Dd Docs

Pulls Datadog documentation through their llms.txt endpoint, which gives you an LLM-optimized index of all their docs with direct links to markdown sources. Useful when you're configuring monitors, setting up APM, or need to check feature limits without leaving your editor. The skill basically wraps curl commands to fetch either the main index or specific doc pages by appending .md to any Datadog docs URL. It's a straightforward docs lookup tool, nothing fancy, but it saves you from context switching to a browser when you need to reference how Datadog's API or monitoring features actually work.

skills.sh installs: 1.9K
GitHub stars: 184
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add datadog-labs/agent-skills --skill dd-docs --agent claude-code

Installs into .claude/skills of the current project.

Files

Datadog Docs

Use the smallest source that answers the question, then stop. Cite the page URL you used.

search_datadog_documentation is available → Search.
The question is an API endpoint or request schema, and search did not answer it → API.
Otherwise → Page.

Search

search_datadog_documentation (MCP toolset documentation, no extra permission) returns at most 10 source passages with links. It does not write an answer. It supports English, French, Japanese, Korean, and Spanish.

Call read_datadog_documentation with one source URL or document id only when a passage is not enough. It returns long pages in parts; stop at the part that answers.

If the tool is not in your tool list, skip this section. Enabling the toolset is a separate setup task.

API

Pup reads the live API reference and needs no auth. Commands, smallest first:

pup docs api <topic> --operations
pup docs api <topic>

The operations list is the small result. Fetch pup docs api <topic> <operation> only when you need that operation's request schema: the page includes every sample. Skip pup docs api with no topic.