genie agent query or run a dashboard live.

Scope

  • Genie agent scoping: 30-table-or-view limit, 10,000 conversations/10,000 messages per conversation, 100 instructions per agent, 20 questions-per-minute throughput.
  • Instructions and trusted assets: parameterized SQL query caching and exact-text matching for verification marking.
  • Metric views and semantic layer: definition correctness, measure/dimension design, parameter and window-measure status (PUBLIC PREVIEW features flagged).
  • Dashboard limits and rendering: 15 pages, 100 datasets, 100 widgets per page, 10,000 rows for charts (100,000 for tables), 100,000 distinct filter values.
  • Benchmark design and accuracy: LLM-judge confidence (88.1% +/- 5.5%), Cohen's kappa (0.64 +/- 0.13), one-week visibility, and margin-of-error interpretation.
  • 'Individual data' versus 'Share data': row filter and column mask enforcement per viewer (Individual) versus complete bypass (Share).

Read the full file on GitHub · 133 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 133 lines · 112 tokens per session scan A eced35b14376

Subscribe to this mod's changes

databricks-ai-bi-genie is a skill published in the GitHub repository VincentChuWaiChow/vanguard-frontier-agentic (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 112 tokens to every session and 3,233 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.