メニュー
New Relic observability integration for running NRQL queries, checking alert issues, and searching entities via NerdGraph during RCA investigations
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/Arvo-AI/aurora --skill newrelicコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Bitbucket code repository integration for managing repos, branches, PRs, issues, and CI/CD pipelines
Datadog monitoring integration for querying logs, metrics, monitors, events, traces, hosts, and incidents during RCA investigations
GitHub code repository integration for investigating code changes, deployments, commits, PRs, and suggesting fixes during RCA
SOC 職業分類に基づく
SKILL.md を表示中
| name | newrelic |
| id | newrelic |
| description | New Relic observability integration for running NRQL queries, checking alert issues, and searching entities via NerdGraph during RCA investigations |
| category | observability |
| connection_check | {"method":"get_token_data","provider_key":"newrelic","required_field":"api_key"} |
| tools | ["query_newrelic"] |
| index | Observability platform -- NRQL queries, alert issues, entity search via NerdGraph |
| rca_priority | 3 |
| allowed-tools | query_newrelic |
| metadata | {"author":"aurora","version":"1.0"} |
New Relic integration for querying observability data during Root Cause Analysis. New Relic is a REMOTE service. Use ONLY the query_newrelic API tool. All data is accessed via NerdGraph with resource_type parameter.
query_newrelic(resource_type=TYPE, query=QUERY, time_range=RANGE, limit=N)
'nrql' -- Run NRQL queries. query=NRQL string e.g. "SELECT count(*) FROM Transaction WHERE error IS true FACET appName"'issues' -- Active alert issues. query=state filter (ACTIVATED, CREATED, CLOSED)'entities' -- Search monitored entities (APM apps, hosts). query=entity name or filterTransaction, TransactionError, SystemSample, Log, Span, ProcessSampleFACET for grouping results by fieldTIMESERIES for trends over timeSINCE for time range (auto-injected from time_range if not present)LIMIT to cap results (auto-injected if not present)SELECT count(*) FROM TransactionError WHERE appName='X' SINCE 1 hour ago TIMESERIESSELECT average(cpuPercent) FROM SystemSample FACET hostname SINCE 30 minutes agoSELECT count(*) FROM Log WHERE level = 'ERROR' FACET service SINCE 1 hour agoSELECT average(duration) FROM Transaction WHERE appName='X' FACET name SINCE 1 hour agoSELECT rate(count(*), 1 minute) FROM Transaction FACET appName SINCE 1 hour ago TIMESERIESquery_newrelic(resource_type='entities', query='production-api')query_newrelic(resource_type='entities', query='production-api|APPLICATION')APPLICATION, HOST, MONITOR, WORKLOAD, DASHBOARDquery_newrelic(resource_type='nrql', query="SELECT count(*) FROM Transaction WHERE appName = 'my-app' SINCE 1 hour ago")query_newrelic(resource_type='issues', query='ACTIVATED')query_newrelic(resource_type='entities', query='production-api')Step 1 -- Check alert issues for active/related context:
query_newrelic(resource_type='issues', query='ACTIVATED')
Step 2 -- Search entities to identify affected services and hosts:
query_newrelic(resource_type='entities', query='affected-service')
Step 3 -- Use NRQL to query transactions and errors around the alert time:
query_newrelic(resource_type='nrql', query="SELECT count(*) FROM TransactionError FACET appName SINCE 1 hour ago TIMESERIES")
Step 4 -- Check infrastructure metrics:
query_newrelic(resource_type='nrql', query="SELECT average(cpuPercent), average(memoryUsedPercent) FROM SystemSample FACET hostname SINCE 1 hour ago")
Step 5 -- Correlate with logs:
query_newrelic(resource_type='nrql', query="SELECT count(*) FROM Log WHERE level = 'ERROR' FACET service, message SINCE 1 hour ago")
query_newrelic API tool.resource_type parameter is required and must be one of: nrql, issues, entities.'nrql' for any data query -- logs, metrics, transactions, errors, spans, infrastructure.time_range parameter (e.g., '1 hour', '30 minutes') is only used when the NRQL query does not already contain a SINCE clause.LIMIT or more specific WHERE clauses to narrow results.