@uipath/skills 1.199.0 → 1.200.0

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
       "name": "uipath",
       "source": "./",
       "description": "UiPath plugin for Claude Code — custom skills, agents, hooks, and MCP servers for UiPath workflows, UI automation, UI testing and UiPath troubleshoot",
-      "version": "1.199.0",
+      "version": "1.200.0",
       "author": {
         "name": "UiPath"
       },

package/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "uipath",
-  "version": "1.199.0",
+  "version": "1.200.0",
   "description": "UiPath plugin for Claude Code — custom skills, agents, hooks, and MCP servers for UiPath RPA workflows, UI automation, UI testing, Python coded agents and UiPath troubleshoot",
   "author": {
     "name": "UiPath"

package/CODEOWNERS

@@ -71,15 +71,15 @@
 /tests/tasks/activation/uipath-functions.jsonl @AlexBizon @UiPath/team-coded-agents
 
 # Planner skill (PDD → SDD design + multi-skill task planning)
-/skills/uipath-planner/ @RaduAna-Maria
-/tests/tasks/uipath-planner/ @RaduAna-Maria
+/skills/uipath-planner/ @RaduAna-Maria @abhiram-vad
+/tests/tasks/uipath-planner/ @RaduAna-Maria @abhiram-vad
 
 # Solution skill (uip solution lifecycle)
 /skills/uipath-solution/ @UiPath/team-merlot @UiPath/team-orange
 /tests/tasks/uipath-solution/ @UiPath/team-merlot @UiPath/team-orange
 
 # Flow skill
-/skills/uipath-maestro-flow/ @bai-uipath @rockymadden @gozhang2 @tmatup @akshaylive @jiyangzh @nikhil-maryala @baishalighosh @DevMomo
+/skills/uipath-maestro-flow/ @bai-uipath @rockymadden @gozhang2 @tmatup @akshaylive @jiyangzh @nikhil-maryala @baishalighosh @DevMomo @chandusailella @mukundbayyaram
 # Flow test tasks (general) — more specific subfolder rules below override this
 /tests/tasks/uipath-maestro-flow/ @bai-uipath @rockymadden @gozhang2 @tmatup @akshaylive @jiyangzh @nikhil-maryala @baishalighosh @DevMomo
 
@@ -105,19 +105,20 @@
 /tests/tasks/uipath-maestro-case/guardrails/ @apetraru-uipath @valentinabojan @ctiliescuuipath
 
 # Coded Apps skill
-/skills/uipath-coded-apps/ @Raina451 @deepeshrai-tech @Sandeepan-Ghosh-0312 @swati354
-/tests/tasks/uipath-coded-apps/ @Raina451 @deepeshrai-tech @Sandeepan-Ghosh-0312 @swati354
+/skills/uipath-coded-apps/ @Raina451 @deepeshrai-tech @Sandeepan-Ghosh-0312 @swati354 @ninja-shreyash
+/tests/tasks/uipath-coded-apps/ @Raina451 @deepeshrai-tech @Sandeepan-Ghosh-0312 @swati354 @ninja-shreyash
 
 # Connector Builder skill
 /skills/uipath-connector-builder/ @mukeshkumar-uipath @chandusailella @apoosarla-uipath
 /tests/tasks/uipath-connector-builder/ @mukeshkumar-uipath @chandusailella @apoosarla-uipath
+/tests/tasks/activation/uipath-connector-builder.jsonl @mukeshkumar-uipath @chandusailella @apoosarla-uipath
 
 # Flow skill — plugin guides (away team owned)
 # Add your team here when contributing a new plugin category
 /skills/uipath-maestro-flow/references/plugins/connector/ @baishalighosh @chandusailella @bai-uipath @rockymadden @DevMomo
 /skills/uipath-maestro-flow/references/plugins/connector-trigger/ @baishalighosh @chandusailella @bai-uipath @rockymadden @DevMomo
 /skills/uipath-maestro-flow/references/author/references/plugins/inline-agent/ @AlexandruCGhimisi @andreibalas-uipath @al3xanndru
-/tests/tasks/uipath-maestro-flow/connector_features/ @baishalighosh
+/tests/tasks/uipath-maestro-flow/connector_features/ @baishalighosh @chandusailella @mukundbayyaram
 
