alarm

分类: 商业与运营 | 上传者: CloudChef | 下载: 0 | 版本: v1.0（最新）

报警操作技巧。列出警报，使用数据源丰富的资源事实分析警报规则上下文，并根据修复指南执行警报状态操作。

更新日志: Source: GitHub https://github.com/CloudChef/atlasclaw-providers

目录结构

当前层级: tree/main/providers/SmartCMP-Provider/skills/alarm/

📁 references/
- 📄 WORKFLOW.md 1.7 KB
📁 scripts/
- 📄 _alarm_common.py 9.8 KB
- 📄 _analysis.py 15.5 KB
- 📄 analyze_alert.py 10.7 KB
- 📄 list_alerts.py 6.0 KB
- 📄 operate_alert.py 2.3 KB
📄 SKILL.md 2.4 KB

SKILL.md

---
name: "alarm"
description: "Alarm operations skill. List alerts, analyze alert rule context with datasource-enriched resource facts, and perform alert status operations with remediation guidance."
provider_type: "smartcmp"
instance_required: "true"

# === LLM Context Fields ===
triggers:
  - list alarms
  - show alerts
  - analyze alert
  - mute alert
  - resolve alert
  - reopen alert
  - operate alert

use_when:
  - User wants to inspect alarms or alerts
  - User needs rule-aware, resource-aware alarm analysis with remediation recommendations
  - User wants to mute, resolve, or reopen alerts

avoid_when:
  - User wants approval actions (use approval skill)
  - User wants resource requests (use request skill)
  - User only wants standalone reference data browsing without alarm analysis (use datasource skill)

examples:
  - "Show current alarms"
  - "Analyze alert ALM-1001"
  - "Mute alert ALM-1001"
  - "Resolve alerts ALM-1001 and ALM-1002"

related:
  - approval
  - datasource
---

# alarm

Alarm workflow for triggered alert retrieval, rule-aware analysis, and
status operations.

## Purpose

Provide alarm-management capabilities:
- List triggered alerts with machine-readable metadata
- Analyze one alert with normalized facts, datasource-enriched resource context, assessment, and remediation guidance
- Perform validated status operations (`mute`, `resolve`, `reopen`)

## Scripts

| Script | Description | Location |
|--------|-------------|----------|
| `list_alerts.py` | Query `/alarm-alert` and emit `##ALARM_META_START##` metadata | `scripts/` |
| `analyze_alert.py` | Fetch alert + rule context, enrich related resources via datasource `list_resource.py`, and emit `##ALARM_ANALYSIS_START##` output | `scripts/` |
| `operate_alert.py` | Call `/alarm-alert/operation` for validated status changes | `scripts/` |

## Workflow

See [references/WORKFLOW.md](references/WORKFLOW.md) for the supported workflow.

## Resource Enrichment

During alert analysis, this skill should silently reuse the datasource skill's
shared `../shared/scripts/list_resource.py` flow when the alert exposes
`entityInstanceId` or `nodeInstanceId`.

- Resolve related SmartCMP resources before finalizing the analysis narrative.
- Merge normalized `type + properties` resource facts into the alert analysis payload.
- If resource lookup is unavailable, continue the alert analysis with core alert
  and policy facts, and treat resource enrichment as best-effort context.

登录后下载/点赞/收藏 ❤ 9 | ★ 0

alarm

目录结构

SKILL.md

举报内容

提示