> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orq.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Orq Skills for code assistants

> Extend Claude Code, Cursor, Codex, and other AI assistants with reusable Skills and Commands built for the full Build, Evaluate, Optimize lifecycle on Orq.ai.

## Overview

**Orq Skills** are pre-built, reusable workflows from the [orq-ai/assistant-plugins](https://github.com/orq-ai/assistant-plugins) repository. They come in two forms:

* **Skills**: multi-step workflows that require reasoning, such as building an agent, running an experiment, or analyzing trace failures.
* **Commands**: quick slash-command actions for immediate results, such as listing traces or showing analytics.

Both are built on the [Agent Skills](https://agentskills.io) standard format, which means they work with any compatible assistant: [Claude Code](/docs/integrations/code-assistants/claude-code), [Cursor](/docs/integrations/code-assistants/cursor), Gemini CLI, and others. Each skill encodes best practices from prompt engineering, agent design, evaluation methodology, and experimentation into a repeatable, triggered workflow.

## Prerequisites

* An active **orq.ai** account
* An [API key](/docs/administer/api-keys)
* The **Orq MCP** server connected to the assistant (see [MCP Quickstart](/docs/integrations/code-assistants/mcp))

## Installation

Choose the option that matches the assistant used:

<CodeGroup>
  ```bash Claude Code plugin theme={"theme":{"light":"github-light","dark":"github-dark"}}
  # Installs skills, commands, agents, and the MCP server in one step
  claude plugin marketplace add orq-ai/claude-plugins
  claude plugin install orq-skills@orq-claude-plugin
  ```

  ```bash npx skills CLI theme={"theme":{"light":"github-light","dark":"github-dark"}}
  # Installs skills only: works with Cursor, Gemini CLI, and other compatible assistants
  npx skills add orq-ai/assistant-plugins
  ```
</CodeGroup>

<Note>
  Use **one path only**. The Claude Code plugin install includes the MCP server. Running both paths will install the MCP twice. Commands (`/orq:quickstart`, `/orq:workspace`, and others) and agents are only available with the Claude Code plugin.
</Note>

## Verify

**Claude Code:** Run the interactive onboarding command to confirm everything is working:

```
/orq:quickstart
```

**Cursor, Gemini CLI, and others:** Describe a task (e.g., "list my Orq.ai agents") and confirm the skill responds correctly.

## Commands

Quick-action slash commands available in [Claude Code](/docs/integrations/code-assistants/claude-code). Use `/orq:<command>` to trigger them.

| Command        | Description                                                                                                                                                                                                    | Usage                                                           |
| -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------- |
| **quickstart** | Interactive onboarding: credentials, MCP setup, skills tour                                                                                                                                                    | `/orq:quickstart`                                               |
| **workspace**  | Workspace overview: [Agents](/docs/agents/build), [Deployments](/docs/deployments/overview), [Prompts](/docs/prompts/creating), [Datasets](/docs/datasets/creating), [Experiments](/docs/experiments/overview) | `/orq:workspace [section]`                                      |
| **traces**     | Query and summarize [Traces](/docs/observability/traces) with filters                                                                                                                                          | `/orq:traces [--deployment name] [--status error] [--last 24h]` |
| **models**     | List available AI models by provider                                                                                                                                                                           | `/orq:models [search-term]`                                     |
| **analytics**  | Usage [Analytics](/docs/analytics/dashboards): requests, cost, tokens, errors                                                                                                                                  | `/orq:analytics [--last 24h] [--group-by model]`                |

## Skills

Skills are triggered by describing what is needed. The assistant picks the right skill automatically.

