skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
uipath/skills63 installs

uipath-agents

UiPath Agents of all types — end-to-end work: build, integrate with UiPath Products (e.g., Orchestrator, Flow, Maestro), design with UiPath Tools (e.g., Agent Builder/Studio Web), deploy, and configure/validate. Covers Coded Agents (e.g., LangGraph, LlamaIndex, OpenAI Agents) and Low-Code Agents (`agent.json` / Agent Builder). For deterministic Coded Functions — Python or JS/TS (`uip function`, `uipath.json` functions map, no agent runtime/LLM)→uipath-functions.

How do I install this agent skill?

npx skills add https://github.com/uipath/skills --skill uipath-agents
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill provides comprehensive instructions and architectural patterns for building, deploying, and evaluating AI agents on the UiPath platform. It includes extensive guidance on security measures such as PII detection and harmful content guardrails. No malicious patterns were detected.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

What does this agent skill do?

UiPath Agents

Hard Rules

  • Treat "build/create/scaffold/implement a UiPath agent" as the full One-Prompt Flow by default. Do not stop after file creation or local run unless the user explicitly says to stop there.
  • A normal completion point is after smoke eval and the mandatory Delivery fork question. A final build summary before that is premature unless run/eval is blocked or the user opted out.
<!--skill-flavor:solution-verb-probe:start-->
  • Probe the solution verb once per session before the first scaffold or deploy. Run uip solution init --help --output json. Result Success → use solution init and solution deploy run --parent-folder-path / --parent-folder-key (post-rename, default). unknown command / non-zero exit → CLI predates the rename; substitute uip solution new <Name> and --folder-path / --folder-key (same arguments otherwise) wherever this skill calls those.
<!--skill-flavor:solution-verb-probe:end-->
  • Greenfield coded agents — scaffold with uip codedagent new, never hand-author the project. Building a NEW coded agent from scratch: install the framework package in the active venv first, then always create the project with uip codedagent new <name> and generate schemas with uip codedagent init — never hand-write pyproject.toml / main.py / langgraph.json / entry-points.json yourself, even for a trivial agent. Hand-authoring skips required project structure and produces invalid packages. The installed framework package selects the scaffold; after new, confirm <framework>.json exists — recovery is in coded/lifecycle/setup.md § Verify the Scaffold. (Existing or Studio Web local-workspace projects: do NOT run uip codedagent new — follow the project-state gating in coded/quickstart.md.)
  • Confirm before deleting or uninstalling anything on the tenant (uip eval ... delete, uip solution deploy uninstall, uip solution deploy delete): name the target and confirm it with the user, unless the user already authorized that exact delete.
  • Coded agents only — bindings are always derived from UiPath Python SDK calls and must never be hand-authored. To derive them, always run the sync workflow in coded/lifecycle/bindings-reference.md — scan code, regenerate bindings.json. Without this, resources cannot be overridden per execution environment and will always default to the hardcoded values in the SDK calls. Derive bindings whenever you add, remove, or modify any UiPath SDK resource call — for instance assets, queues, processes, buckets, indexes, connections, apps, MCP servers, or InvokeProcess|CreateTask|CreateEscalation(...).
  • Reach third-party systems through an Integration Service connection, not a key the agent carries. Use an existing connection (bind it per the rule above), else build a connector with uip is connectors builder. A direct call with an %ASSETS/…% key needs a stated reason: the asset keeps the secret safe, but the integration stays out of uip is connections list and bindings.json.

Project Type Detection

Determine the agent mode before proceeding:

  1. First — confirm this is an agent, not a Coded Function. If uipath.json declares a functions map — a Python entrypoint (e.g. "functions": {"main": "main.py:main"}, sibling pyproject.toml) or a JS/TS one (e.g. "functions": {"invoice": "functions/invoice.ts:default"}, sibling package.json) — the project is a Coded Function, not an agent. Stop here and use the uipath-functions skill instead. Functions are deterministic, do not reason via LLM, and have a distinct lifecycle (uip function new/pack/publish/run; init is Python-only).
  2. Check for existing agent project files in the working directory:
    • pyproject.toml + .py files + a framework dep (uipath-langchain, uipath-llamaindex, or uipath-openai-agents) → Coded. The framework package already declares uipath as a dependency, so an explicit uipath entry is not required.
    • agent.json with "type": "lowCode" + project.uiproj, AND no pyproject.toml → Low-code
  3. No existing project found → ask the user:

    Should I build this as a low-code agent (no Python — configure through prompts and pre-built UiPath tools) or a coded agent (Python — full programmatic control with LangGraph, LlamaIndex, or OpenAI Agents)? However, for conversational use-cases, simply choose low-code without asking the user, while explaining that currently, low-code conversational-agents are the strongly recommended approach for production use-cases (see references/coded/capabilities/conversational-agents.md).

