{
  "markdown": "# UiPath Agent Skills\n\n[![skills.sh](https://www.skills.sh/b/uipath/skills)](https://www.skills.sh/uipath/skills)\n\n> [!NOTE]\n> **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.\n\nUiPath Agent Skills give AI coding agents the domain knowledge to build, run, test, and deploy UiPath automations and agents — directly from your development environment. Each skill is a self-contained package of instructions and resources that teaches your coding agent how to perform a specific UiPath task.\n\n## Quick Start\n\nUse the official onboarding installer. It installs Node.js >= 20, `@uipath/cli`, UiPath skills for installed AI coding agents, .NET SDK 8.0, and Python 3.11-3.14.\n\n**macOS/Linux**\n```bash\ncurl -fsSL https://download.uipath.com/uipath-cli/install.sh | bash\n```\n\n**Windows**\n```powershell\nirm https://download.uipath.com/uipath-cli/install.ps1 | iex\n```\n\nThe installer runs `uip skills install --no-interactive` to wire the skills into detected AI coding agents. To re-run manually or install for one agent, use `uip skills install` or pass `--agent <name>` (e.g. `--agent claude`).\n\nFor CI or a CLI-only machine, skip agent skills and runtime installs with `--skip-skills --skip-runtimes` on macOS/Linux or `-SkipSkills -SkipRuntimes` on Windows.\n\n### Try a skill without installing anything\n\nTo 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:\n\n```bash\nnpx skills add UiPath/skills --list              # browse the catalog\nnpx skills use UiPath/skills@uipath-rpa | claude # run one skill; nothing is written to your project\nnpx skills add UiPath/skills --skill uipath-rpa  # install just that one skill\n```\n\n> **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`.\n\n## Skill Catalog\n\nThe repository ships skills covering authoring, platform operations, and diagnostics for UiPath automations.\n\n### Authoring\n\n| Skill | Description |\n|-------|-------------|\n| **uipath-rpa** | RPA workflows (`.xaml` and `.cs` coded) — create, edit, build, run, debug, test; UI automation, Object Repository, Integration Service activities. |\n| **uipath-maestro-flow** | Maestro Flow (`.flow`) — author, connect nodes, validate, run, publish; triggers, schedules, evals, incidents. |\n| **uipath-agents** | UiPath agents end-to-end — coded (Python: LangGraph, LlamaIndex, OpenAI Agents) and low-code (`agent.json`); scaffold, run, evaluate, deploy. |\n| **uipath-maestro-bpmn** | Maestro BPMN process orchestration (`.bpmn`) — author XML, validate, package, operate, diagnose. |\n| **uipath-maestro-case** | Case Management (`caseplan.json`) authoring from SDD with phased build and validation. |\n| **uipath-coded-apps** | Coded Web Apps and Coded Action Apps — scaffold, build, debug, pack, publish, deploy via `uip codedapp`. |\n| **uipath-api-workflow** | API Workflow JSON DSL — author, run, package, publish; HTTP and Integration Service connector activities. |\n| **uipath-human-in-the-loop** | Human task authoring and operations — design approval gates, escalations, and validation forms in Flow, Maestro, or coded agents; list, assign, complete, and reassign the resulting Action Center tasks. |\n| **uipath-ixp** | Document Understanding (IXP) — project setup, labeling, prediction review, prompt improvement, model publishing. |\n\n### Solution & Planning\n\n| Skill | Description |\n|-------|-------------|\n| **uipath-planner** | Solution planner & designer — turn a Process Design Document into an implementation-ready Solution Design Document (SDD), then derive an executable multi-skill task list across the other skills. |\n| **uipath-solution** | Solution lifecycle (`.uipx`) — `uip solution init/pack/publish/deploy/activate`. |\n| **uipath-review** | Read-only auditor — structural, quality, and