onboarding-summary

作者: datadog-labs

產生即時單步儀器(SSI)入門確認報告 — 驗證APM儀器是否端到端正常運作,並包含深入連結至…

npx skills add https://github.com/datadog-labs/agent-skills --skill onboarding-summary

APM Onboarding Summary

Triggers

Invoke this skill when:

  • All steps in verify-ssi have passed
  • All checks in troubleshoot-ssi have been resolved
  • The user asks "is everything working?", "show me the status", or "confirm APM is set up"

Do NOT invoke this skill if any verification or troubleshooting check is still failing — resolve those first.


Context to resolve before acting

VariableHow to resolve
AGENT_NAMESPACENamespace where Datadog Agent is installed
APP_NAMESPACENamespace of the application
APP_LABELCheck spec.selector.matchLabels.app in the Deployment manifest
CLUSTER_NAMEspec.global.clusterName in datadog-agent.yaml
SERVICE_NAMEtags.datadoghq.com/service label on the Deployment
ENVtags.datadoghq.com/env label on the Deployment
DD_SITEspec.global.site in datadog-agent.yaml

Prerequisites

Claude runs

pup auth status --site <DD_SITE>

If valid token — proceed.

ERROR: Not authenticated:

Claude runs

pup auth login --site <DD_SITE>

This opens a browser tab for OAuth. Complete the login there — Claude will continue once the command exits.


Collect live confirmation data

Run all of the following. Each populates a row in the final report.

Claude runs

# Agent pod count and status
kubectl get pods -n <AGENT_NAMESPACE> \
  -l app.kubernetes.io/component=agent \
  --no-headers

# SSI instrumentation config live in cluster
kubectl get datadogagent datadog -n <AGENT_NAMESPACE> \
  -o jsonpath='{.spec.features.apm.instrumentation}'

# Init container confirmed in app pod spec
kubectl get pod -l app=<APP_LABEL> -n <APP_NAMESPACE> \
  -o jsonpath='{.items[0].spec.initContainers[*].name}'

# Service visible and traced in APM
DD_SITE=<DD_SITE> pup apm services list --env <ENV> --from 1h

# Traces arriving in the last hour
DD_SITE=<DD_SITE> pup traces search --query "service:<SERVICE_NAME>" --from 1h --limit 5

Present the report

Fill in every value from live command output. Do not leave any placeholder unfilled. If a value cannot be confirmed, mark that row as failed and link to troubleshoot-ssi.


APM onboarding complete

CheckDetailStatus
Datadog Agent<N> pod(s) Running in <AGENT_NAMESPACE>OK
SSI enabledTargeting namespace <APP_NAMESPACE>, language <LANGUAGE> v<MAJOR_VERSION>OK
Init container injecteddatadog-lib-<language>-init present in pod specOK
Tracer reportingService <SERVICE_NAME> appears in pup apm services list with isTraced: trueOK
APM service visible<SERVICE_NAME> in env <ENV>OK
Traces arriving<N> trace(s) found in the last hourOK

Your service in Datadog — click to open:

Construct each URL by substituting real values. Do not print placeholder URLs.

ViewURL
Service overviewhttps://app.<DD_SITE>/apm/services/<SERVICE_NAME>?env=<ENV>
Traces explorerhttps://app.<DD_SITE>/apm/traces?query=service:<SERVICE_NAME>%20env:<ENV>
Service maphttps://app.<DD_SITE>/apm/map?env=<ENV>&service=<SERVICE_NAME>
Agent fleethttps://app.<DD_SITE>/fleet-automation

Security constraints

  • Never write a raw API key into any file or chat message

來自 datadog-labs 的更多技能

dd-audit
datadog-labs
稽核軌跡調查——誰變更了什麼、金鑰遭入侵、成本飆升的根本原因、合規證據(SOC 2/PCI),以及AI活動稽核。
official
agent-install
datadog-labs
Install the Datadog Agent on Kubernetes using the Datadog Operator — required before enabling Single Step Instrumentation (SSI), which automatically…
official
agent-observability-auto-experiment
datadog-labs
針對真實的 Datadog LLM-Obs 資料執行迭代式程式碼改進爬山演算法,以 Claude Code 作為代理程式在本機端運行。建立基準評估,逐步進行…
official
agent-observability-eval-bootstrap
datadog-labs
Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts…
official
agent-observability-eval-pipeline
datadog-labs
為已儀器化的 ml_app 設計的端到端 Agent Observability 管線 — 分類生產追蹤、根因分析故障、啟動評估器,然後(可選地)…
official
agent-observability-experiment-analyzer
datadog-labs
分析LLM實驗結果。處理單一或對比實驗,探索性或問答模式。當使用者說「分析實驗」、「比較…」時使用。
official
agent-observability-replay-trace
datadog-labs
當開發者想要針對某一個特定的 Agent Observability / LLM Obs trace(其輸出結果不盡理想)進行迭代時使用——將該 trace 重新對其……
official
agent-observability-trace-rca
datadog-labs
Root cause analysis on production LLM traces. Diagnoses why an LLM application is failing — works from eval judge verdicts, runtime errors, or structural…
official