Official agent skill

GPU Live Metric Validation

Validate live GPU metrics on clusters running the Agent version under test and investigate missing metrics or tag failures.

OfficialApache-2.0Auto-check passedDevOps & Cloud

Install GPU Live Metric Validation

skills CLI

$ npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install DataDog/datadog-agent gpu-live-metric-validation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/DataDog/datadog-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/gpu-live-metric-validation .claude/skills/gpu-live-metric-validation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "gpu-live-metric-validation" agent skill from https://github.com/DataDog/datadog-agent/tree/main/.agents/skills/gpu-live-metric-validation into .claude/skills/gpu-live-metric-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpu-live-metric-validation", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/DataDog/datadog-agent/tree/main/.agents/skills/gpu-live-metric-validation

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install DataDog/datadog-agent gpu-live-metric-validation --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DataDog/datadog-agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/gpu-live-metric-validation .agents/skills/gpu-live-metric-validation && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "gpu-live-metric-validation" agent skill from https://github.com/DataDog/datadog-agent/tree/main/.agents/skills/gpu-live-metric-validation into .agents/skills/gpu-live-metric-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpu-live-metric-validation", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install DataDog/datadog-agent gpu-live-metric-validation --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DataDog/datadog-agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/gpu-live-metric-validation .cursor/skills/gpu-live-metric-validation && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "gpu-live-metric-validation" agent skill from https://github.com/DataDog/datadog-agent/tree/main/.agents/skills/gpu-live-metric-validation into .cursor/skills/gpu-live-metric-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpu-live-metric-validation", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/DataDog/datadog-agent.git --path .agents/skills/gpu-live-metric-validation

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install DataDog/datadog-agent gpu-live-metric-validation --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DataDog/datadog-agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/gpu-live-metric-validation .gemini/skills/gpu-live-metric-validation && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "gpu-live-metric-validation" agent skill from https://github.com/DataDog/datadog-agent/tree/main/.agents/skills/gpu-live-metric-validation into .gemini/skills/gpu-live-metric-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpu-live-metric-validation", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install DataDog/datadog-agent gpu-live-metric-validation

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/DataDog/datadog-agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/gpu-live-metric-validation .github/skills/gpu-live-metric-validation && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "gpu-live-metric-validation" agent skill from https://github.com/DataDog/datadog-agent/tree/main/.agents/skills/gpu-live-metric-validation into .github/skills/gpu-live-metric-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpu-live-metric-validation", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install DataDog/datadog-agent gpu-live-metric-validation --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/DataDog/datadog-agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/gpu-live-metric-validation .opencode/skills/gpu-live-metric-validation && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "gpu-live-metric-validation" agent skill from https://github.com/DataDog/datadog-agent/tree/main/.agents/skills/gpu-live-metric-validation into .opencode/skills/gpu-live-metric-validation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpu-live-metric-validation", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: gpu-live-metric-validation
GitHub stars: 3.8k
Token cost: ~1.1k tokens
SKILL.md length: 468 words
Files: 1
Skills in repo: 35
Repo updated: Oct 9, 2026
First seen: Oct 8, 2026
Licence: Apache-2.0

At a glance

Validate live GPU metrics on clusters running the Agent version under test and investigate missing metrics or tag failures.

Works in 3 steps: Ask the user which supported orgs to… → Run the validator for each selected org → Record the selected org, Agent version…
Asked to validate GPU metrics on live clusters
SKILL.md covers Purpose, Required input, Validation workflow and Investigating findings, plus 2 more sections
Needs DD_API_KEY and DD_APP_KEY

What it does

GPU Live Metric Validation is an agent skill from DataDog/datadog-agent, published by the product's own GitHub organization. Validate live GPU metrics on clusters running the Agent version under test and investigate missing metrics or tag failures. Use when asked to validate GPU metrics on live clusters, check a GPU Agent release, or run dda inv gpu.validate-metrics.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud. It works with Datadog. The repository describes itself as: Main repository for Datadog Agent. The licence is Apache-2.0.

