Skip to content
Back to search

dynatrace-for-ai

MarketplaceWorks with Claude CodeGitHub

Skills, prompts, and instructions for building AI agents on top of Dynatrace production context

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/dynatrace/dynatrace-for-ai with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/dynatrace/dynatrace-for-ai'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/dynatrace-dynatrace-for-ai/badge.svg)](/listings/dynatrace-dynatrace-for-ai)

HTML

<a href="/listings/dynatrace-dynatrace-for-ai"><img src="/api/listings/dynatrace-dynatrace-for-ai/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Skills Package (skills.sh)

npx skills add dynatrace/dynatrace-for-ai

Works with Claude Code, Cursor, Cline, GitHub Copilot, OpenCode, and other [compatible agents](https://agentskills.io).

Claude Code Plugin

claude plugin install dynatrace@claude-plugins-official

Prefer browsing interactively? Run `/plugin` in Claude Code, open the **Discover** tab, and search "Dynatrace".

The plugin includes skills as well as the Dynatrace MCP server. Set these environment variables before starting Claude Code to connect it to your environment:

export DT_ENVIRONMENT=https://<env>.apps.dynatrace.com   # e.g. https://abc12345.apps.dynatrace.com
export DT_PLATFORM_TOKEN=<your-platform-token>

Verify that it works via:

claude mcp login plugin:dynatrace:dynatrace

Please consult the [Dynatrace MCP server docs ](https://docs.dynatrace.com/docs/shortlink/dynatrace-mcp-server) for a full list of scopes required for using the MCP Server with a Platform Token.

To update the plugin, use:

claude plugin marketplace update
claude plugin update dynatrace@claude-plugins-official

Note: The bundled MCP server connects to your Dynatrace environment. See the [Dynatrace Privacy Policy](https://www.dynatrace.com/company/trust-center/privacy/) for details on data handling.

Cursor Plugin

The Dynatrace plugin is listed on the [Cursor Marketplace](https://cursor.com/marketplace/mcp/dynatrace). Install is GUI-only: open **Customize** in the Cursor sidebar, find "Dynatrace", select **Install**, and choose project or user scope.

Set the same `DT_ENVIRONMENT` and `DT_PLATFORM_TOKEN` environment variables shown above before starting Cursor.