 # IXP
 /skills/uipath-maestro-flow/references/author/references/plugins/ixp/ @jcalero @constantinmuraru @scallaway-uipath @tommilligan @joe-prosser @vlad-crisan @richsilv @AWilcke
@@ -160,8 +161,8 @@
 /skills/uipath-ixp/ @cezara98t @paul-ciobanu @misupantea-uipath @andrei-uipath @alexandrujircan
 /tests/tasks/uipath-ixp/ @cezara98t @paul-ciobanu @misupantea-uipath @andrei-uipath @alexandrujircan
 # MCP skill (UiPath AgentHub MCP server registration + tool authoring)
-/skills/uipath-mcp-servers/ @cosminpaunel @UiPath/team-coded-agents
-/tests/tasks/uipath-mcp-servers/ @cosminpaunel @UiPath/team-coded-agents
+/skills/uipath-mcp-servers/ @cristipufu @UiPath/team-coded-agents
+/tests/tasks/uipath-mcp-servers/ @cristipufu @UiPath/team-coded-agents
 
 # Insights skill (job monitoring and analytics)
 /skills/uipath-insights/ @suranabhavya @rliuup
@@ -169,3 +170,8 @@
 
 # Automation Discovery skill
 /skills/uipath-automation-discovery/ @uisherif
+
+# Process Mining skill (process apps, data ingestion, dbt transformations)
+/skills/uipath-process-mining/ @UiPath/team-backendhoven
+/tests/tasks/uipath-process-mining/ @UiPath/team-backendhoven
+/tests/tasks/activation/uipath-process-mining.jsonl @UiPath/team-backendhoven

package/README.md

@@ -1,5 +1,7 @@
 # UiPath Agent Skills
 
+[![skills.sh](https://www.skills.sh/b/uipath/skills)](https://www.skills.sh/uipath/skills)
+
 > [!NOTE]
 > **Work in Progress** — This repository is under active development. Skills are being added and refined. Contributions, feedback, and ideas are welcome! See [Contributing](#contributing) below.
 
@@ -40,6 +42,18 @@ After installing, verify with `node -v` and then run the quick start command abo
 
 </details>
 
+### Try a skill without installing anything
+
+To evaluate a single skill before adopting the whole set, use the [`skills` CLI](https://www.skills.sh) — no UiPath CLI and no project changes required:
+
+```bash
+npx skills add UiPath/skills --list              # browse the catalog
+npx skills use UiPath/skills@uipath-rpa | claude # run one skill; nothing is written to your project
+npx skills add UiPath/skills --skill uipath-rpa  # install just that one skill
+```
+
+> **For ongoing use, prefer `uip skills install` above.** It detects every coding agent on your machine and keeps skills updated as they change; `npx skills add` installs a point-in-time copy that you must update yourself with `npx skills update`.
+
 ## Skill Catalog
 
 The repository ships skills covering authoring, platform operations, and diagnostics for UiPath automations.
@@ -105,9 +119,10 @@ Every skill's maturity is tracked in [`assets/skill-status.json`](assets/skill-s
 | `uipath-maestro-flow` | In-development |
 | `uipath-mcp-servers` | In-development |
 | `uipath-planner` | Preview |
-| `uipath-platform` | Preview |
+| `uipath-platform` | Stable |
+| `uipath-process-mining` | Preview |
 | `uipath-review` | Preview |
-| `uipath-rpa` | Preview |
+| `uipath-rpa` | Stable |
 | `uipath-solution` | Preview |
 | `uipath-tasks` | Preview |
 | `uipath-test` | In-development |
@@ -123,7 +138,7 @@ Every skill's maturity is tracked in [`assets/skill-status.json`](assets/skill-s
 
 | Agent | Description |
 |-------|-------------|
-| **Project Discovery** (`uipath-project-discovery-agent`) | Auto-discovers UiPath project structure, dependencies, conventions, and generates context files for Claude Code (`.claude/rules/project-context.md`) and UiPath Autopilot (`AGENTS.md`). Triggered automatically when a UiPath project is detected without existing context, or on explicit user request. |
+| **Project Discovery** (`uipath-project-discovery-agent`) | Auto-discovers UiPath project structure, dependencies, and conventions, then writes the context files itself for Claude Code (`.claude/rules/project-context.md`) and UiPath Autopilot (`AGENTS.md`). Triggered automatically when a UiPath project with authored workflows is detected without existing context, or on explicit user request. Skips empty and freshly-scaffolded projects. |
 
