[
  {
    "id": "docs-reference-architecture-001",
    "question": "I'm using the architecture reference. Help me verify implementation and operations details so I can make changes or debug behavior from the right mental model.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user verify implementation and operations details and gives enough concrete guidance, decision criteria, verification steps, or risk framing to make changes or debug behavior from the right mental model."
  },
  {
    "id": "docs-reference-architecture-002",
    "question": "I'm locating the right layer for a change. Help me connect structure, lifecycle, and ownership so I can edit the plugin, blueprint, or sandbox layer intentionally.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user connect structure, lifecycle, and ownership and gives enough concrete guidance, decision criteria, verification steps, or risk framing to edit the plugin, blueprint, or sandbox layer intentionally."
  },
  {
    "id": "docs-reference-architecture-003",
    "question": "I'm modifying architecture-sensitive files. Help me understand the invariants that must remain true so I can avoid breaking sandbox creation or operation.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user understand the invariants that must remain true and gives enough concrete guidance, decision criteria, verification steps, or risk framing to avoid breaking sandbox creation or operation."
  },
  {
    "id": "docs-reference-cli-selection-guide-001",
    "question": "I'm choosing between `nemoclaw` and `openshell`. Help me pick the command surface that owns my operation so I can complete the task without breaking NemoClaw management.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user pick the command surface that owns my operation and gives enough concrete guidance, decision criteria, verification steps, or risk framing to complete the task without breaking NemoClaw management."
  },
  {
    "id": "docs-reference-cli-selection-guide-002",
    "question": "I'm tempted to run a low-level OpenShell command. Help me understand when it bypasses NemoClaw lifecycle expectations so I can avoid unsupported or confusing states.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user understand when it bypasses NemoClaw lifecycle expectations and gives enough concrete guidance, decision criteria, verification steps, or risk framing to avoid unsupported or confusing states."
  },
  {
    "id": "docs-reference-cli-selection-guide-003",
    "question": "I'm doing onboarding, policy, debugging, or low-level sandbox work. Help me apply a simple CLI selection rule so I can move quickly without memorizing every command boundary.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user apply a simple CLI selection rule and gives enough concrete guidance, decision criteria, verification steps, or risk framing to move quickly without memorizing every command boundary."
  },
  {
    "id": "docs-reference-commands-001",
    "question": "I'm opening the CLI command reference. Help me find the exact action, flag, or recovery path I need so I can run the right command without scanning source code.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user find the exact action, flag, or recovery path I need and gives enough concrete guidance, decision criteria, verification steps, or risk framing to run the right command without scanning source code."
  },
  {
    "id": "docs-reference-commands-002",
    "question": "I'm choosing among setup, lifecycle, policy, inference, and diagnostic commands. Help me see command groups and examples clearly so I can locate the right command faster.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user see command groups and examples clearly and gives enough concrete guidance, decision criteria, verification steps, or risk framing to locate the right command faster."
  },
  {
    "id": "docs-reference-commands-003",
    "question": "I'm using `nemoclaw` in scripts or CI. Help me understand example output and exit behavior so I can automate safely and handle failures correctly.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user understand example output and exit behavior and gives enough concrete guidance, decision criteria, verification steps, or risk framing to automate safely and handle failures correctly."
  },
  {
    "id": "docs-reference-network-policies-001",
    "question": "I'm reading the network policy reference. Help me understand baseline access decisions so I can assess the sandbox's default exposure.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user understand baseline access decisions and gives enough concrete guidance, decision criteria, verification steps, or risk framing to assess the sandbox's default exposure."
  },
  {
    "id": "docs-reference-network-policies-002",
    "question": "I'm reviewing default rules and filesystem constraints. Help me know what is allowed before any customization so I can decide what needs to change for my environment.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user know what is allowed before any customization and gives enough concrete guidance, decision criteria, verification steps, or risk framing to decide what needs to change for my environment."
  },
  {
    "id": "docs-reference-network-policies-003",
    "question": "I'm tracing a denied request. Help me understand how operator approval turns into policy so I can audit and reason about egress changes.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user understand how operator approval turns into policy and gives enough concrete guidance, decision criteria, verification steps, or risk framing to audit and reason about egress changes."
  },
  {
    "id": "docs-reference-troubleshooting-001",
    "question": "I'm troubleshooting a NemoClaw problem. Help me map my symptom to the fastest safe recovery step so I can get unstuck without making the environment worse.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user map my symptom to the fastest safe recovery step and gives enough concrete guidance, decision criteria, verification steps, or risk framing to get unstuck without making the environment worse."
  },
  {
    "id": "docs-reference-troubleshooting-002",
    "question": "I'm uncertain which subsystem failed. Help me run diagnostics that separate install, onboarding, runtime, policy, and inference issues so I can focus on the likely cause.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user run diagnostics that separate install, onboarding, runtime, policy, and inference issues and gives enough concrete guidance, decision criteria, verification steps, or risk framing to focus on the likely cause."
  },
  {
    "id": "docs-reference-troubleshooting-003",
    "question": "I'm asking the community or filing an issue. Help me collect the right logs, versions, and error details so I can give maintainers enough information to help.",
    "expected_skill": "nemoclaw-user-reference",
    "ground_truth": "A NemoClaw-specific answer that helps the user collect the right logs, versions, and error details and gives enough concrete guidance, decision criteria, verification steps, or risk framing to give maintainers enough information to help."
  }
]