Index of every page on this site: llms.txt
All skills
datadog-labs avatar

/dd-docs

@618fae3 official
Run it yourself

Look up Datadog documentation, limits, and feature availability. Prefer search_datadog_documentation when that MCP tool is available, then one Markdown page from docs.datadoghq.com/llms.txt. For API reference, use pup docs api.

Use this Skill: https://skilld.dev/gh/datadog-labs/agent-skills/dd-docs

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈59 tokens for metadata: the name and description. ≈377 when used: this file.

Description uses 3.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈237 characters, or 3.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Datadog Docs

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

  1. search_datadog_documentation is available → Search.
  2. The question is an API endpoint or request schema, and search did not answer it → API.
  3. 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.

Page

https://docs.datadoghq.com/llms.txt is the section index. Open the one section index it links to, then fetch one page by appending .md:

https://docs.datadoghq.com/monitors/llms.txt
https://docs.datadoghq.com/monitors.md

Documentation is served from docs.datadoghq.com. Site-specific values, such as API endpoints, are selected on that page.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts15d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    This skill is a legitimate tool for looking up Datadog documentation using official MCP tools, a specialized CLI (pup), and the official documentation website. All external resources and commands are directed at Datadog's official infrastructure.

  • Socket15d

    No alerts

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer8mo

    1/1 file flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 618fae3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 days ago.

Activeupdated 2 weeks ago
Other metadata
metadata
{
  "version": "1.1.0",
  "author": "datadog-labs",
  "repository": "https://github.com/datadog-labs/agent-skills",
  "tags": "datadog,docs,llms.txt,dd-docs",
  "alwaysApply": "false"
}
  • Documentation
  • datadog
  • llms.txt
  • apm
  • monitoring
  • logs
  • metrics
  • api-reference

README badge

README badge for datadog-labs/agent-skills/dd-docs

Locates and fetches Datadog documentation from docs.datadoghq.com/llms.txt, an LLM-optimized index that maps Datadog products and features to their documentation pages. Use this skill to resolve questions about Datadog's APM, logging, monitoring, dashboards, synthetics, and API capabilities during development or architecture work.

Generated from the current SKILL.md.

What is llms.txt and how does it differ from the regular Datadog docs?
llms.txt is an LLM-optimized documentation index at docs.datadoghq.com/llms.txt that provides an overview of all Datadog products, a searchable list of documentation pages with URLs and descriptions, and direct links to Markdown sources. It's designed for efficient parsing by AI agents rather than human browsing.
Can I fetch raw Markdown versions of Datadog documentation pages?
Yes. Most Datadog Docs URLs support a .md suffix to return raw Markdown content, e.g. docs.datadoghq.com/monitors.md instead of docs.datadoghq.com/monitors/.
What should I do if docs.datadoghq.com is unreachable?
Check network connectivity first. For region-specific documentation, use the appropriate Datadog site domain (e.g. datadoghq.eu).
Does this skill cover all Datadog products and features?
The skill provides lookup access to documentation for major Datadog products including APM, Logs, Metrics, Monitors, Dashboards, Security, Synthetics, RUM, Incidents, and the API Reference. Refer to the official llms.txt index for the complete list of available documentation.

Generated from the current SKILL.md. These answers refresh after source changes.