 ## Multi-Tool Support
 

package/assets/skill-status.json

@@ -151,6 +151,14 @@
       "last_synced": null
     },
     "uipath-platform": {
+      "status": "stable",
+      "confluence": {
+        "page_id": null,
+        "url": null
+      },
+      "last_synced": null
+    },
+    "uipath-process-mining": {
       "status": "preview",
       "confluence": {
         "page_id": null,
@@ -167,7 +175,7 @@
       "last_synced": null
     },
     "uipath-rpa": {
-      "status": "preview",
+      "status": "stable",
       "confluence": {
         "page_id": null,
         "url": null

package/assets/uip-catalog-snapshot.json

@@ -1,6 +1,6 @@
 {
-  "generated_at": "2026-06-24T05:25:39Z",
-  "cli_version": "1.197.0-alpha.20260623.7621",
+  "generated_at": "2026-08-08T04:29:32Z",
+  "cli_version": "1.200.0-dev.8173",
   "verbs": [
     "admin",
     "admin audit",
@@ -177,6 +177,7 @@
     "agent guardrails",
     "agent guardrails catalog",
     "agent guardrails list",
+    "agent guardrails llm-as-judge-models",
     "agent init",
     "agent input",
     "agent input add",
@@ -233,6 +234,7 @@
     "agenthub mcp update",
     "agenthub mcp-tools",
     "agenthub mcp-tools candidates",
+    "agenthub mcp-tools create-raw",
     "agenthub mcp-tools create-resource",
     "agenthub mcp-tools delete",
     "agenthub mcp-tools disable",
@@ -318,6 +320,7 @@
     "codedagent pull",
     "codedagent push",
     "codedagent register",
+    "codedagent review",
     "codedagent run",
     "codedagent setup",
     "codedapp",
@@ -327,8 +330,10 @@
     "codedapp publish",
     "codedapp pull",
     "codedapp push",
+    "coder",
     "completion",
     "config",
+    "config clear",
     "config get",
     "config set",
     "context-grounding",
@@ -389,15 +394,15 @@
     "docsai ask",
     "feedback",
     "feedback send",
-    "functions",
-    "functions init",
-    "functions new",
-    "functions pack",
-    "functions publish",
-    "functions push",
-    "functions run",
-    "functions runtime-install",
-    "functions serve",
+    "function",
+    "function init",
+    "function new",
+    "function pack",
+    "function publish",
+    "function push",
+    "function run",
+    "function runtime-install",
+    "function serve",
     "gov",
     "gov access-policy",
     "gov access-policy create",
@@ -449,6 +454,13 @@
     "gov compliance-packs state enable",
     "gov compliance-packs state get",
     "gov compliance-packs state list",
+    "gov compliance-packs state restore",
+    "guardrails",
+    "guardrails byo-configurations",
+    "guardrails byo-configurations create",
+    "guardrails byo-configurations delete",
+    "guardrails byo-configurations list",
+    "guardrails byo-configurations update",
     "insights",
     "insights jobs",
     "insights jobs completed-timeline",
@@ -474,10 +486,59 @@
     "is connections update-polling-interval",
     "is connectors",
     "is connectors audit-logs",
+    "is connectors builder",
+    "is connectors builder activity",
+    "is connectors builder activity create",
+    "is connectors builder activity delete",
+    "is connectors builder activity field",
+    "is connectors builder activity field create",
+    "is connectors builder activity field delete",
+    "is connectors builder activity field get",
+    "is connectors builder activity field list",
+    "is connectors builder activity field schema",
+    "is connectors builder activity get",
+    "is connectors builder activity hook",
+    "is connectors builder activity hook create",
+    "is connectors builder activity hook delete",
+    "is connectors builder activity hook get",
+    "is connectors builder activity hook list",
+    "is connectors builder activity list",
+    "is connectors builder activity method",
+    "is connectors builder activity method curate",
+    "is connectors builder activity method get",
+    "is connectors builder activity method set",
+    "is connectors builder activity param",
+    "is connectors builder activity param create",
+    "is connectors builder activity param delete",
+    "is connectors builder activity param get",
+    "is connectors builder activity param list",
+    "is connectors builder auth",
+    "is connectors builder auth get",
+    "is connectors builder auth set",
+    "is connectors builder auth system",
+    "is connectors builder auth system create",
+    "is connectors builder auth system list",
+    "is connectors builder init",
+    "is connectors builder init header",
+    "is connectors builder init header delete",
+    "is connectors builder init preset",
+    "is connectors builder init preset apply",
