Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →datadog/pup
Datadog API CLI with 49 command groups, 300+ subcommands. Skills and domain agents for monitoring, logs, APM, security, and infrastructure.
Passed 21 of 23 test cases with the skill, and 4 of 23 without it.
and 17 more in the full report
19 fixed2 passed either way0 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am installing the Rust-based Datadog Pup CLI binary on macOS using Homebrew. What Homebrew tap and formula installation commands should I execute?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies running brew tap datadog-labs/pack | Missed | Passed |
| Specifies running brew install pup | Passed | Passed |
The instructions your model reads when the skill loads.
Rust-based CLI for Datadog APIs. 49 command groups, 300+ subcommands across 53 command modules.
# Install all skills and agents for the auto-detected AI assistant
pup skills install
# Or install for a specific platform (claude, cursor, codex, opencode, pi)
pup skills install claude
pup skills install codex
pup skills install cursor
# Install for every supported platform at once
pup skills install all
# Install a single skill by name
pup skills install claude --name dd-pup
# Default scope is user-global; pass --project to install into the repo
pup skills install claude --project
# List all available skills
pup skills list
| Skill | Description |
|---|---|
| dd-pup | Primary CLI - all pup commands, auth, site config |
| dd-monitors | Create, manage, mute monitors and alerts |
| dd-logs | Search logs, pipelines, archives |
| dd-apm | Traces, services, performance analysis |
| dd-docs | Search Datadog documentation via llms.txt |
| dd-code-generation | CLI vs code-gen decision, multi-language examples |
| dd-file-issue | Issue routing to correct repo, duplicate search |
| dd-idp | Explore software, work and delivery, infrastructure, operations, and security through entity kinds and relationships |
test cases passed, vs 4 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.