agent-skills
Datadog monitoring, tracing, auditing, and CI/CD troubleshooting
All Skills in This Repository (24)
Pure Emerald Level Indicatorsagent-skills
Define frontmatter-driven Datadog skill catalogs for AI agents.
dd-browser-sdk
Migrate Datadog Browser SDK integrations from v6 to v7.
troubleshoot-ssi
Diagnose and fix SSI issues on Linux hosts with pup and SSH.
enable-ssi
Configure Unified Service Tags on Linux hosts and verify Single Step Instrumentation.
onboarding-summary
Generate a live SSI onboarding confirmation report for Linux hosts.
agent-install
Install the Datadog Agent on Linux hosts via SSH with SSI.
verify-ssi
Verify Single Step Instrumentation injection and trace reception on Linux hosts.
eval-trace-rca
Diagnose root causes of LLM trace failures using eval results and runtime errors.
eval-bootstrap
Generate SDK-based Python evaluators or JSON specs from production traces.
eval-session-classify
Classify Datadog assistant sessions into satisfaction verdicts using session_id and LLM Observability traces.
experiment-analyzer
Analyze LLM experiment results to produce summaries, comparisons, and actionable insights.
upgrade-browser-sdk-v7
Automate Datadog Browser SDK migration from v6 to v7 across projects.
Frequently Asked Questions
FAQPage SchemaHow to install Datadog agent-skills?βΌ
Run `npx skills add datadog-labs/agent-skills --all -g -y` in your terminal to install all skills globally. Most skills also need the pup CLI, installed via `brew install datadog-labs/pack/pup` followed by `pup auth login`.
How to set up Datadog APM on Kubernetes?βΌ
The dd-apm skills walk through installing the Datadog Operator, enabling Single Step Instrumentation, and verifying traces end to end. Your agent handles the kubectl and helm commands and confirms traces are arriving.
Can it investigate a Datadog cost spike?βΌ
Yes. The dd-audit cost-spike skill correlates usage metering data with audit trail changes to find who changed what before the spike. It also covers security investigations, key compromise, and SOC 2 or PCI compliance reports.
How to fix a failing CI pipeline with Datadog?βΌ
The unblock-pr skill classifies each CI failure as flaky, infra, or regression and proposes a targeted fix. The triage-flaky-test skill then digs into flaky tests and can quarantine them with your approval.
Does it work with Claude Code and Cursor?βΌ
Yes. All skills follow the standard SKILL.md format and run in Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, and OpenCode.
Related Repositories in Software Engineering
View All in Software Engineeringβopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core