SkillFoxx

Type a name, a task or a service

Match with Foxx AI

Datadog Agent Skills

Official Datadog skills: monitors, logs, APM, cloud integrations, RUM and LLM observability from inside the agent

  • 183 ★ on the repository
  • Last commit
  • MIT
SkillEditors’ pick

Broad access

Why this level

  • The skills create and mute monitors, set up AWS, Azure and GCP integrations through Terraform and handle Datadog API keys.
  • Searching logs and the audit trail hands the agent the contents of production systems, including secrets and personal data that ended up in logs.
All reasons and checks

datadog-labs/agent-skillsAuthor:Datadog

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/datadog-agent-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Broad accessThe tool can change data, run commands or handle secrets.

  • The skills create and mute monitors, set up AWS, Azure and GCP integrations through Terraform and handle Datadog API keys.
  • Searching logs and the audit trail hands the agent the contents of production systems, including secrets and personal data that ended up in logs.

This is third-party code. Review the repository files before installing.

What it does

Datadog Agent Skills is a set of skills from Datadog itself for working with its observability platform. The base skill `dd-pup` teaches the agent to use the pup console client: commands, login and PATH setup. The others handle monitors (create, mute), logs, traces and APM services, while `dd-docs` searches the Datadog documentation. Separate groups cover installation and integrations. The Datadog Agent installs on Docker, Kubernetes, Linux, macOS and Windows. AWS, Azure, GCP and Oracle Cloud connect through Terraform. The profiler is set up for Java, Python, Go, Ruby, Node.js, .NET and PHP, and Browser RUM goes into React, Next.js, Angular, Vue, Nuxt and Svelte. The `agent-observability` group of ten skills analyzes LLM experiments, finds failure causes in traces and builds evaluators. The `dd-audit` skills investigate the audit trail: who changed what, a suspected key leak, a cost spike.

Who it is for. Teams that keep services under Datadog monitoring and run on-call, agent setup and incident analysis from Claude Code, Codex or Cursor.

Good fit when

  • A service fails in production and the agent searches logs and traces for failing requests without opening the web UI.
  • A new Kubernetes cluster gets the Datadog Agent, then Single-Step Instrumentation is enabled and verified.
  • A monitor is noisy at night and has to be muted for a while or have its condition adjusted.
  • A React or Next.js frontend gets Browser RUM, with the agent adding the instrumentation.
  • An LLM app answers badly, and you need to find the failure cause in traces and build an evaluator for repeat checks.

Not a fit when

  • Monitoring runs on another platform: the skills work only with Datadog products.
  • You need the Datadog MCP server: this is skills plus the pup client, and the MCP server ships separately.
  • You need a single capability, such as log search: install it by name with `--skill`, the whole set is not required for that.

Example request

Find payment service errors in Datadog logs for the last hour and show which traces match them.

Limitations

A Datadog account, a logged-in pup client (`pup auth login`) and an API key for your own Datadog region are required. The nested SSI skills in `dd-apm/k8s-ssi` and `dd-apm/linux-ssi` are not in the plugin manifest because their names clash, and `dd-apm` loads them by path. The CI/CD skills use MCP together with pup. To install the whole set through `npx skills add` you have to list every skill with a `--skill` flag. The Datadog Agent and cloud integrations are set up from the skills, but rights in AWS, Azure and GCP stay with your own accounts and roles.

How to disable. In Claude Code run `claude plugin uninstall agent-skills@datadog-labs`. Remove skills installed through `npx skills` with the same CLI or by hand from the agent's skills directory. The pup client comes off the way it went on: `brew uninstall pup` or `npm uninstall -g @datadog/pup`.

FAQ

How do I install all skills in Claude Code with one command?

The repository doubles as a plugin marketplace. Run `claude plugin marketplace add datadog-labs/agent-skills`, then `claude plugin install agent-skills@datadog-labs`. The same steps for GitHub Copilot CLI go through `copilot plugin`.

How do I install only the base skill?

Run `npx skills add datadog-labs/agent-skills --skill dd-pup --full-depth -y`. Other skills are added the same way with different names in `--skill`.

What do the `agent-observability` skills do?

They work with Agent Observability data in Datadog: compare offline experiments, find failure causes in production traces, generate evaluator code and classify whether the user reached their goal in a session. The `agent-observability-eval-pipeline` skill runs the evaluation pipeline and accepts `--stop-after` to stop early.