When your agent uses it

Asked to validate GPU metrics on live clusters
Check a GPU Agent release
Run dda inv gpu.validate-metrics

Example prompts

“/gpu-live-metric-validation”

Requirements

A credential in DD_API_KEY
A credential in DD_APP_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

Ask the user which supported orgs to validate.
Run the validator for each selected org
Record the selected org, Agent version wildcard, lookback window, and

What it can do on your machine

Read from SKILL.md and the folder at commit a706f1a. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- DD_API_KEY
- DD_APP_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

GPU Live Metric Validation loads about 1.1k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 468 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~68
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from DataDog/datadog-agent at commit a706f1a, republished under its Apache-2.0 licence (© DataDog). 468 words, ~1,077 tokens.

Download SKILL.mdSave it as .claude/skills/gpu-live-metric-validation/SKILL.md (or your agent's skills folder).

name: gpu-live-metric-validation
description: Validate live GPU metrics on clusters running the Agent version under test and investigate missing metrics or tag failures. Use when asked to validate GPU metrics on live clusters, check a GPU Agent release, or run dda inv gpu.validate-metrics.

<!-- @format -->

GPU Live Metric Validation

Purpose

Run GPU metric validation against Kubernetes clusters that are exclusively running the Agent version under test during the selected validation window, then investigate any findings.

Required input

Ask the user which Datadog orgs to validate before running any queries. The supported values match tasks/gpu.py:

prod (app.datadoghq.com)
staging (ddstaging.datadoghq.com)

Validation workflow

Ask the user which supported orgs to validate.
Run the validator for each selected org:
bash
```
dda inv gpu.validate-metrics \
  --org <prod-or-staging> \
  --lookback-seconds <window-seconds>
```
By default, the task derives the Agent image-tag wildcard from the current release branch and its latest release-candidate tag. It passes that wildcard to the validator, which queries datadog.agent.running grouped by kube_cluster_name,image_tag, selects clusters whose nonempty image tags all match the wildcard, and ANDs that cluster selection with the GPU configuration filters.

Use --agent-version <wildcard> to override the derived version; it is required outside release branches (N.N.x), where derivation fails. Use --metric-filter <filter> only for an additional scope; it is ANDed with the version-derived cluster filter.
Record the selected org, Agent version wildcard, lookback window, and validation output before interpreting any findings.

Investigating findings

For follow-up Datadog queries, use dd-auth to select the target. pup consumes the injected DD_API_KEY, DD_APP_KEY, and DD_SITE; do not combine this workflow with pup --org.

Start from a failing GPU metric and group it by the smallest useful set of dimensions, normally gpu_uuid, host, and kube_cluster_name. Add the failed tag as a group-by dimension when investigating a tag failure.

bash

dd-auth --domain <target-domain> -- \
  pup --no-agent metrics query \
  --query='count:gpu.<metric>{<validation-filter>} by {gpu_uuid,host,kube_cluster_name,<failed-tag>}' \
  --from=<validation-window> --to=now

Identify patterns before drawing conclusions: whether failures are limited to a GPU architecture, device mode, GPU model, host, cluster, workload, or Agent image tag. Confirm the affected cluster's Agent image tag with:
bash
```
dd-auth --domain <target-domain> -- \
  pup --no-agent metrics query \
  --query='sum:datadog.agent.running{<cluster-filter>} by {kube_cluster_name,image_tag}' \
  --from=<validation-window> --to=now
```
Preserve the exact queries and affected GPU/host/cluster identifiers in the summary.