+    "is connectors builder inspect",
+    "is connectors builder state",
+    "is connectors builder state patch",
+    "is connectors builder state query",
+    "is connectors builder trigger",
+    "is connectors builder trigger create",
+    "is connectors builder validate",
+    "is connectors download",
     "is connectors event-operations",
     "is connectors export",
     "is connectors get",
+    "is connectors import",
     "is connectors list",
+    "is connectors metadata",
+    "is connectors publish",
+    "is connectors publish-status",
     "is connectors swagger",
     "is resources",
     "is resources describe",
@@ -492,6 +553,9 @@
     "is triggers",
     "is triggers describe",
     "is triggers objects",
+    "is typecache",
+    "is typecache activities",
+    "is typecache packages",
     "is webhooks",
     "is webhooks config",
     "ixp",
@@ -539,6 +603,15 @@
     "ixp projects update-prompt",
     "ixp projects update-title",
     "llm-configuration",
+    "llm-configuration byo-connections",
+    "llm-configuration byo-connections create",
+    "llm-configuration byo-connections delete",
+    "llm-configuration byo-connections get",
+    "llm-configuration byo-connections list",
+    "llm-configuration byo-connections list-product-configs",
+    "llm-configuration byo-connections update",
+    "llm-gateway",
+    "llm-gateway models",
     "login",
     "login refresh",
     "login status",
@@ -556,6 +629,7 @@
     "maestro bpmn debug-instance continue",
     "maestro bpmn debug-instance create",
     "maestro bpmn debug-instance incidents",
+    "maestro bpmn debug-instance status",
     "maestro bpmn debug-instance variables",
     "maestro bpmn debug-instance variables-all",
     "maestro bpmn debug-instance variables-set",
@@ -744,6 +818,7 @@
     "maestro flow debug-instance continue",
     "maestro flow debug-instance create",
     "maestro flow debug-instance incidents",
+    "maestro flow debug-instance status",
     "maestro flow debug-instance variables",
     "maestro flow debug-instance variables-all",
     "maestro flow debug-instance variables-set",
@@ -847,6 +922,18 @@
     "maestro flow variable-update remove",
     "mcp",
     "mcp serve",
+    "model-hub",
+    "model-hub custom-routings",
+    "model-hub custom-routings create",
+    "model-hub custom-routings get",
+    "model-hub organizations",
+    "model-hub organizations get",
+    "model-hub policy-previews",
+    "model-hub policy-previews get",
+    "model-hub routing-history",
+    "model-hub routing-history list",
+    "model-hub tenants",
+    "model-hub tenants get",
     "or",
     "or assets",
     "or assets create",
@@ -1043,7 +1130,11 @@
     "platform licenses",
     "platform licenses consumables",
     "platform licenses consumables get",
+    "platform licenses summary",
     "platform tenants",
+    "platform tenants folder-outcome-billing",
+    "platform tenants folder-outcome-billing get",
+    "platform tenants folder-outcome-billing set",
     "platform tenants licenses",
     "platform tenants licenses get",
     "platform tenants licenses set",
@@ -1052,7 +1143,118 @@
     "platform users licenses available",
     "platform users licenses get",
     "platform users licenses set",
+    "pm",
+    "pm app-types",
+    "pm app-types get",
+    "pm app-types list",
+    "pm apps",
+    "pm apps create",
+    "pm apps data-mapping",
+    "pm apps data-mapping get",
+    "pm apps data-mapping update",
+    "pm apps data-model",
+    "pm apps data-model add-table",
+    "pm apps data-model get",
+    "pm apps delete",
+    "pm apps list",
+    "pm apps model",
+    "pm apps model fields",
+    "pm apps model fields list",
+    "pm apps model fields remove",
+    "pm apps model fields set",
+    "pm apps model get",
+    "pm apps model update",
+    "pm apps publish",
+    "pm files",
+    "pm files upload",
+    "pm ingestions",
+    "pm ingestions create",
+    "pm ingestions logs",
+    "pm query",
+    "pm query details",
+    "pm query info",
+    "pm query insights",
+    "pm query layout",
+    "pm query percentile",
+    "pm query rca",
+    "pm query run",
+    "pm transformations",
+    "pm transformations apply",
+    "pm transformations create",
+    "pm transformations get",
+    "pm transformations list",
+    "pm transformations logs",
+    "pm transformations run",
+    "pm transformations status",
+    "pm transformations update",
     "rpa",
+    "rpa activities",
+    "rpa activities find",
+    "rpa activities get-default-xaml",
+    "rpa analyze",
+    "rpa analyzer-rules",
+    "rpa analyzer-rules list",