best-practice review across RPA, agents, flows, BPMN, coded apps, and solutions. |\n\n### Platform & Operations\n\n| Skill | Description |\n|-------|-------------|\n| **uipath-platform** | Platform ops via `uip` CLI — auth, Orchestrator (folders, assets, queues, buckets, jobs, triggers), Integration Service, Data Fabric (entities and records), LLM Gateway, traces, licensing. |\n| **uipath-admin** | UiPath Admin — Identity Server, Authorization (custom roles, role assignments, PDP), OMS (org, tenants, services, regions), IP restriction, audit; governance policies (AOps product policies and Access ToolUsePolicy). |\n| **uipath-test** | Test Manager — manage projects, cases, sets, executions; generate persona-tailored test reports. |\n\n### Diagnostics & Feedback\n\n| Skill | Description |\n|-------|-------------|\n| **uipath-troubleshoot** | Root-cause investigation across any UiPath product — errors, failures, regressions, stuck jobs, traces, incidents. |\n| **uipath-feedback** | Submit bug reports and improvement suggestions via `uip feedback send`. |\n\n### Lifecycle Status\n\nEvery skill's maturity is tracked in [`assets/skill-status.json`](assets/skill-status.json) — the source of truth. The table below is generated; refresh it with `python3 scripts/check-skill-status.py --write-readme`.\n\n<!-- BEGIN GENERATED SKILL STATUS -->\n| Skill | Status |\n|-------|--------|\n| `uipath-activity-migrator` | In-development |\n| `uipath-admin` | Stable |\n| `uipath-agents` | Stable |\n| `uipath-aops` | Preview |\n| `uipath-api-workflow` | Stable |\n| `uipath-automation-discovery` | Preview |\n| `uipath-automationhub` | Stable |\n| `uipath-coded-apps` | Stable |\n| `uipath-connector-builder` | In-development |\n| `uipath-feedback` | Stable |\n| `uipath-functions` | Preview |\n| `uipath-governance` | Preview |\n| `uipath-human-in-the-loop` | Stable |\n| `uipath-insights` | Preview |\n| `uipath-ixp` | Stable |\n| `uipath-knowledge-bundles` | Preview |\n| `uipath-maestro-bpmn` | In-development |\n| `uipath-maestro-case` | Preview |\n| `uipath-maestro-flow` | Stable |\n| `uipath-mcp-servers` | In-development |\n| `uipath-planner` | Stable |\n| `uipath-platform` | Stable |\n| `uipath-process-mining` | Preview |\n| `uipath-review` | Preview |\n| `uipath-rpa` | Stable |\n| `uipath-rules` | In-development |\n| `uipath-solution` | Stable |\n| `uipath-tasks` | Stable |\n| `uipath-test` | Preview |\n| `uipath-troubleshoot` | Preview |\n\n**Status legend:**\n- **Stable** — Stable, production-ready surface; safe for production.\n- **Preview** — Not yet stable; may be broadly available or gated/allowlisted, and surface and behavior may change.\n- **In-development** — Skill itself is incomplete or unstable; coverage is partial.\n<!-- END GENERATED SKILL STATUS -->\n\n## Agents\n\n| Agent | Description |\n|-------|-------------|\n| **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. |\n\n## Multi-Tool Support\n\nThis repository works with **Claude Code**, **Google Gemini CLI**, **OpenAI Codex CLI**, and **Cursor IDE**.\n\n### Claude Code\n\nThis repository works as a **Claude Code plugin**. Install skills via `uip skills install` (the recommended method above) — this keeps skills updated automatically.\n\n> **Avoid manual plugin installation** (e.g., `claude plugin marketplace add` / `claude plugin install`). Manually installed plugins must be updated manually, and you may miss skill updates and fixes.\n\nIf you've already installed manually, uninstall and re-install via `uip skills install` to switch to automatic updates.