Bootstrap a reproducible LLM Observability experiment through the Python ddtrace SDK or the Node dd-trace SDK. Use for experiment, dataset, evaluator, benchmark, regression, or LLM-as-a-judge scaffolding. The legacy Python invocation remains supported.
Install
npx skills add datadog-labs/agent-skills --skill agent-observability-experiment-bootstrapnpx skills add datadog-labs/agent-skills --skill agent-observability-experiment-bootstrap -a claude-code -gnpx skills add datadog-labs/agent-skills --skill agent-observability-experiment-bootstrap -a codex -ggemini skills install https://github.com/datadog-labs/agent-skills.git --path agent-observability/agent-observability-experiment-bootstrapgh skill install datadog-labs/agent-skills agent-observability-experiment-bootstrapgit clone --depth 1 https://github.com/datadog-labs/agent-skills /tmp/datadog-labs__agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/datadog-labs__agent-skills/agent-observability/agent-observability-experiment-bootstrap ~/.claude/skills/agent-observability-experiment-bootstrap # Claude Code
cp -R /tmp/datadog-labs__agent-skills/agent-observability/agent-observability-experiment-bootstrap ~/.agents/skills/agent-observability-experiment-bootstrap # Codex, Cursor, Gemini CLI, Copilot, OpenCode