Show full SKILL.md (185 more words)Show less

Candidate investigations by failure type

Missing metric: compare the affected GPU configuration with the metric's expected support and query gpu.device.total for the same scope to confirm that devices were present.
Missing required tag: group the failing metric by the required tag and affected GPU/host/cluster. Compare a related GPU metric to determine whether the absence is metric-specific.
Invalid tag value: group by the invalid tag and affected GPU/host/cluster. Check whether a series has multiple values for the same tag key before treating a comma-separated value as a single emitted tag value.
Unknown or extra tag: query a workload/container metric such as container.cpu.usage for the same pod and container. Compare its tags with the GPU metric to determine whether the tag originates from the workload.
If a workload tag points to a Kubernetes resource, inspect the corresponding Kubernetes object and its labels and annotations before assigning a source.

Constraints

Use an explicit, bounded validation window.
Use dd-auth to select the target for pup queries.
Do not validate clusters that reported a different nonempty Agent image tag in the validation window.
Do not use pup --org with dd-auth.

Files

Just SKILL.md in .agents/skills/gpu-live-metric-validation of DataDog/datadog-agent.

Open the folder on GitHubat commit a706f1a

Compare with similar skills

GPU Live Metric Validation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

GPU Live Metric Validation compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
GPU Live Metric Validation this skillDataDog/datadog-agent	3.8k	—	~1.1k	Automated safety check: Pass	Apache-2.0	today
Apm IntegrationsDataDog/dd-trace-js	837	—	~3k	Automated safety check: Pass	Custom licence	today
Dd IdpDataDog/pup	1k	—	~2k	Automated safety check: Pass	Apache-2.0	today
Datadog Data Source GeneratorDataDog/terraform-provider-datadog	468	—	~2.7k	Automated safety check: Pass	MPL-2.0	today
Apm IntegrationsDataDog/dd-trace-java	736	—	~3.7k	Automated safety check: Notes	Apache-2.0	today
Azure FunctionsDataDog/dd-trace-dotnet	573	—	~4.7k	Automated safety check: Pass	Apache-2.0	today

Similar skills

Apm Integrations
DataDog/dd-trace-js
Official
A skill your agent uses when adding, debugging, fixing, or modifying instrumentation and plugins for third-party libraries in dd-trace-js.
837 GitHub stars~3k tokensUpdated today
DevOps & CloudAuto-check passed
Dd Idp
DataDog/pup
Official
Find, filter, count, and connect software, teams, engineering work and delivery, infrastructure, and operational or security records through Pup's read-only Datadog entity graph.
1k GitHub stars~2k tokensUpdated today
DevOps & CloudAuto-check passed
Datadog Data Source Generator
DataDog/terraform-provider-datadog
Official
Generates a Datadog Terraform provider data source from an OpenAPI operation with tfgen and opens a review-ready GitHub PR with a risk scan and testing guide.
468 GitHub stars~2.7k tokensUpdated today
DevOps & CloudAuto-check passed
Apm Integrations
DataDog/dd-trace-java
Official
Write a new library instrumentation end-to-end. An agent skill from DataDog/dd-trace-java.
736 GitHub stars~3.7k tokensUpdated today
DevOps & CloudAuto-check: notes
Azure Functions
DataDog/dd-trace-dotnet
Official
Dev/test workflow for tracer engineers working on the Datadog .NET tracer — build a local Datadog.AzureFunctions NuGet package, deploy it to a test Azure Function App, trigger it, and analyze…
573 GitHub stars~4.7k tokensUpdated today
DevOps & CloudAuto-check passed
Tool Connector
ZhixiangLuo/10xProductivity
Connect any tool you use at work to your agent — including internal company tools, custom-built systems, deployment portals, incident trackers, internal knowledge bases, HR systems, and commercial…
478 GitHub stars~925 tokensUpdated 2 mo ago
DevOps & CloudAuto-check passed