+    "rpa build",
+    "rpa cleanup",
+    "rpa data-fabric-entities",
+    "rpa data-fabric-entities install",
+    "rpa data-fabric-entities list",
+    "rpa debug",
+    "rpa debug apply-file-changes",
+    "rpa debug break",
+    "rpa debug continue",
+    "rpa debug continue-ignore",
+    "rpa debug continue-retry",
+    "rpa debug restart-from-top",
+    "rpa debug resume",
+    "rpa debug set-breakpoints",
+    "rpa debug start",
+    "rpa debug start-from-here",
+    "rpa debug state",
+    "rpa debug step-into",
+    "rpa debug step-out",
+    "rpa debug step-over",
+    "rpa debug test-activity",
+    "rpa debug toggle-breakpoint",
+    "rpa execution",
+    "rpa execution cancel",
+    "rpa files",
+    "rpa files diff",
+    "rpa get-library-object-repository",
+    "rpa get-object-repository",
+    "rpa init",
+    "rpa instances",
+    "rpa instances list",
+    "rpa pack",
+    "rpa packages",
+    "rpa packages inspect",
+    "rpa packages install",
+    "rpa packages versions",
+    "rpa remote",
+    "rpa remote configure",
+    "rpa remote download-file",
+    "rpa remote exec",
+    "rpa remote upload-file",
+    "rpa restore",
+    "rpa run",
+    "rpa studio",
+    "rpa studio start",
+    "rpa templates",
+    "rpa templates search",
+    "rpa test-data",
+    "rpa test-data add-entity",
+    "rpa test-data add-queue",
+    "rpa test-data add-variation",
+    "rpa tm",
+    "rpa tm clear-default-project",
+    "rpa tm connect",
+    "rpa tm set-default-project",
+    "rpa tm status",
+    "rpa uia",
+    "rpa validate",
+    "rpa workflow-examples",
+    "rpa workflow-examples get",
+    "rpa workflow-examples list",
     "rpa-legacy",
     "rpa-legacy debug",
     "rpa-legacy find-activities",
@@ -1068,6 +1270,7 @@
     "skills uninstall",
     "skills update",
     "solution",
+    "solution cleanup",
     "solution delete",
     "solution deploy",
     "solution deploy activate",
@@ -1080,20 +1283,23 @@
     "solution deploy run",
     "solution deploy status",
     "solution deploy uninstall",
+    "solution deploy upgrade",
     "solution download",
+    "solution feeds",
+    "solution feeds list",
     "solution init",
     "solution pack",
     "solution packages",
     "solution packages delete",
     "solution packages download",
     "solution packages list",
-    "solution project",
-    "solution project add",
-    "solution project import",
-    "solution project list",
-    "solution project publish",
-    "solution project remove",
-    "solution project resync",
+    "solution projects",
+    "solution projects add",
+    "solution projects import",
+    "solution projects list",
+    "solution projects publish",
+    "solution projects remove",
+    "solution projects resync",
     "solution publish",
     "solution resources",
     "solution resources add",
@@ -1147,6 +1353,7 @@
     "tm objectlabel get",
     "tm objectlabel list",
     "tm objectlabel remove",
+    "tm pack",
     "tm project",
     "tm project clear-default-folder",
     "tm project create",
@@ -1247,8 +1454,7 @@
     "codedagent push",
     "codedagent register",
     "codedagent run",
-    "context-grounding",
-    "llm-configuration",
-    "rpa"
+    "coder",
+    "context-grounding"
   ]
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@uipath/skills",
-  "version": "1.199.0",
+  "version": "1.200.0",
   "description": "UiPath agent skills for Claude Code, Codex, Cursor, Copilot, Gemini and OpenCode — RPA, UI automation, UI testing, coded agents/apps/workflows, and troubleshooting. Distributed as the UiPath Claude Code plugin.",
   "author": {
     "name": "UiPath"
@@ -25,6 +25,7 @@
     "troubleshoot"
   ],
   "private": false,
+  "uipathSkillsFlavor": "default",
   "files": [
     "skills",
     "agents",
@@ -35,9 +36,17 @@
     "version-manifest.json",
     "README.md",
     "LICENSE",
-    "CODEOWNERS"
+    "CODEOWNERS",
+    "scripts/npm-package-lifecycle.mjs"
   ],
   "scripts": {
+    "skills:test": "node --test tests/scripts/compose-skill-flavor.test.mjs tests/scripts/manage-skill-flavors-skill.test.mjs",
+    "skills:validate": "node scripts/compose-skill-flavor.mjs validate",
+    "skills:build": "node scripts/compose-skill-flavor.mjs build",
+    "skills:pack": "node scripts/compose-skill-flavor.mjs pack",
+    "skills:recover": "node scripts/npm-package-lifecycle.mjs recover",
+    "prepack": "node scripts/npm-package-lifecycle.mjs prepare",
+    "postpack": "node scripts/npm-package-lifecycle.mjs restore",
     "version:sync": "node scripts/sync-version.mjs",
     "version:check": "node scripts/sync-version.mjs --check"
   }