| Skill                          | Description                                                                                                                                                                                             | Docs                                                                                                         |
| ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
| **build-agent**                | Design, create, and configure an **Orq.ai** [Agent](/docs/agents/build) with tools, instructions, [Knowledge Bases](/docs/proxy/knowledge-bases), and [Memory](/docs/memory-stores/using-memory-stores) | [SKILL.md](https://github.com/orq-ai/assistant-plugins/blob/main/skills/build-agent/SKILL.md)                |
| **build-evaluator**            | Create validated LLM-as-a-Judge [Evaluators](/docs/hub/overview#evaluators) following evaluation best practices                                                                                         | [SKILL.md](https://github.com/orq-ai/assistant-plugins/blob/main/skills/build-evaluator/SKILL.md)            |
| **analyze-trace-failures**     | Read production [Traces](/docs/observability/traces), identify what is failing, build failure taxonomies, and categorize issues                                                                         | [SKILL.md](https://github.com/orq-ai/assistant-plugins/blob/main/skills/analyze-trace-failures/SKILL.md)     |
| **run-experiment**             | Create and run **Orq.ai** [Experiments](/docs/experiments/overview): compare configurations with specialized agent, conversation, and RAG evaluation                                                    | [SKILL.md](https://github.com/orq-ai/assistant-plugins/blob/main/skills/run-experiment/SKILL.md)             |
| **generate-synthetic-dataset** | Generate and curate evaluation [Datasets](/docs/datasets/creating): structured generation, quick from description, expansion, and dataset maintenance                                                   | [SKILL.md](https://github.com/orq-ai/assistant-plugins/blob/main/skills/generate-synthetic-dataset/SKILL.md) |
| **optimize-prompt**            | Analyze and optimize system [Prompts](/docs/prompts/creating) using a structured prompting guidelines framework                                                                                         | [SKILL.md](https://github.com/orq-ai/assistant-plugins/blob/main/skills/optimize-prompt/SKILL.md)            |
| **setup-observability**        | Instrument LLM applications with orq.ai tracing. Covers AI Router (zero-code traces) and OpenTelemetry/OpenInference. Guides from framework detection through baseline verification to trace enrichment | [SKILL.md](https://github.com/orq-ai/assistant-plugins/blob/main/skills/setup-observability/SKILL.md)        |
| **compare-agents**             | Run cross-framework agent comparisons: compare any combination of orq.ai, LangGraph, CrewAI, or OpenAI Agents SDK agents using evaluatorq                                                               | [SKILL.md](https://github.com/orq-ai/assistant-plugins/blob/main/skills/compare-agents/SKILL.md)             |

## Example workflows

### Instrument an existing app

```
"Add orq.ai tracing to my app"                 → setup-observability
/orq:traces --last 1h                           # Verify traces are flowing
"Analyze these failures"                        → analyze-trace-failures
```

### Build a new agent

```
"I need a customer support agent"              → build-agent
"Create test cases for it"                     → generate-synthetic-dataset
"Build an evaluator for response accuracy"     → build-evaluator
"Run an experiment to get a baseline"          → run-experiment
```

### Debug production issues

```
/orq:traces --status error --last 24h          # Find errors
"Analyze these failures"                       → analyze-trace-failures
"Fix the prompt based on the failure analysis" → optimize-prompt
"Re-run the experiment to verify the fix"      → run-experiment
```

### Improve an existing agent

```
/orq:analytics --group-by deployment           # Spot high error rates
"Analyze traces for the checkout agent"        → analyze-trace-failures
"Build evaluators for the failure modes"       → build-evaluator
"Generate a dataset covering edge cases"       → generate-synthetic-dataset
"Run an experiment and compare"                → run-experiment
"Optimize the prompt based on results"         → optimize-prompt
```

### Improve an existing prompt

```
"My prompt isn't performing well, help me improve it" → optimize-prompt
"Create test cases to compare before and after"       → generate-synthetic-dataset
"Build an evaluator for a specific dimension"         → build-evaluator
"Run an experiment: current vs optimized prompt"      → run-experiment
"Refine the prompt based on failure cases"            → optimize-prompt
```

## Resources

<Card title="orq-ai/assistant-plugins" icon="github" href="https://github.com/orq-ai/assistant-plugins">
  Source repository for all skills, commands, and agents
</Card>