From uipath
Authors and deploys UiPath governance policies: AOps product policies for feature control (Studio, AI Trust Layer, Agent Builder) and access policies for cross-workflow invocations.
How this skill is triggered — by the user, by Claude, or both
Slash command
/uipath:uipath-governanceThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Uber skill for UiPath governance authoring. Two backing CLI surfaces:
references/access-policy/access-policy-commands.mdreferences/access-policy/access-policy-overview-guide.mdreferences/access-policy/planning-arch.mdreferences/access-policy/planning-impl.mdreferences/access-policy/plugins/actor/impl.mdreferences/access-policy/plugins/actor/planning.mdreferences/access-policy/plugins/executable/impl.mdreferences/access-policy/plugins/executable/planning.mdreferences/access-policy/plugins/selector/impl.mdreferences/access-policy/plugins/selector/planning.mdreferences/access-policy/plugins/tags/impl.mdreferences/access-policy/plugins/tags/planning.mdreferences/access-policy/policy-manage-guide.mdreferences/access-policy/resource-lookup-guide.mdreferences/access-policy/sample-policy-guide.mdreferences/aops-policy/aops-governance-recipes-guide.mdreferences/aops-policy/aops-policy-commands.mdreferences/aops-policy/aops-policy-deploy-guide.mdreferences/aops-policy/aops-policy-deployed-guide.mdreferences/aops-policy/aops-policy-manage-guide.mdUber skill for UiPath governance authoring. Two backing CLI surfaces:
| Surface | Governs | CLI |
|---|---|---|
| AOps product policy | Product feature behavior — what Studio / StudioX / Assistant / Robot / AI Trust Layer / Agent Builder can do at design-time / runtime | uip gov aops-policy |
Access policy (ToolUsePolicy) | Resource/tool-use boundary — when an Actor Process invokes a child Resource (Agent / Maestro / Flow / RPA / API / Case Management), is the call allowed? | uip gov access-policy |
Both surfaces share verbs (block, restrict, deny, allow, require, enforce). The same English sentence often maps to either layer, so this skill classifies first and only then routes to the matching mechanic.
Activate on any governance / policy / rule intent — even when the user did not name the underlying CLI:
policy / rule / guardrail / govern / gate / control requestsblock / restrict / deny / disable / disallow an action, model, app, URL, agent, flow, or processrequire / enforce / mandate a behavior or ruleallow only / permit only / limit to / restrict to Xwho can / which … can / on behalf of — actor- or identity-shaped governancecompliance / posture / audit framing on top of policiesSibling redirects:
uipath-platformuipath-agents / uipath-rpa / uipath-maestro-flowreferences/disambiguation-guide.md. Never start create / update / delete until classification is settled — by user wording or by the disambiguation question.uip login before any uip gov … command. evaluate (Access) additionally requires tenant-scoped login — see access-policy-overview-guide.md § Critical Rules.references/disambiguation-guide.md — it lists the strong signals for each branch, the phrase patterns that need disambiguation, and the canonical worked example. If a strong signal matches, route silently. If the phrasing is ambiguous (matches both branches), ask the disambiguation question and wait for a digit reply. If the user replies with anything other than 1 or 2, treat it as a re-statement of intent and re-classify. Do not run any CLI command before classification is settled — the disambiguation question itself does not need uip, and an unrelated request (platform ops, agent authoring) must redirect to a sibling skill before any setup happens here.uip and login (only after classification routes to a governance branch).
which uip && uip --version
uip login status --output json
If not installed: npm install -g @uipath/uipcli. If not logged in: uip login (--authority <URL> for non-prod). For Access evaluate, login MUST be tenant-scoped.When the user's intent fits both branches, render exactly this numbered list (no AskUserQuestion, no table) and wait for a digit reply:
### Which layer should this rule govern?
1. **Govern the product** — control what Studio / StudioX / Assistant / Robot / AI Trust Layer / Agent Builder *can do* (e.g. block ChatGPT inside Studio, enforce Workflow Analyzer, disable a Marketplace widget). Backed by `uip gov aops-policy`.
2. **Govern resource/tool use** — control which Actor Processes / identities can *invoke* which child Resource as a tool (e.g. block agents tagged `Sandbox` from being called, only let the finance group trigger this Flow). Backed by `uip gov access-policy`.
Reply with the number.
The canonical ambiguous prompt is "Block ChatGPT for my finance team using Studio." See references/disambiguation-guide.md for the worked-out reasoning of why both interpretations produce a working but different artifact.
| I need to... | Read |
|---|---|
| Decide which branch a request belongs to (priors, phrase tables, worked example) | references/disambiguation-guide.md |
| Author an AOps product policy | references/aops-policy/aops-policy-overview-guide.md |
| Deploy an AOps policy to user / group / tenant | references/aops-policy/aops-policy-deploy-guide.md |
| Query the deployed AOps policy / effective rules | references/aops-policy/aops-policy-deployed-guide.md |
| Author an Access ToolUsePolicy | references/access-policy/access-policy-overview-guide.md |
| Look up CLI flags / output shapes (AOps) | references/aops-policy/aops-policy-commands.md |
| Look up CLI flags / output shapes (Access) | references/access-policy/access-policy-commands.md |
| Resolve a name to a UUID for Access | references/access-policy/resource-lookup-guide.md |
uipath-platform.npx claudepluginhub uipath/skills --plugin uipathUiPath platform operations via the uip CLI — Orchestrator, Integration Service, LLM Gateway, auth, folders, assets, queues, jobs, webhooks, BYO LLM keys, traces, licensing. Load before any UiPath API call.
Encodes human-readable governance policies into machine-executable JSON constraints for AI agents and CI pipelines to validate automatically. Outputs rule files in .ai/governance/.
Governs Power Automate flows and Power Apps at scale via FlowStudio MCP store: classifies by business impact, detects orphans, audits connectors, enforces compliance, manages notifications, computes scores.