package/scripts/npm-package-lifecycle.mjs

@@ -0,0 +1,46 @@
+#!/usr/bin/env node
+
+import { existsSync } from "node:fs";
+import path from "node:path";
+import process from "node:process";
+import { fileURLToPath, pathToFileURL } from "node:url";
+
+const repoRoot = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "..");
+const composerPath = path.join(repoRoot, "scripts", "compose-skill-flavor.mjs");
+const action = process.argv[2] ?? process.env.npm_lifecycle_event;
+const actions = new Set(["prepare", "restore", "recover"]);
+
+async function main() {
+  if (!actions.has(action)) {
+    throw new Error(`expected lifecycle action prepare, restore, or recover; got ${JSON.stringify(action)}`);
+  }
+
+  if (!existsSync(composerPath)) {
+    const sourceIndicators = [
+      path.join(repoRoot, ".git"),
+      path.join(repoRoot, "skill-flavors"),
+      path.join(repoRoot, "build", ".root-pack-transaction"),
+    ].filter((candidate) => existsSync(candidate));
+    if (sourceIndicators.length) {
+      throw new Error(
+        `skill package source was detected, but the flavor composer is missing: ${composerPath}`,
+      );
+    }
+    return;
+  }
+
+  const composer = await import(pathToFileURL(composerPath).href);
+  if (action === "prepare") {
+    composer.prepareRootDefaultPackage(repoRoot);
+    return;
+  }
+
+  composer.restoreRootDefaultPackage(repoRoot);
+}
+
+try {
+  await main();
+} catch (error) {
+  console.error(`ERROR: ${error.message}`);
+  process.exitCode = 1;
+}

package/skills/uipath-admin/SKILL.md

@@ -120,11 +120,13 @@ Each rule is the agent contract. Per-area detail is in the linked reference file
 