Manual

Copy skill directories into your agent's skills path (`.agents/skills/`, `.claude/skills/`, `.cursor/skills/`, etc.).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 11 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "dynatrace-for-ai",
  3. "owner": { "name": "Dynatrace" },
  4. "plugins": [
  5. {
  6. "name": "dynatrace",
  7. "description": "Dynatrace observability skills and knowledge packages for AI coding agents.",
  8. "source": "./"
  9. }
  10. ]
  11. }
README.md · README · 216 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Dynatrace for AI
  2. [![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/Dynatrace/dynatrace-for-ai/badge)](https://scorecard.dev/viewer/?uri=github.com/Dynatrace/dynatrace-for-ai)
  3. Everything AI agents need to work with [Dynatrace](https://www.dynatrace.com), starting with skills.
  4. **Skills** are portable knowledge packages following the [Agent Skills](https://agentskills.io) open format. They give AI coding agents the domain-specific context to query, analyze, and interpret Dynatrace data. They work with Claude Code, GitHub Copilot, Cursor, OpenCode, Gemini CLI, and [30+ other compatible tools](https://agentskills.io).
  5. ## Installation
  6. ### Skills Package (skills.sh)
  7. ```bash
  8. npx skills add dynatrace/dynatrace-for-ai
  9. ```
  10. Works with Claude Code, Cursor, Cline, GitHub Copilot, OpenCode, and other [compatible agents](https://agentskills.io).
  11. ### Claude Code Plugin
  12. ```bash
  13. claude plugin install dynatrace@claude-plugins-official
  14. ```
  15. Prefer browsing interactively? Run `/plugin` in Claude Code, open the **Discover** tab, and search "Dynatrace".
  16. The plugin includes skills as well as the Dynatrace MCP server. Set these environment variables before starting Claude Code to connect it to your environment:
  17. ```bash
  18. export DT_ENVIRONMENT=https://<env>.apps.dynatrace.com # e.g. https://abc12345.apps.dynatrace.com
  19. export DT_PLATFORM_TOKEN=<your-platform-token>
  20. ```
  21. Verify that it works via:
  22. ```bash
  23. claude mcp login plugin:dynatrace:dynatrace
  24. ```
  25. Please consult the [Dynatrace MCP server docs
  26. ](https://docs.dynatrace.com/docs/shortlink/dynatrace-mcp-server) for a full list of scopes required for using the MCP Server with a Platform Token.
  27. To update the plugin, use:
  28. ```bash
  29. claude plugin marketplace update
  30. claude plugin update dynatrace@claude-plugins-official
  31. ```
  32. Note: The bundled MCP server connects to your Dynatrace environment. See the [Dynatrace Privacy Policy](https://www.dynatrace.com/company/trust-center/privacy/) for details on data handling.
  33. ### Cursor Plugin
  34. The Dynatrace plugin is listed on the [Cursor Marketplace](https://cursor.com/marketplace/mcp/dynatrace). Install is GUI-only: open **Customize** in the Cursor sidebar, find "Dynatrace", select **Install**, and choose project or user scope.
  35. Set the same `DT_ENVIRONMENT` and `DT_PLATFORM_TOKEN` environment variables shown above before starting Cursor.
  36. ### Google Antigravity Plugin
  37. Install the plugin with the Antigravity CLI:
  38. ```bash
  39. agy plugin install https://github.com/Dynatrace/dynatrace-for-ai
  40. ```
  41. In the Antigravity CLI you can also run `/plugin install https://github.com/Dynatrace/dynatrace-for-ai`.
  42. The plugin includes all skills and the Dynatrace MCP server. It stays disabled until you configure the MCP server. Open `/plugin`, select **dynatrace**, and turn it on. Then enter:
  43. - `DT_ENVIRONMENT`: your environment URL, e.g. `https://abc12345.apps.dynatrace.com` (`https://` is required; leave off the trailing slash)
  44. - `DT_PLATFORM_TOKEN`: a platform token with the [MCP gateway scopes](https://docs.dynatrace.com/docs/shortlink/dynatrace-mcp-server)
  45. You can change these values later from **Configure MCP servers...** in `/plugin`. Antigravity does not read them from your shell environment.
  46. ### Devin Plugin
  47. The Dynatrace plugin is listed on the [Devin Marketplace](https://github.com/CognitionAI/devin-marketplace/tree/main/plugins/dynatrace). Install via the Devin CLI:
