Agent Native

datadog

This skill queries Datadog observability data including logs, metrics, monitors, dashboards, hosts, and APM spans via the Datadog API.

by LettaOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (letta-ai)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
License
MIT (permissive)
Pin
6785511pinned Oct 9, 2026
Context cost
about 730 tokenswhen the skill loads
GitHub stars
148on letta-ai/skills
Scripts
3 scripts

What it does

“Query Datadog observability data (logs, metrics, monitors, dashboards, hosts) via direct API. Use when investigating production issues, checking monitors, searching logs, or accessing Datadog data.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill queries Datadog observability data including logs, metrics, monitors, dashboards, hosts, and APM spans via the Datadog API. The agent can search logs by query, retrieve metric timeseries, list or filter monitors, and inspect incident and service data to investigate production issues and system health.

When to use it

  • Investigating production incidents and error patterns
  • Querying metrics and performance data over time ranges
  • Filtering monitors by status to find active alerts
  • Searching logs with Datadog query syntax for troubleshooting

When not to

  • Without valid Datadog API and application keys configured
  • When read-only access to Datadog is not permitted
  • For modifying monitors, dashboards, or creating incidents

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add letta-ai/skills --skill datadog

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install letta-ai/skills datadog@6785511e7d3913d9ec598435a77ae637cd45fc89

Installs the commit we checked (6785511).

Copy by hand

Download the folder at 6785511 and put it in .claude/skills/datadog for Claude Code and in .agents/skills/datadog for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 6785511

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "datadog" by Letta.

Source, pinned to commit 6785511e7d3913d9ec598435a77ae637cd45fc89:
https://github.com/letta-ai/skills/tree/6785511e7d3913d9ec598435a77ae637cd45fc89/tools/datadog

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/datadog/ for Claude Code and .agents/skills/datadog/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/letta/datadog

SKILL.md at the pin

---
name: datadog
description: Query Datadog observability data (logs, metrics, monitors, dashboards, hosts) via direct API. Use when investigating production issues, checking monitors, searching logs, or accessing Datadog data.
---

# Datadog CLI

Direct API access to Datadog observability data — logs, metrics, monitors, dashboards, hosts, and APM spans.

## Prerequisites

Set these environment variables:

```bash
export DD_API_KEY="your-32-char-hex-api-key"
export DD_APP_KEY="your-application-key"
export DD_SITE="us5.datadoghq.com"  # or datadoghq.com, datadoghq.eu, etc.
```

**Get keys from Datadog:**
- API Key: Organization Settings → API Keys
- App Key: Organization Settings → Application Keys

**Required scopes** (for read-only access):
- `dashboards_read`, `monitors_read`, `metrics_read`, `logs_read_data`, `incidents_read`, `hosts_read`, `apm_read`

## Quick Start

```bash
# Test credentials
npx tsx <skill-path>/scripts/datadog.ts validate

# Search logs
npx tsx <skill-path>/scripts/datadog.ts search-logs "status:error" --from -1h

# Query metrics
npx tsx <skill-path>/scripts/datadog.ts query-metrics "avg:system.cpu.user{*}" --from -4h

# List monitors
npx tsx <skill-path>/scripts/datadog.ts list-monitors
```

## Commands

### Logs

```bash
# Search logs (default: last hour, 50 results)
npx tsx <skill-path>/scripts/datadog.ts search-logs "service:api status:error"
npx tsx <skill-path>/scripts/datadog.ts search-logs "env:prod" --from -30m --limit 100
```

### Metrics

```bash
# Query metric timeseries
npx tsx <skill-path>/scripts/datadog.ts query-metrics "avg:system.cpu.user{*}" --from -4h
npx tsx <skill-path>/scripts/datadog.ts query-metrics "sum:requests.count{service:api}.as_count()" --from -1d
```

### Monitors

```bash
# List all monitors
npx tsx <skill-path>/scripts/datadog.ts list-monitors

# Filter monitors
npx tsx <skill-path>/scripts/datadog.ts list-monitors --query "status:alert"

# Get specific monitor
npx tsx <skill-path>/scripts/datadog.ts get-monitor 12345
```

### Dashboards

```bash
npx tsx <skill-path>/scripts/datadog.ts list-dashboards
```

### Hosts

```bash
npx tsx <skill-path>/scripts/datadog.ts list-hosts
npx tsx <skill-path>/scripts/datadog.ts list-hosts --filter "env:production"
```