What if I get a 403 because of the wrong region?

The `dd-account-setup` skill validates API keys and fixes that error, and signs in or creates an account when needed.

Is the separate pup client required?

Yes: pup is the primary console client and the skills rely on its commands. It installs through Homebrew, npm (`npm install -g @datadog/pup`) or a source build with `cargo build --release`.

Discussion

No questions or reviews yet.

Skills

Official Dynatrace skills for agents: DQL, traces, logs, Kubernetes, cloud and security work inside Claude Code and Cursor.

SkillExtended access175
Official

Datadog's official managed MCP server: logs, metrics, traces and incidents right in your agent

MCP serverExtended access47

A large base of DevOps, security, infrastructure and compliance skills for AI agents

SkillMinimal access1.2K
Official

Forty-five skills, custom agents and CloudFormation templates for AWS DevOps Agent: incident analysis and operations reviews

SkillExtended access137
Editors’ pick

AWS's official set of MCP servers, skills and plugins so an agent can build, deploy and operate on AWS

PluginBroad access3.4K

Official Dynatrace CLI with kubectl-style syntax and a bundled skill: workflows, dashboards, DQL queries and SLOs

CLIExtended access201

README in short

The README opens with a table of skills, then covers installing the pup client through Homebrew, npm or a source build and three ways to install skills: one, the whole set, or as a plugin. A separate section walks through Agent Observability, from session classification to root cause and evaluator generation.

README badge

Original SKILL.md

---
name: agent-skills
description: Datadog skills for AI agents. Essential monitoring, logging, tracing and observability.
metadata:
  version: "1.0.3"
---

# Datadog Skills

Essential Datadog skills for AI agents.

## Core Skills

| Skill | Description |
|-------|-------------|
| **dd-account-setup** | Ensure an authenticated Datadog account with a valid API key on the right region; validates keys, fixes wrong-region 403s, signs in or creates an account |
| **dd-android-sdk** | Route Datadog Android SDK upgrades to the migration instructions for the project's current and target major versions. |
| **dd-apm** | Traces, services, performance analysis |
| **dd-apps**              | Build Datadog Apps — scaffold, run, upload, publish, CI/CD |
| **dd-aws-integration** | Connect an AWS account to Datadog with Terraform - cross-account IAM role, metrics and resource collection |
| **dd-azure-integration** | Connect Azure subscriptions or management groups to Datadog with Terraform - Entra app registration, Monitoring Reader |
| **dd-browser-sdk** | Browser SDK setup, RUM, Logs, Session Replay, version migration |
| **dd-docs** | Search Datadog documentation |
| **dd-gcp-integration** | Connect GCP projects or folders to Datadog with Terraform - keyless service-account impersonation |
| **dd-instrument-llmo** | Instrument Python & Node.js/Next.js AI backends with Datadog LLM Observability — SDK init, agent/workflow spans, RUM↔LLMO session linking |
| **dd-instrument-rum** | Instrument browser apps with Datadog Browser RUM — React, Next.js, Angular, Vue, Nuxt, Svelte, vanilla |
| **dd-llmo** | LLM Observability traces, experiments, evals |
| **dd-logs** | Search logs, pipelines, archives |
| **dd-monitors** | Create, manage, mute monitors and alerts |
| **dd-oci-integration** | Connect an Oracle Cloud tenancy to Datadog with Terraform - Datadog's official OCI module |
| **dd-product-recommender** | Recommend the right Datadog products for a codebase and/or goal (recommendation only) |
| **dd-profiler-setup** | Set up Datadog Continuous Profiler for a service — Java, Python, Go, Ruby, Node.js, .NET, PHP |
| **dd-pup** | Primary CLI - all pup commands, auth, PATH setup |
| **dd-software-delivery** | CI/CD workflow skills — unblock PR, triage flaky tests |

## Install

```bash
# Install core skills
npx skills add datadog-labs/agent-skills \
  --skill dd-pup \
  --skill dd-monitors \
  --skill dd-logs \
  --skill dd-apm \
  --skill dd-docs \
  --full-depth -y

# Install CI/CD workflow skills
npx skills add datadog-labs/agent-skills \
  --skill dd-software-delivery/unblock-pr \

Report a problem

Foxx AIDatadog Agent Skills
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.