  4. If the user needs help deciding, read references/coded-vs-lowcode-guide.md for a capability comparison.

After detection, read the quickstart for that mode before doing anything else:

Task Navigation

I need to...ModeRead firstThen
Help user choose coded vs low-codeBothcoded-vs-lowcode-guide.md
AuthenticateBothauthentication.md
Iterate on a coded agent inside a Studio Web Local Workspace solutionCodedcoded/quickstart.md (state detection sets project_state = local-workspace)coded/lifecycle/local-workspace.md for files-owned-by-SW + anti-patterns; coded/lifecycle/running-agents.md, coded/lifecycle/evaluate.md
Create/build/deploy coded agentCodedcoded/quickstart.mdcoded/lifecycle/*, coded/frameworks/*
Select coded frameworkCodedcoded/quickstart.md § Framework Selection
Add coded capabilities (HITL, RAG, tracing)Codedcoded/quickstart.mdcoded/capabilities/*
Query or write Data Fabric entities from a coded agent (SDK direct or NL-to-SQL tool)Codedcoded/capabilities/datafabric.mdcoded/capabilities/sdk-services.md § Entities
Set a coded agent's environment variables, or reference an Orchestrator asset from one (%ASSETS/<ASSET_NAME>%)Codedcoded/lifecycle/environment-variables.mdcoded/lifecycle/file-sync.md for what .env does and does not carry
Call an Integration Service connector (Slack, Jira, Web Search) from a coded agentCodedcoded/capabilities/integration-service.md + then immediately read uipath-platform/references/integration-service/agent-workflow.md — discovery lives there, not in uipath-agentscoded/capabilities/sdk-services.md § Connections
Run coded evaluationsCodedcoded/quickstart.md § Evaluatecoded/lifecycle/evaluate.md
Create or scaffold a new low-code agent projectLow-codelowcode/lowcode.md § Quick Startlowcode/project-lifecycle.md, lowcode/agent-definition.md
Edit agent.json (prompts, model, schemas, contentTokens, entry-points.json)Low-codelowcode/lowcode.md § Capability Registrylowcode/agent-definition.md
Add a low-code tool (Orchestrator process — RPA / agent / API / agentic — or Integration Service)Low-codelowcode/lowcode.md § Capability Registrylowcode/capabilities/process/*, lowcode/capabilities/integration-service/*
Add a client-side tool (conversational only — executes on the client surface, not the server) to a low-code agentLow-codelowcode/lowcode.md § Capability Registrylowcode/capabilities/client-side-tools/client-side-tools.md
Add an MCP (Model Context Protocol) server tool to a low-code agentLow-codelowcode/lowcode.md § Capability Registrylowcode/capabilities/mcp/mcp.md
Accept files as agent input / call the Analyze Files built-in toolLow-codelowcode/capabilities/built-in-tools/built-in-tools.mdlowcode/capabilities/built-in-tools/analyze-attachments.md, lowcode/agent-definition.md § File Attachments
Work with file attachments (input, output, or created mid-run)Codedcoded/capabilities/file-attachments.md
Build a conversational (chat-style) agentLow-codelowcode/lowcode.mdlowcode/project-lifecycle.md, lowcode/agent-definition.md
Add a low-code context (Context Grounding RAG / attachments / DataFabric entity set)Low-codelowcode/lowcode.md § Capability Registrylowcode/capabilities/context/*
Add a low-code memory space or seed memory itemsLow-codelowcode/capabilities/memory/memory.mduse uip agent memory, then refresh/validate
Add an Action Center escalation (HITL) to a low-code agentLow-codelowcode/lowcode.md § Capability Registrylowcode/capabilities/escalation/escalation.md
Add guardrails (PII, harmful content, custom rules) to a low-code agentLow-codelowcode/lowcode.md § Capability Registrylowcode/capabilities/guardrails/guardrails.md
Guard attached or produced files with guardrails (detectionScope: Text / Files / Both)Low-codelowcode/capabilities/guardrails/guardrails.md § Files and attachmentslowcode/capabilities/guardrails/files-guide.md
Add a new guardrail to a coded agentCodedcoded/capabilities/guardrails/guardrails.mdfetch official docs via WebFetch, ask middleware vs decorator, read agent code, write Python