### Incidents

```bash
npx tsx <skill-path>/scripts/datadog.ts list-incidents
```

### APM (Spans & Services)

```bash
# Search spans
npx tsx <skill-path>/scripts/datadog.ts search-spans "service:api @http.status_code:500" --from -1h

# List services
npx tsx <skill-path>/scripts/datadog.ts list-services
```

## Time Formats

The `--from` and `--to` flags accept:
- Relative: `-1h`, `-30m`, `-1d`, `-4h`
- ISO 8601: `2026-03-20T00:00:00Z`

## Datadog Sites

| Region | DD_SITE value |
|--------|---------------|
| US1 | `datadoghq.com` |
| US3 | `us3.datadoghq.com` |
| US5 | `us5.datadoghq.com` |
| EU | `datadoghq.eu` |
| AP1 | `ap1.datadoghq.com` |

## Troubleshooting

**403 Forbidden:**
- Check DD_SITE matches your Datadog region
- Verify app key has required scopes
- Confirm API key is active

**Credentials not found:**
- Ensure DD_API_KEY and DD_APP_KEY are exported
- Check for typos in env var names

From letta-ai/skills at 6785511, shown as plain text under its license: MIT (permissive). The license text is in tools/datadog/LICENSE.

View SKILL.md on GitHub at 6785511

Files

7 files, 67 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 6785511
All 50 skills from Letta

More from Letta

  • acquiring-skills

    Enables the agent to discover and install skills from multiple registries including Hermes Skills Hub, ClawHub, GitHub, and community repositories.

    Agents not labelled yet · about 3.1K tokens · pinned 6 days ago

  • browser-use

    Control a real browser using Chrome DevTools Protocol over WebSocket to navigate pages, interact with UI, fill forms, scrape sites, and capture screenshots or…

    Claude Code, Codex, Cursor +4 · about 3.2K tokens · pinned 6 days ago

  • Context Doctor

    Context Doctor investigates and repairs an agent's context including memory, system prompt, and skills by analyzing observed behavior as evidence.

    Claude Code, Codex, Cursor +3 · about 1K tokens · pinned 6 days ago

  • creating-mods

    This skill creates and edits mod files that extend local Letta instances with tools, slash commands, event handlers, custom model providers, permissions, and…

    Claude Code, Codex, Cursor +4 · about 2.4K tokens · pinned 6 days ago

  • creating-skills

    This skill guides developers in creating modular packages that extend Letta Code agent capabilities with specialized knowledge, workflows, tool integrations…

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 4.5K tokens · pinned 6 days ago

  • curating-memory-palace

    This skill lets the agent maintain a Memory Palace, a structured dashboard view that shows the user what the agent is working on, what it could do next, and…

    Agents not labelled yet · about 3.1K tokens · pinned 6 days ago

All Observability skills
  • dd-code-generation

    This skill enables agents to interact with Datadog through the pup CLI tool for immediate queries and operations, or generate code for integrating Datadog…

    by DatadogOfficial publisher

    Claude Code, Codex, Cursor +3 · about 4.3K tokens · pinned 6 days ago

  • dd-logs

    This skill enables agents to search, process, and archive Datadog logs using the pup command-line tool.

    by DatadogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 1.2K tokens · pinned 6 days ago

  • agent-observability-online-experiment

    This skill guides users through setting up online A/B tests for LLM applications using Datadog's Agent Observability and feature flags.

    by DatadogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 5.9K tokens · pinned 6 days ago

  • agent-observability-replay-trace

    Replay a single production trace against local code changes to test fixes iteratively.

    by DatadogOfficial publisher

    Contains scripts

    Claude Code · about 3.4K tokens · pinned 6 days ago

  • agent-observability-session-classify

    Classifies whether a user's intent was satisfied in a Datadog Agent Observability trace or session by analyzing conversation content, tool outcomes, and…

    by DatadogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 15.7K tokens · pinned 6 days ago

  • agent-skills

    This skill package provides Datadog observability tools for AI agents, including monitoring, logging, tracing, APM, and cloud integrations through the pup CLI.

    by DatadogOfficial publisher

    Claude Code, Codex, Cursor +4 · about 910 tokens · pinned 6 days ago

Open roles at Letta

4 open roles on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use