dd-llmo-eval-bootstrap

What is dd-llmo-eval-bootstrap?

dd-llmo-eval-bootstrap is a Claude skill by datadog-labs that analyze production LLM traces and generate evaluators. It is listed under Other and has no public popularity data yet.

Is dd-llmo-eval-bootstrap safe to install?

We have not scanned dd-llmo-eval-bootstrap yet because its SKILL.md could not be fetched. Read the source before installing.

How do I install dd-llmo-eval-bootstrap?

1. Install with the skills CLI. Works for Claude Code and other agents that read skills.

   npx skills add https://github.com/datadog-labs/skills --skill dd-llmo-eval-bootstrap

2. Or copy it by hand. Claude Code loads any folder with a SKILL.md from ~/.claude/skills.

   git clone https://github.com/datadog-labs/skills
   cp -r skills/dd-llmo-eval-bootstrap ~/.claude/skills/dd-llmo-eval-bootstrap

3. Use it. Claude loads the skill when a task matches its description. You can also name it in your prompt.

   Use the dd-llmo-eval-bootstrap skill to …

Or ask Claude to set it up

Paste this into Claude Code and it installs dd-llmo-eval-bootstrap for you:

Install the "dd-llmo-eval-bootstrap" skill from https://github.com/datadog-labs/skills into ~/.claude/skills, then tell me in one line what it does.

More from datadog-labs/skills

This repository has 8 Claude skills on MCPMods.

• dd-apm: Query Datadog APM data directly from your editor (Not scanned)
• dd-docs: Look up Datadog documentation via the LLM-optimized docs index (Not scanned)
• dd-llmo-eval-trace-rca: Root-cause LLM app failures using eval traces (Not scanned)
• dd-llmo-experiment-analyzer: Analyze single or comparative LLM experiment results (Not scanned)
• dd-logs: Search, filter, and archive Datadog logs through pup CLI (Not scanned)
• dd-monitors: Manage Datadog monitors through the pup CLI (Not scanned)
• dd-pup: Rust-based CLI (pup) for talking to the Datadog API (Not scanned)