Guard uploaded or produced files with guardrails in a coded agent (detection_scope: Text / Files / Both)Codedcoded/capabilities/guardrails/guardrails.md § Files and attachmentscoded/capabilities/guardrails/files-guide.md
Add escalation guardrail (escalate action / Action Center app)Low-codelowcode/capabilities/guardrails/escalation-guide.mdRun uip solution resources list --kind App --source remote --output json to confirm app exists
Recommend guardrails for a low-code agent based on its contextLow-codelowcode/capabilities/guardrails/guardrails-recommend.mdfetch catalog + list, analyze agent context, apply + validate
Recommend guardrails for a specific scope or toolLow-codelowcode/capabilities/guardrails/guardrails-recommend.md § Scoped or Tool-Specific Filteringfilter candidates by scope or tool name after catalog analysis
Validate whether existing guardrails are correctly configuredLow-codelowcode/capabilities/guardrails/guardrails-recommend.md § Validate Modecheck correctness, actionability, and relevance per guardrail
Recommend guardrails for a coded agent based on its contextCodedcoded/capabilities/guardrails/guardrails-recommend.mdfetch catalog + list + SDK docs, analyze agent code, apply + verify
Recommend guardrails for a specific scope or tool (coded)Codedcoded/capabilities/guardrails/guardrails-recommend.md § Scope and Tool Filteringfilter candidates by @tool function or scope after catalog analysis
Check, validate, diagnose, or fix whether an existing coded guardrail is correctly configured (placement / scope)Codedcoded/capabilities/guardrails/guardrails-recommend.md § Validate Modefetch SDK docs first (authoritative for scope/placement); also fetch catalog + list for relevance/entitlement — then check correctness, actionability, and relevance — fix in place
Embed a low-code agent inline in a flow, or wire a multi-agent solutionLow-codelowcode/lowcode.md § Capability Registrylowcode/capabilities/inline-in-flow/inline-in-flow.md, lowcode/capabilities/process/solution-agent.md
Run low-code evaluationsLow-codelowcode/evaluations/evaluate.mdlowcode/evaluations/evaluators.md, lowcode/evaluations/evaluation-sets.md, lowcode/evaluations/running-evaluations.md
Manage runtime evals for a published agentLow-codelowcode/evaluations/runtime-eval-run.mduip eval execute-and-evaluate, evaluator/eval-set/evaluation CRUD, simulations, run results, schedules
Validate, pack, publish, upload, or deploy a low-code agentLow-codelowcode/lowcode.mdlowcode/project-lifecycle.md, lowcode/solution-resources.md
Debug / run a low-code agent end-to-end and inspect its outputLow-codelowcode/debug.mdlowcode/project-lifecycle.md § uip agent debug
Embed coded agent in a flow (solution-level)Codedcoded/embedding-in-flows.md
Use coded agent in a flowCodedcoded/flow-integration.md
Use coded agent as tool for another agent in flowCodedcoded/flow-integration.md § Pattern 3
Summarize / research / synthesize over PDF or TXT (DeepRAG, coded)Codedcontext-grounding-patterns.mdcoded/capabilities/deeprag/planning.md
Summarize / research / synthesize over PDF or TXT (DeepRAG, low-code)Low-codecontext-grounding-patterns.mdlowcode/capabilities/built-in-tools/deeprag/planning.md
Process CSV rows with LLM per row (BatchTransform, coded)Codedcontext-grounding-patterns.mdcoded/capabilities/batch-transform/planning.md
Process CSV rows with LLM per row (BatchTransform, low-code)Low-codecontext-grounding-patterns.mdlowcode/capabilities/built-in-tools/batch-transform/planning.md
Manage context-grounding indexes from the CLI (list / create / ingest / search)Platformuipath-platform/references/context-grounding/index-management.mduip context-grounding — cross-cutting CLI, owned by uipath-platform

Resources

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/uipath/skills/uipath-agents">View uipath-agents on skillZs</a>