Back to Details

scrying

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Scrying

Scrying

Observe a live remote system, service, or deployment in real time.
实时观察远程系统、服务或部署的状态。

What This Skill Does

此技能的作用

Use this spell when you need to see what is happening right now on a distant system rather than reading stale logs or cached reports. In this grimoire, Scrying is treated as a literal spell with a prototype delivery profile. Canonical reference input: Scrying (spell).
当你需要查看远程系统当前的实时状态，而非读取过时日志或缓存报告时，可使用此技能。 在这本魔法手册中，Scrying被视为一项具备原型交付配置的技能。 标准参考输入：Scrying（技能）。

When To Use

使用场景

  • You need live status from a remote service, server, or deployment.
  • Cached dashboards or old logs are not trustworthy enough for the decision at hand.
  • You want continuous observation of a system you cannot directly access.
  • You want to pull a live snapshot of your Home Assistant device states — all lights, sensors, locks, and climate status in one view.
  • 你需要获取远程服务、服务器或部署的实时状态。
  • 缓存的仪表板或旧日志不足以支撑当前决策。
  • 你希望持续观察无法直接访问的系统。
  • 你希望获取Home Assistant设备状态的实时快照——在一个视图中查看所有灯光、传感器、门锁和气候状态。

Prerequisites

前置条件

  • Environment variables available to Hermes: 
    HA_URL
    , 
    HA_TOKEN
    .
  • Primary credential or token: 
    HA_TOKEN
    .
  • Binaries on PATH: 
    curl
    .
  • Hermes可访问的环境变量：
    HA_URL
    、
    HA_TOKEN
    。
  • 主凭证或令牌：
    HA_TOKEN
    。
  • PATH中的可执行文件：
    curl
    。

Setup

设置步骤

  1. Confirm the required environment variables are available inside the active Hermes runtime, not just in a shell profile.
  2. Verify the required binaries resolve on PATH before you rely on them in a procedure.
  3. Choose a non-production or low-risk target first if the skill can page, unlock, alert, or touch a live integration.
  1. 确认所需环境变量在活跃的Hermes运行时中可用，而非仅存在于shell配置文件中。
  2. 在依赖这些可执行文件执行流程前，验证它们能在PATH中被找到。
  3. 如果该技能可发送通知、解锁设备、触发警报或触及实时集成，请先选择非生产环境或低风险目标进行测试。

Procedure

执行流程

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Identify the target system, service, or resource to observe.
  3. Establish the best available live data channel: API polling, log streaming, health endpoints, or dashboard scraping.
  4. Present the current state with explicit timestamps and staleness indicators.
  5. Maintain the scrying session with periodic refresh and alert on state changes.
  6. If Home Assistant is available, GET /api/states to retrieve all entity states and present a human-readable summary of the current home status.
  7. Stop for explicit confirmation before taking a live action that changes access, triggers an alert, or touches a real system boundary.
  8. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
  1. 在采取行动前，重述目标、成功条件以及任何不可触碰的边界。
  2. 确定要观察的目标系统、服务或资源。
  3. 建立最佳可用的实时数据通道：API轮询、日志流、健康检查端点或仪表板抓取。
  4. 展示当前状态，并附上明确的时间戳和过时状态标识。
  5. 通过定期刷新维持监控会话，并在状态变化时发出警报。
  6. 如果Home Assistant可用，调用GET /api/states接口获取所有实体状态，并以人类可读的形式呈现当前家居状态摘要。
  7. 在执行会改变访问权限、触发警报或触及真实系统边界的实时操作前，需等待明确确认。
  8. 将结果整理为以下交付物，并明确标注可信度、假设条件和未解决的风险。

Deliverables

交付物

  • A live or near-live status view of the target system.
  • Timestamps and refresh intervals so the user knows how stale each datum is.
  • Alerts or callouts for state changes detected during the session.
  • 目标系统的实时或近实时状态视图。
  • 时间戳和刷新间隔，让用户了解每个数据的过时程度。
  • 会话期间检测到状态变化时的警报或提示。

Pitfalls / Guardrails

注意事项/防护措施

  • Call out the glue, permissions, or missing infrastructure before you imply this is fully operational.
  • Do not access systems without the user's authorization and credentials.
  • Never conflate cached or stale data with live state — always label the observation time.
  • Prefer read-only observation channels; do not mutate the target to observe it.
  • Do not rely on a live integration until credentials, target scope, and rollback expectations are verified.
  • 在暗示该技能完全可用前，需说明所需的衔接组件、权限或缺失的基础设施。
  • 未经用户授权和提供凭证，不得访问系统。
  • 切勿将缓存或过时数据与实时状态混淆——始终标注观察时间。
  • 优先选择只读观察通道；不要为了观察而修改目标系统。
  • 在验证凭证、目标范围和回滚预期前，不要依赖实时集成。

Verification

验证步骤

  • Check that the result includes every deliverable promised above.
  • Check that confirmed facts, assumptions, and inferences are visibly separated.
  • Check that the exact live target, confirmation gate, and rollback or recovery path are explicit.
  • Check that any missing glue code, permissions, or future work is labeled before the skill is treated as ready.
  • Check the required environment variables and binaries in the active Hermes runtime before trusting the procedure on a live target.
  • 检查结果是否包含上述所有承诺的交付物。
  • 检查已确认的事实、假设和推论是否清晰区分。
  • 检查明确标注了实时目标、确认关卡以及回滚或恢复路径。
  • 在将技能视为可用前，检查是否标注了任何缺失的衔接代码、权限或未来工作。
  • 在信任该流程可用于实时目标前，检查活跃Hermes运行时中的所需环境变量和可执行文件是否齐全。

Example Invocation

调用示例

text
/scrying show me the live state of this system right now, with timestamps and staleness clearly labeled
text
/scrying show me the live state of this system right now, with timestamps and staleness clearly labeled