菜单
New Relic APM and monitoring. Use when running NRQL queries, checking application performance, error rates, or throughput via New Relic.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Pull incident context from alerting platforms (PagerDuty). Use when investigating who's on-call, incident history, alert patterns, or MTTR metrics.
Opsgenie alert management and on-call scheduling. Use for listing alerts, checking on-call, computing MTTA/MTTR, and alert fatigue analysis. Supports team and priority filtering.
Amplitude product analytics. Use when querying user events, funnels, retention, or product usage data. Provides event segmentation, user activity lookup, and annotation queries.
Google BigQuery data warehouse queries and schema inspection. Use when running SQL queries, listing datasets/tables, or inspecting table schemas in BigQuery.
MySQL/MariaDB database inspection and queries. Use when investigating table schemas, running queries, checking processlist, replication status, InnoDB engine status, or lock contention.
PostgreSQL database inspection and queries. Use when investigating table schemas, running queries, checking locks, replication status, or long-running queries.
| name | observability-newrelic |
| description | New Relic APM and monitoring. Use when running NRQL queries, checking application performance, error rates, or throughput via New Relic. |
| allowed-tools | Bash(python *) |
IMPORTANT: Credentials are injected automatically by a proxy layer. Do NOT check for NEWRELIC_API_KEY in environment variables - it won't be visible to you. Just run the scripts directly; authentication is handled transparently.
Configuration environment variables you CAN check (non-secret):
NEWRELIC_ACCOUNT_ID - New Relic account IDNEWRELIC_BASE_URL - API base URL (proxy mode)All scripts are in .claude/skills/observability-newrelic/scripts/
python .claude/skills/observability-newrelic/scripts/query_nrql.py --account-id ACCOUNT_ID --query "SELECT average(duration) FROM Transaction SINCE 1 hour ago"
python .claude/skills/observability-newrelic/scripts/get_apm_summary.py --account-id ACCOUNT_ID --app-name MyApp [--time-range 30m]
-- Response time
SELECT average(duration) FROM Transaction WHERE appName = 'MyApp' SINCE 1 hour ago
-- Throughput
SELECT count(*) FROM Transaction WHERE appName = 'MyApp' SINCE 1 hour ago TIMESERIES 5 minutes
-- Error rate
SELECT percentage(count(*), WHERE error = true) FROM Transaction WHERE appName = 'MyApp' SINCE 1 hour ago
-- Apdex score
SELECT apdex(duration, t: 0.5) FROM Transaction WHERE appName = 'MyApp' SINCE 1 hour ago
-- Slowest transactions
SELECT average(duration), count(*) FROM Transaction WHERE appName = 'MyApp' SINCE 1 hour ago FACET name LIMIT 10
-- Database query time
SELECT average(databaseDuration) FROM Transaction WHERE appName = 'MyApp' SINCE 1 hour ago TIMESERIES
-- External service calls
SELECT average(externalDuration), count(*) FROM Transaction WHERE appName = 'MyApp' SINCE 1 hour ago FACET externalTransactionName
1. get_apm_summary.py --account-id <id> --app-name <app> (overview)
2. query_nrql.py --query "SELECT average(duration) FROM Transaction WHERE appName = '<app>' SINCE 1 hour ago TIMESERIES 5 minutes"
3. query_nrql.py --query "SELECT percentage(count(*), WHERE error = true) FROM Transaction WHERE appName = '<app>' SINCE 1 hour ago TIMESERIES 5 minutes"