  48. ```bash
  49. devin plugins install CognitionAI/devin-marketplace#plugins/dynatrace
  50. ```
  51. Or from the Devin web app: **Customize → Plugins → Add plugin → From repository**.
  52. Enter your Dynatrace environment host and a platform token with the [MCP gateway scopes](https://docs.dynatrace.com/docs/shortlink/dynatrace-mcp-server) when prompted. Skills ship bundled with the plugin; the listing is maintained directly in Cognition's repo, synced from this one.
  53. ### Manual
  54. Copy skill directories into your agent's skills path (`.agents/skills/`, `.claude/skills/`, `.cursor/skills/`, etc.).
  55. ## Connecting to Dynatrace
  56. Skills provide knowledge only. To run live queries and manage your environment, pair them with a tool.
  57. ### Dynatrace CLI (dtctl)
  58. **[dtctl](https://github.com/dynatrace-oss/dtctl)** is a kubectl-style CLI for the Dynatrace platform. It ships with its own [Agent Skill](https://github.com/dynatrace-oss/dtctl/tree/main/skills/dtctl) that teaches agents how to operate it.
  59. ```bash
  60. brew install dynatrace-oss/tap/dtctl # Install
  61. dtctl auth login --context my-env \
  62. --environment "https://<env>.apps.dynatrace.com" # Authenticate
  63. npx skills add dynatrace-oss/dtctl # Install the dtctl skill
  64. dtctl doctor # Verify setup
  65. ```
  66. Or install the dtctl skill with dtctl itself: `dtctl skills install`
  67. ### Dynatrace MCP Server
  68. The **[Dynatrace MCP server](https://docs.dynatrace.com/docs/shortlink/dynatrace-mcp-server)** provides Dynatrace API access via MCP. The Claude Code plugin bundles the MCP server configuration automatically — just set `DT_ENVIRONMENT` and `DT_PLATFORM_TOKEN` as shown above. For other agents that support MCP natively, see the [MCP server docs](https://docs.dynatrace.com/docs/shortlink/dynatrace-mcp-server).
  69. The MCP server is remote — Dynatrace hosts it, so there is nothing to install. Releases are published to the [official MCP registry](https://registry.modelcontextprotocol.io) as `io.github.Dynatrace/dynatrace-for-ai`, so MCP hosts that read the registry can add it by name.
  70. ## Skills
  71. ### DQL & Query Language
  72. | Skill | Description |
  73. |-------|-------------|
  74. | [dt-dql-essentials](skills/dt-dql-essentials/SKILL.md) | DQL syntax rules, common pitfalls, and query patterns. Load this before writing any DQL. |
  75. ### Observability
  76. | Skill | Description |
  77. |-------|-------------|
  78. | [dt-obs-services](skills/dt-obs-services/SKILL.md) | Service RED metrics and runtime telemetry for .NET, Java, Node.js, Python, PHP, and Go. |
  79. | [dt-obs-frontends](skills/dt-obs-frontends/SKILL.md) | Real User Monitoring, Web Vitals, user sessions, mobile crashes, and frontend errors. |
  80. | [dt-obs-tracing](skills/dt-obs-tracing/SKILL.md) | Distributed traces, spans, service dependencies, and failure detection. |
  81. | [dt-obs-hosts](skills/dt-obs-hosts/SKILL.md) | Host and process metrics: CPU, memory, disk, network, and containers. |
  82. | [dt-obs-kubernetes](skills/dt-obs-kubernetes/SKILL.md) | Kubernetes clusters, pods, nodes, workloads, labels, and resource relationships. |
  83. | [dt-obs-aws](skills/dt-obs-aws/SKILL.md) | AWS resources: EC2, RDS, Lambda, ECS/EKS, VPC, load balancers, and cost optimization. |
  84. | [dt-obs-azure](skills/dt-obs-azure/SKILL.md) | Azure resources: VMs, VMSS, SQL Database, Storage, AKS, App Service, Functions, VNet, Event Hubs, Container Apps, and Key Vault. |
  85. | [dt-obs-gcp](skills/dt-obs-gcp/SKILL.md) | GCP resources: Compute Engine, GKE, Cloud Run, Pub/Sub, VPC, DNS, IAM, and Secret Manager. |
  86. | [dt-obs-logs](skills/dt-obs-logs/SKILL.md) | Log queries, filtering, pattern analysis, and log correlation. |
  87. | [dt-obs-problems](skills/dt-obs-problems/SKILL.md) | Problem entities, root cause analysis, impact assessment, and problem correlation. |
  88. | [dt-obs-predictive-analytics](skills/dt-obs-predictive-analytics/SKILL.md) | Time series forecasting, capacity saturation planning, and trend/anomaly detection across hosts, services, and infrastructure. |
