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 (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead.

Install

npx skills add datadog-labs/agent-skills --skill agent-observability-eval-bootstrap

npx skills add datadog-labs/agent-skills --skill agent-observability-eval-bootstrap -a claude-code -g

npx skills add datadog-labs/agent-skills --skill agent-observability-eval-bootstrap -a codex -g

gemini skills install https://github.com/datadog-labs/agent-skills.git --path agent-observability/agent-observability-eval-bootstrap

gh skill install datadog-labs/agent-skills agent-observability-eval-bootstrap

git 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-eval-bootstrap ~/.claude/skills/agent-observability-eval-bootstrap   # Claude Code
cp -R /tmp/datadog-labs__agent-skills/agent-observability/agent-observability-eval-bootstrap ~/.agents/skills/agent-observability-eval-bootstrap   # Codex, Cursor, Gemini CLI, Copilot, OpenCode

Install

Related