 23. **Disambiguate `org` vs `tenant` scope before querying.** If the prompt is vague AND no prior turn fixed the scope, **stop and ask once** (a single clarifying question — use AskUserQuestion when available) — never silently default to `tenant` or any single scope. If you genuinely cannot get an answer (non-interactive run) and must proceed, query **both** scopes and combine the results rather than guessing one — silently picking a single scope is the failure mode. **Scope is a positional subgroup, NOT a flag:** write `uip admin audit org sources` / `uip admin audit tenant events` — there is no `--scope` option (`audit sources --scope organization` is invalid). Routing table (user-phrasing → scope + why it lives where) and investigation playbooks: [audit-workflow-guide.md → Audit scope disambiguation](references/audit-workflow-guide.md#audit-scope-disambiguation--route-by-user-phrasing).
 24. **`audit <scope> events` returns an object, not a bare array.** Shape is `{auditEvents, next, previous}`. Do not index `Data[0]`; read `Data.auditEvents[]`. **Cursor semantics are chronological**: `next` = newer events, `previous` = older events. The default newest-backward walk follows `previous`.
-25. **`--limit` paginates internally — never loop on `--from-date` / `--to-date` to "paginate".** The server clamps `maxCount` to `[10, 200]` per request; when the user wants more than 200, the CLI fetches `ceil(N/200)` pages under the hood. Pass `--limit 500` (or larger) — do NOT re-implement pagination in the agent.
+25. **`--limit` paginates internally — never loop on `--from-date` / `--to-date` to "paginate".** The server clamps `maxCount` to `[10, 200]` per request; when the user wants more than 200, the CLI fetches `ceil(N/200)` pages under the hood. Pass `--limit 500` (or larger, **up to the 10000 maximum**) — do NOT re-implement pagination in the agent. `--limit` must be in `[1, 10000]`; a bigger value is rejected up front with `Result: "ValidationError"`, so never pass an arbitrarily huge number to mean "everything" — for that, omit `--limit` or stay within the range.
 26. **Discover via `audit <scope> sources` first — never invent source / target / type GUIDs.** The catalog response gives the GUIDs you pass to `events --source / --target / --type`. This is also the answer to "what audit events / sources can I see?" — **run `audit <scope> sources` and report the live catalog; do not answer conceptually from memory or the reference docs.**
 27. **Bound the time window, ISO 8601 in UTC.** Don't call `audit <scope> events` without `--from-date` and `--to-date` on a noisy tenant. Accepted formats: date-only (`2026-04-01`) or with time (`2026-04-01T14:30:00Z`). **`--to-date` is inclusive of the exact instant** — to capture a full final day, pass the start of the next day or `T23:59:59.999Z`. This next-day trick is for `events` only — `export` bounds are whole days (Rule 30). Resolve relative phrases ("yesterday", "last 7 days") against the actual current UTC date (e.g. `date -u`) — never guess dates — and echo the resolved window in your reply.
+27b. **"No matching event" is a complete answer — never name an actor the evidence does not support.** An audit trail is evidence, so attributing an action to the wrong person is worse than returning nothing. If the targeted query comes back empty, say so plainly, state what you searched (scope, source/target/type, window), and offer a next step (widen the window, try the other scope, check the resource ever existed). **Never** promote an actor from an adjacent event — a different resource, a different event type, or a broad `--search` hit — into the answer, and do not keep loosening filters until something returns and then present that as the culprit. Only name an actor when the cited event matches both the resource and the verb asked about, quoting `createdOn` plus the identifying `eventDetails` field so the user can verify it. Detail: [audit-workflow-guide.md → Step 5](references/audit-workflow-guide.md#step-5--when-nothing-matches-say-so).
 28. **`--tenant-id` is silently ignored on `org`-scoped audit commands.** If you find yourself reaching for it on `audit org events`, switch to `audit tenant` instead.
 29. **On 401 from audit, do NOT retry.** The token is missing the `Audit.Read` scope; tell the user to `uip logout && uip login`.
+29b. **On a 5xx from audit, DO retry — the envelope tells you so.** `ErrorCode: server_error` / `Retry: RetryLater` (e.g. `HTTP 503: no healthy upstream`, `HTTP 504`) is a transient, not a bad request. Re-run the **same** query up to two more times with a few seconds of backoff before reporting failure — changing `--limit` or the window between attempts is not a fix and only obscures the cause. Retry immediately-and-once is usually not enough; wait between attempts. **Never write or present an error envelope as if it were the result** — if the user asked you to save the JSON, saving `{"Result":"Failure",...}` to that file is a failed retrieval, not a result. Report the failure explicitly instead.
 30. **`audit <scope> export` writes into a base directory (`--output-path`): a uniquely-named folder of day-wise JSON files (default) or a single merged CSV.** `--from-date`, `--to-date`, and `--output-path` are all required. **Export dates are whole UTC days, inclusive on both ends** (the server truncates times to the calendar day): `--from-date 2026-01-01 --to-date 2026-01-31` exports all of January; a single day is `--from-date X --to-date X` with the same date. Do **not** apply the `events` next-day trick here — a next-day `--to-date` exports an extra full day. `--output-path` is a **base directory** (created if missing) — **pass a directory only, never a filename or extension**; the CLI creates a uniquely-named `audit_<from>_<to>_<generated-at>` output inside it (folder for `json`, `.csv` for `csv`), so repeated exports of the same window never collide. **Do not hand-craft the per-export name.** **`--file-format <json|csv>`** selects the shape: `json` (default) = a folder of `<YYYY-MM-DD>.json` files; `csv` = one merged CSV — pick `csv` for a flat spreadsheet/Excel-friendly dump, `json` for per-day files. If the user named a destination folder, pass it verbatim as `--output-path` — no confirmation needed; confirm first only when you had to pick a default (e.g. `./audit-exports`) yourself. Then report the generated `Path` (and `GeneratedAt`) from the result.
 