More from DataDog/datadog-agent

All 35 skills in this repo

Triage CI Failure
DataDog/datadog-agent
Official
Classify a failed CI as either caused by an active incident, flakiness, or a true code regression.
3.8k GitHub stars~2.3k tokensUpdated today
Auto-check passed
Elicit
DataDog/datadog-agent
Official
Run a structured discovery session to build an Allium specification through conversation.
3.8k GitHub starsUsed in 1 repo~3.7k tokens
Auto-check passed
Follow PR
DataDog/datadog-agent
Official
Monitor the current PR's GitLab pipeline to completion, then report success, auto-fix, or investigate a failure.
3.8k GitHub stars~3.2k tokensUpdated today
Auto-check passed
Create Epic Recap
DataDog/datadog-agent
Official
A skill your agent uses when an engineer or manager asks to recap, summarize, or post an update on a Jira Epic — a progress update for an in-progress Epic (how far along it is, what's shipped so…
3.8k GitHub stars~5k tokensUpdated today
Auto-check: notes
Explain Lading Config
DataDog/datadog-agent
Official
Explains a lading.yaml config file from the regression test suite, using the lading Rust source as ground truth for field meanings and defaults.
3.8k GitHub stars~1.2k tokensUpdated today
Auto-check passed
Distill
DataDog/datadog-agent
Official
Extract an Allium specification from an existing codebase. An agent skill from DataDog/datadog-agent.
3.8k GitHub starsUsed in 1 repo~7k tokens
Auto-check passed

Works with

Datadog

Questions about GPU Live Metric Validation

What does GPU Live Metric Validation do?

Validate live GPU metrics on clusters running the Agent version under test and investigate missing metrics or tag failures. GPU Live Metric Validation is an agent skill from DataDog/datadog-agent, published by the product's own GitHub organization. Validate live GPU metrics on clusters running the Agent version under test and investigate missing metrics or tag failures.

When should I use GPU Live Metric Validation?

GPU Live Metric Validation fits situations like: asked to validate GPU metrics on live clusters; check a GPU Agent release; run dda inv gpu.validate-metrics.

How do I install GPU Live Metric Validation in Claude Code?

Run `npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a claude-code`. Or copy the skill folder (.agents/skills/gpu-live-metric-validation in DataDog/datadog-agent) into .claude/skills/gpu-live-metric-validation in your project. Claude Code loads it when a task matches its description.

How do I install GPU Live Metric Validation in Codex?

Run `npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a codex`. Or copy the skill folder (.agents/skills/gpu-live-metric-validation in DataDog/datadog-agent) into .agents/skills/gpu-live-metric-validation in your project. Codex loads it when a task matches its description.

Can I use GPU Live Metric Validation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DataDog/datadog-agent --skill gpu-live-metric-validation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gpu-live-metric-validation, .gemini/skills/gpu-live-metric-validation, .github/skills/gpu-live-metric-validation and .opencode/skills/gpu-live-metric-validation in your project.

What does GPU Live Metric Validation need to run?

Going by SKILL.md and its folder, GPU Live Metric Validation needs credentials named DD_API_KEY and DD_APP_KEY. Our summary lists: A credential in DD_API_KEY; A credential in DD_APP_KEY.

Does GPU Live Metric Validation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is GPU Live Metric Validation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does GPU Live Metric Validation use?

GPU Live Metric Validation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does GPU Live Metric Validation use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to GPU Live Metric Validation?

Skills that share tags, products or a category with GPU Live Metric Validation: Apm Integrations (DataDog/dd-trace-js, 837 stars), Dd Idp (DataDog/pup, 1k stars), Datadog Data Source Generator (DataDog/terraform-provider-datadog, 468 stars) and Apm Integrations (DataDog/dd-trace-java, 736 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains GPU Live Metric Validation?

DataDog (a GitHub organization, an official publisher) maintains it in DataDog/datadog-agent, which has 3,759 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 9, 2026.

Source: DataDog/datadog-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install GPU Live Metric Validation

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

GPU Live Metric Validation

Purpose

Required input

Validation workflow

Investigating findings

Candidate investigations by failure type

Constraints

Files

Compare with similar skills

Similar skills

More from DataDog/datadog-agent

Related

Questions about GPU Live Metric Validation