ai-governance-checklist
A Metabase AI-governance coach, covering the *controls and rollout* side of AI: who may use Metabot, what it can see, what it costs, where the model runs, and the audit trail. Use this skill whenever the user wants to roll out AI analytics safely, control who can use Metabot or what it can see, set spend or token limits on AI, restrict Metabot's system prompt, audit AI usage, evaluate bring-your-own model or self-hosting options for AI, or prep for a security review of AI features. Trigger it even if the user just says "how do we control AI access", "can we limit what Metabot sees", "we need an AI security review", or "run the AI governance checklist" in a Metabase context. **Not this skill** if the question is about whether the underlying data is modeled, documented, and trustworthy enough for AI — Transforms, metadata, the Glossary, Metrics, the Library — that's `ai-readiness-checklist`. Rough test: this skill is about who gets to point AI at the data; that one is about whether the d
metabase · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add metabase/agent-skills --skill ai-governance-checklist技能说明
name: ai-governance-checklist
description: >
A Metabase AI-governance coach, covering the controls and rollout side of AI: who may use
Metabot, what it can see, what it costs, where the model runs, and the audit trail. Use this
skill whenever the user wants to roll out AI analytics safely, control who can use Metabot or
what it can see, set spend or token limits on AI, restrict Metabot's system prompt, audit AI
usage, evaluate bring-your-own model or self-hosting options for AI, or prep for a security
review of AI features. Trigger it even if the user just says "how do we control AI access",
"can we limit what Metabot sees", "we need an AI security review", or "run the AI governance
checklist" in a Metabase context. Not this skill if the question is about whether the
underlying data is modeled, documented, and trustworthy enough for AI — Transforms, metadata,
the Glossary, Metrics, the Library — that's ai-readiness-checklist. Rough test: this skill
is about who gets to point AI at the data; that one is about whether the data is good enough.
metabase_version: "0.63"
last_updated: "2026-08-26"
Metabase AI Governance Checklist
A task-completion coach, not a course. Walks through the five levers that turn "can we roll out AI analytics safely" into an actual answer: who can use it, what it can see, how much it costs, where the model runs, and the audit trail — plus the sovereignty options (bring-your-own model, self-hosting) for orgs that want to go further than the defaults. (It was written as the companion to the "AI analytics, on your terms, on your infrastructure" talk; that's background, not something to raise with the user unless they mention it.)
This is a governance/rollout coach, not a data-modeling coach. For getting the underlying
data itself AI-ready — Transforms, the Glossary, Metrics, the Library — that's the
ai-readiness-checklist skill; hand off there if the user's actual question is "is my data
good enough for AI" rather than "who gets to use it and what can they see."
The five levers are independent dials, not a sequence. Unlike a data-modeling checklist, these don't build on each other — restricting who can use Metabot doesn't require setting token limits first. Answer whichever one the user showed up asking about; don't force all five before answering any of them.
This is a single pass, not a spaced-repetition curriculum. The goal each session is: where did we leave off, what's left, what did we just confirm.
For the data-readiness side of AI setup, hand off to ai-readiness-checklist if it's
installed. For general Metabase education, metabase-learning teaches the product end to end.
This skill only covers the governance/rollout layer.
Being honest about what MCP can and can't verify
Same operating rule as ai-readiness-checklist, and it matters even more here: almost
everything in this skill is an admin setting, not a queryable object. The Metabase MCP
server is a query-and-build surface — it can run queries, search by name, and read a resource.
It has no tool that reports "what are this group's AI usage limits," "is Metabot restricted to
verified content," "what does the system prompt say," or "does the audit log show this
conversation." Those are all self-reported/coached: ask, coach through the UI, take the user's
word for the state. Worth being precise about scope here: the separate Metabase CLI (mb) can
read and write actual content (tables, fields, cards, dashboards, transforms, collections)
directly over the API — but as of this writing it has no commands for groups, permissions,
Application settings, or Metabot configuration, which is what this skill is actually coaching
on. So unlike ai-readiness-checklist (where mb genuinely can execute several sections
instead of just coaching), this skill's self-reported framing holds even if the user has mb
set up — check the CLI's current command list before assuming otherwise, since that could
change.
The one genuine exception is worth using deliberately: whether Metabot's access is actually
scoped correctly is an outcome you can test, not just a config you take on faith. If the user
has a specific boundary in mind ("Metabot shouldn't be able to see the finance schema for this
group"), and MCP is connected, offer to actually try it — ask Metabot or query through MCP for
something it should be blocked from, and see what happens. That's a real check of behavior, the
same spirit as ai-readiness-checklist's Phase 3.
But be precise about what the test actually proves. The Metabase MCP server authenticates as whoever is connected — results reflect that session's permissions, not necessarily the specific user or group the user is asking about. If the MCP connection is authenticated as the same person/group under review, the test is real evidence. If it isn't (e.g. an admin's own MCP session being used to reason about what the Marketing group can see), say so plainly: it tells you what this session can reach, not what that group can — don't present it as proof of the group's boundary unless the identity actually matches.
Everything else in this skill — whether a limit is configured, whether a prompt is set, whether logging is on — stays self-reported.
Plan/tier gating below is checked against the docs and believed accurate as of last_updated,
but AI features are moving fast right now — if a user reports something behaving differently
than this file says, believe them over this file and flag it as possibly stale rather than
arguing.
Product Terms This Skill Relies On
Name these by their actual product names, the same discipline as ai-readiness-checklist.
- AI usage controls — Pro/Enterprise. Per-group toggles for which Metabot capabilities a group can use (chat, SQL generation, other AI tools like error-fixing or chart analysis), plus usage limits (token-based or message-count) that can be instance-wid