  89. | [dt-alerting](skills/dt-alerting/SKILL.md) | End-to-end alerting lifecycle: anomaly detector setup, alert events in Grail, problem grouping, and workflow notification routing. |
  90. | [dt-obs-analytics](skills/dt-obs-analytics/SKILL.md) | Analyze Dynatrace dashboards and notebooks with Davis analyzers: anomaly detection, novelty scoring, and metric correlation. |
  91. | [dt-obs-ext-monitors](skills/dt-obs-ext-monitors/SKILL.md) | Ingest third-party test and monitor results into Dynatrace Grail via the platform events ingest API. |
  92. | [dt-obs-extensions](skills/dt-obs-extensions/SKILL.md) | Check Dynatrace extension status and troubleshoot extension errors: monitoring configuration status, error diagnosis, and error code interpretation. |
  93. | [dt-obs-genai](skills/dt-obs-genai/SKILL.md) | Analyze observability signals from GenAI applications: golden signals, LLM cost/token analytics, agent tool-call behavior, and evaluation results. |
  94. | [dt-obs-log-semantic-mapping](skills/dt-obs-log-semantic-mapping/SKILL.md) | Suggest and validate semantic dictionary mappings for audit log integrations, using vendor log payloads or live ingested events. |
  95. | [dt-obs-network-devices](skills/dt-obs-network-devices/SKILL.md) | Analyze SNMP-monitored network devices (switches, routers, firewalls, load balancers): topology, interface metrics, and SNMP trap/syslog events. |
  96. | [dt-obs-network-flows](skills/dt-obs-network-flows/SKILL.md) | Analyze network flows from OneAgent, NetFlow/IPFIX/sFlow, and cloud VPC flow logs: top talkers, communication dependencies, and connection health. |
  97. ### Security
  98. | Skill | Description |
  99. |-------|-------------|
  100. | [dt-sec-insights](skills/dt-sec-insights/SKILL.md) | Query and analyze security data in `security.events`: Runtime Vulnerability Analytics, Runtime Application Protection, Automated Detections (MITRE ATT&CK), and Security Posture Management (KSPM/CSPM). |
  101. | [dt-sec-contextualization](skills/dt-sec-contextualization/SKILL.md) | Resolve security signals and IoC matches to runtime entities, and connect findings across topology levels through a shared runtime entity. |
  102. | [dt-sec-ioc-hunting](skills/dt-sec-ioc-hunting/SKILL.md) | Hunt threat-intelligence indicators of compromise across logs and spans, producing a threat-exposure score. |
  103. | [dt-sec-semantic-mapping](skills/dt-sec-semantic-mapping/SKILL.md) | Suggest and validate semantic dictionary mappings for new security integrations, using vendor API samples or live events. |
  104. | [dt-obs-compliance-assistant](skills/dt-obs-compliance-assistant/SKILL.md) | Monitor and investigate EU DORA compliance posture: compliance score, Critical/Important Function (CIF) health, incident classification, and ICT risk inputs. |
  105. ### Instrumentation Setup
  106. | Skill | Description |
  107. |-------|-------------|
  108. | [dt-setup-oneagent](skills/dt-setup-oneagent/SKILL.md) | Reference for installing Dynatrace OneAgent across VMs, Kubernetes, AWS Lambda, Windows hosts, remote EC2 instances, and Azure VMs/VMSS. |
  109. | [dt-setup-android](skills/dt-setup-android/SKILL.md) | Instrument an existing Android project (Kotlin or Java) with the Dynatrace Mobile Agent: Gradle plugin, agent config, and user privacy opt-in. |
  110. | [dt-setup-flutter](skills/dt-setup-flutter/SKILL.md) | Integrate the Dynatrace Flutter Plugin: dependency setup, config, SDK bootstrap, navigation tracking, and verification. |
  111. | [dt-setup-ios](skills/dt-setup-ios/SKILL.md) | Set up the Dynatrace iOS SDK via Swift Package Manager: SPM dependency, Dynatrace.plist config, privacy opt-in, and Xcode build verification. |
  112. | [dt-setup-react-native](skills/dt-setup-react-native/SKILL.md) | Integrate the Dynatrace React Native Plugin for bare React Native and Expo: dependency setup, dynatrace.config.js, Babel registration, navigation tracking, and verification. |