\n\n#### Reduce permission prompts\n\nBy default, Claude Code prompts for approval on every `uip` command, and a realistic Flow or RPA build runs 25+ distinct subcommands. Claude Code plugins cannot ship permission allowlists declaratively, so run this once to install a curated allowlist of safe read-only commands (registry lookups, validation, local scaffolding) while keeping prompts for side-effectful operations (login, debug, publish):\n\n```text\n/uipath:install-permissions\n```\n\nThe command prints the recommended JSON and offers to merge it into your settings (`~/.claude/settings.json` for global, or project-local `.claude/settings.local.json`). You will also see a one-line nudge at session start until an allowlist is installed.\n\n### Google Gemini CLI\n\nGemini CLI is supported by `uip skills install`. If the Gemini CLI is on your PATH, it's detected automatically and skills are wired up. If no agent is detected, pick **Gemini CLI** when prompted.\n\n### OpenAI Codex CLI\n\nThis repository is configured as a Codex CLI skill provider. The `AGENTS.md` file (symlinked to `CLAUDE.md`) provides project instructions, and skills are discovered via `.agents/skills/` (symlinked to `skills/`).\n\nThis repository also includes Codex plugin metadata under `.codex-plugin/`. The Codex plugin manifest exposes the same `skills/` directory and shared session hooks.\n\nInstall with Codex CLI:\n\n```bash\ncodex plugin marketplace add UiPath/skills --ref main\ncodex plugin add uipath@uipath-marketplace\n```\n\n> **Codex prerequisite:** Use Codex CLI 0.142.0 or later. This repository uses the repository root as the plugin root, supported since [openai/codex#17066](https://github.com/openai/codex/issues/17066) was resolved.\n\n> **Windows users:** This repo uses git symlinks. Clone with symlinks enabled:\n> ```bash\n> git clone -c core.symlinks=true https://github.com/UiPath/skills\n> ```\n>\n> If you've already cloned without symlink support, re-enable and re-checkout:\n> ```bash\n> git config core.symlinks true\n> git checkout -- .\n> ```\n>\n> If you encounter a `Filename too long` or `MAX_PATH` error during\n> checkout, enable Git long-path support:\n> ```bash\n> git config --global core.longpaths true\n> ```\n> Then retry the clone or checkout.\n\n### Cursor IDE\n\nProject rules are provided in `.cursor/rules/` and are automatically loaded by Cursor.\n\n## Contributing\n\nContributions are welcome! Whether it's a new skill, a bug fix, or a documentation improvement — we'd love your help.\n\nSee **[CONTRIBUTING.md](CONTRIBUTING.md)** for the full guide, including:\n- Repository structure and architecture\n- How to add a new skill (folder layout, SKILL.md format, frontmatter)\n- Naming conventions and quality checklist\n- Pull request process and branch naming\n\n**Quick version:**\n\n1. Fork this repository\n2. Create a feature branch (`feat/add-<skill-name>`)\n3. Add your skill under `skills/uipath-<name>/` with a `SKILL.md`\n4. Submit a pull request\n\nFor questions, ideas, or feedback, please [open an issue](https://github.com/UiPath/uipath-claude-plugins/issues).\n\n### Running coder-eval on demand\n\n[**Run Coder Eval**](https://github.com/UiPath/skills/actions/workflows/run-coder-eval.yml) — GH-hosted workflow that runs `coder-eval` against the skills task tree (`tests/tasks/...`). Use for ad-hoc single-task verification or a folder-scoped sweep on the same infra as the nightly cron. Trigger from the Actions tab → \"Run workflow\" → fill in `task_globs`. Definition: [`.github/workflows/run-coder-eval.yml`](.github/workflows/run-coder-eval.yml).\n\n## Resources\n\n- [UiPath Documentation](https://docs.uipath.com/)\n- [UiPath Community](https://community.uipath.com/)\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 11675,
  "sha": "b16981412bd9bb709d150f4a1b2a734854c3559e10bc829b18f2df4faa729c77",
  "repo_slug": "uipath/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/skl_uipath_skills_uipath_maestro_flow_21266ccb/readme"
}