 ### IP Restriction
@@ -144,6 +146,8 @@ Each rule is the agent contract. Per-area detail is in the linked reference file
 7. **Do NOT call audit `events` with no time bound** on a noisy tenant — default to a bounded window.
 8. **Do NOT pass `--tenant-id` to `org`-scoped audit commands** — it's silently ignored.
 9. **Do NOT retry on 401 auth errors.** The token is missing the required scope (`Audit.Read` for audit). Tell the user to `uip logout && uip login`.
+9a. **Do NOT save or report an audit error envelope as data.** A `{"Result":"Failure"|"ValidationError", ...}` payload is a failed call — retry a 5xx (Rule 29b), fix a `ValidationError`, and never leave it in a file the user asked you to fill with results.
+9b. **Do NOT name a culprit an audit query did not return.** If the targeted search is empty, report "no matching event found" — never borrow an actor from an adjacent or broader-search event (Rule 27b).
 10. **Do NOT call `roles update` with only the flag you want to change.** Re-fetch first; the upsert body overwrites omitted fields (Rule 12).
 11. **Do NOT present authz results without provenance** — role name, `scopeType`, `ownerServiceName`, tenant-binding (names not UUIDs). Detail: [authorization-commands.md → Provenance contract](references/authorization/authorization-commands.md#provenance-contract-for-completion-output).
 12. **Do NOT conflate provisioned services with the available catalog.** `services list` returns provisioned with status; `services list-available` is the catalog. Present them as separate sections.

package/skills/uipath-admin/references/audit-commands.md

@@ -94,7 +94,7 @@ uip admin audit tenant events --from-date 2026-04-22T00:00:00Z --to-date 2026-04
 | `--user-id <guid...>` | no | Filter by acting user IDs. Repeatable. |
 | `--search <term>` | no | Server-side substring search across event content. |
 | `--status <Success\|Failure\|0\|1>` | no | Case-insensitive labels or the raw `AuditEventStatus` enum values. |
-| `--limit <n>` | no | Total events to return. Server clamps each individual API call to **200**; values >200 trigger client-side pagination automatically (cursor handled internally). Omitted = single call with the server's default page size (typically up to 200 events). |
+| `--limit <n>` | no | Total events to return. **Must be between 1 and 10000** — a larger value is rejected up front with `Result: "ValidationError"` / `invalid_argument` before any HTTP call, so do NOT pass a huge number to mean "everything". To retrieve everything in a window, omit `--limit` or pass a value within the range. Server clamps each individual API call to **200**; values >200 trigger client-side pagination automatically (cursor handled internally). Omitted = single call with the server's default page size (typically up to 200 events). |
 | `--login-validity <minutes>` | no | Token-refresh hint. |
 | `--tenant-id <guid>` | no | **Tenant scope only.** Override the active tenant. |