  113. | [dt-setup-genai](skills/dt-setup-genai/SKILL.md) | Instrument a GenAI/LLM app (Python or TypeScript, any provider or agent SDK) to emit OpenTelemetry `gen_ai.*` spans queryable in Dynatrace: detect, instrument, enrich, validate. |
  114. | [dt-setup-openinference-migration](skills/dt-setup-openinference-migration/SKILL.md) | Migrate a GenAI/LLM app from Traceloop/OpenLLMetry to OpenInference with `gen_ai.*` semantic conventions enabled, including ingestion shape and cardinality trade-offs. |
  115. ### Platform
  116. | Skill | Description |
  117. |-------|-------------|
  118. | [dt-app-dashboards](skills/dt-app-dashboards/SKILL.md) | Create, modify, and analyze Dynatrace dashboards: tiles, layouts, variables, and visualizations. |
  119. | [dt-app-notebooks](skills/dt-app-notebooks/SKILL.md) | Create, modify, and analyze Dynatrace notebooks: sections, DQL queries, and analytics workflows. |
  120. | [dt-js-runtime](skills/dt-js-runtime/SKILL.md) | Dynatrace server-side JavaScript runtime: function contract, runtime limits, Web APIs, Node.js modules, and the `@dynatrace-sdk/*` catalog. |
  121. | [dt-platform-costs](skills/dt-platform-costs/SKILL.md) | Query and analyze a Dynatrace tenant's actual billing and usage data with DQL: DPS consumption breakdown, cost-normalized spend ranking, chargeback/showback, cost drivers, and entity-level cost drill-down. |
  122. ### Migration
  123. | Skill | Description |
  124. |-------|-------------|
  125. | [dt-migration](skills/dt-migration/SKILL.md) | Migrate classic entity-based DQL and topology navigation to Smartscape equivalents. |
  126. | [dt-upgrade](skills/dt-upgrade/SKILL.md) | Guide an upgrade from classic/2nd-gen to 3rd-gen Dynatrace: tenant readiness, migration actions per feature area, and AWS/Azure/GCP cloud integration cutover to Smartscape on Grail. |
  127. ## Prompts
  128. **Prompts** are reusable task templates for common Dynatrace workflows. You can copy them from the `/prompts/` directory and paste them directly into any AI chat. For VS Code/GitHub Copilot users, copy prompts into `.github/prompts/` to use as slash commands (e.g. `/troubleshoot-problem`).
  129. Each prompt references the relevant skills above — load those skills first for best results.
  130. | Prompt | Description |
  131. |--------|-------------|
  132. | [dt-daily-standup](prompts/dt-daily-standup.prompt.md) | Generate a daily standup report for one or more services. |
  133. | [dt-health-check](prompts/dt-health-check.prompt.md) | Check the health of a service in production. |
  134. | [dt-incident-response](prompts/dt-incident-response.prompt.md) | Respond to an active production incident with triage, root cause, and a shareable report. |
  135. | [dt-investigate-error](prompts/dt-investigate-error.prompt.md) | Investigate recent errors using Davis Problems as the entry point (problems → logs → traces). |
  136. | [dt-performance-regression](prompts/dt-performance-regression.prompt.md) | Analyze whether a recent deployment caused a performance regression. |
  137. | [dt-troubleshoot-problem](prompts/dt-troubleshoot-problem.prompt.md) | Troubleshoot an existing Dynatrace problem with structured log and trace investigation. |
  138. ## How Skills Work
  139. Skills follow the [Agent Skills specification](https://agentskills.io/specification) and use progressive disclosure:
  140. 1. **Catalog** - Agents load only `name` + `description` (~100 tokens per skill) to know what's available.
  141. 2. **Instructions** - When relevant, the full `SKILL.md` is loaded (<5000 tokens).
  142. 3. **Resources** - Detailed reference files in `references/` are loaded on demand.
  143. Install all skills without penalty. Agents only load what they need.
  144. ## Contributing
  145. Skill content (`skills/`) is maintained internally at Dynatrace and published here periodically. **PRs that modify skill files will not be accepted** — please [open an issue](../../issues/new) instead to suggest changes. See [CONTRIBUTING.md](CONTRIBUTING.md) for details on what can be contributed directly.
  146. ## License
  147. Apache-2.0

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.