# datadog-labs/agent-skills architecture

> Architecture diagram of the GitHub repository datadog-labs/agent-skills, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-28). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/datadog-labs/agent-skills
- Repository: https://github.com/datadog-labs/agent-skills

## Overview

This repository is a collection of Datadog skills that guide AI agents through product workflows; it is not primarily a runtime service. The usual path is an engineer asks an agent for a task, the relevant skill supplies procedural guidance, and the agent uses Datadog tools or local project context to produce a result. README documents the main skill capabilities and an explicit Agent Observability pipeline. The graph uses those documented paths and relationships; source excerpts are limited, so implementation-level links between other skills are omitted.

Main entry points: [`agent-observability/agent-observability-eval-pipeline/SKILL.md`](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-eval-pipeline/SKILL.md) (Eval Pipeline), [`agent-observability/agent-observability-session-classify/SKILL.md`](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-session-classify/SKILL.md) (Session Classification), [`dd-pup/SKILL.md`](https://github.com/datadog-labs/agent-skills/blob/main/dd-pup/SKILL.md) (Pup CLI), [`dd-monitors/SKILL.md`](https://github.com/datadog-labs/agent-skills/blob/main/dd-monitors/SKILL.md) (Monitor Management)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_core["Core Datadog"]
  node_pup["Pup CLI<br/>[SKILL.md]"]
  node_monitors["Monitor Management<br/>[SKILL.md]"]
  node_logs["Log Search<br/>[SKILL.md]"]
  node_apm["APM Guidance<br/>[SKILL.md]"]
  node_docs["Documentation Search<br/>[SKILL.md]"]
end

subgraph group_observability["Agent Observability"]
  node_session["Session Classification<br/>[SKILL.md]"]
  node_rca["Trace RCA<br/>[SKILL.md]"]
  node_evalbootstrap["Evaluator Bootstrap<br/>[SKILL.md]"]
  node_pipeline["Eval Pipeline<br/>[SKILL.md]"]
  node_experiments["Experiment Analysis<br/>[SKILL.md]"]
  node_expbootstrap["Experiment Bootstrap<br/>[SKILL.md]"]
  node_annotations["Annotation Evaluator<br/>[SKILL.md]"]
  node_autoexperiment["Prompt Optimization<br/>[SKILL.md]"]
  node_replay["Trace Replay<br/>[SKILL.md]"]
end

subgraph group_application["Application Workflows"]
  node_rum["RUM Instrumentation<br/>[SKILL.md]"]
  node_browser["Browser SDK<br/>[SKILL.md]"]
  node_apps["Datadog Apps<br/>[SKILL.md]"]
  node_recommender["Product Recommender<br/>[SKILL.md]"]
end

subgraph group_security["Security and Delivery"]
  node_audit["Audit Investigations<br/>[SKILL.md]"]
  node_securityskill["Security Ownership<br/>[SKILL.md]"]
  node_delivery["Delivery Workflows<br/>[SKILL.md]"]
  node_cloud["Cloud Integrations<br/>[SKILL.md]"]
end

node_engineer(("Engineer"))
node_agent(("AI Agent"))
node_datadog{{"Datadog Platform"}}
node_rumsignals{{"RUM Signals"}}
node_localcode["Local Application"]

node_engineer -->|"requests task"| node_agent
node_agent -->|"uses guidance"| node_pup
node_agent -->|"uses guidance"| node_monitors
node_agent -->|"uses guidance"| node_logs
node_agent -->|"uses guidance"| node_apm
node_agent -->|"uses guidance"| node_docs
node_pup -->|"authenticates and operates"| node_datadog
node_monitors -->|"manages monitors"| node_datadog
node_logs -->|"searches logs"| node_datadog
node_apm -->|"investigates traces"| node_datadog
node_docs -->|"searches documentation"| node_datadog
node_agent -->|"uses guidance"| node_session
node_agent -->|"uses guidance"| node_rca
node_agent -->|"uses guidance"| node_pipeline
node_agent -->|"uses guidance"| node_experiments
node_agent -->|"uses guidance"| node_expbootstrap
node_agent -->|"uses guidance"| node_annotations
node_agent -->|"uses guidance"| node_autoexperiment
node_agent -->|"uses guidance"| node_replay
node_pipeline -->|"classifies sessions"| node_session
node_pipeline -->|"diagnoses failures"| node_rca
node_pipeline -->|"builds evaluators"| node_evalbootstrap
node_pipeline -->|"publishes and runs evaluations"| node_datadog
node_session -.->|"combines behavioral signals"| node_rumsignals
node_agent -->|"uses guidance"| node_rum
node_agent -->|"uses guidance"| node_browser
node_agent -->|"uses guidance"| node_apps
node_agent -->|"uses guidance"| node_recommender
node_rum -->|"sends RUM data"| node_datadog
node_browser -->|"guides SDK telemetry"| node_datadog
node_apps -->|"queries platform data"| node_datadog
node_agent -->|"uses guidance"| node_audit
node_agent -->|"uses guidance"| node_securityskill
node_agent -->|"uses guidance"| node_delivery
node_agent -->|"uses guidance"| node_cloud
node_audit -->|"investigates audit data"| node_datadog
node_securityskill -->|"uses security context"| node_datadog
node_delivery -->|"uses MCP and Pup"| node_datadog
node_replay -->|"replays trace against"| node_localcode
node_autoexperiment -->|"scores code changes"| node_localcode
node_experiments -->|"analyzes experiments"| node_datadog
node_expbootstrap -->|"uses LLM observability SDKs"| node_datadog
node_annotations -->|"publishes evaluator draft"| node_datadog

click node_pup "https://github.com/datadog-labs/agent-skills/blob/main/dd-pup/SKILL.md"
click node_monitors "https://github.com/datadog-labs/agent-skills/blob/main/dd-monitors/SKILL.md"
click node_logs "https://github.com/datadog-labs/agent-skills/blob/main/dd-logs/SKILL.md"
click node_apm "https://github.com/datadog-labs/agent-skills/blob/main/dd-apm/SKILL.md"
click node_docs "https://github.com/datadog-labs/agent-skills/blob/main/dd-docs/SKILL.md"
click node_session "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-session-classify/SKILL.md"
click node_rca "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-trace-rca/SKILL.md"
click node_evalbootstrap "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-eval-bootstrap/SKILL.md"
click node_pipeline "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-eval-pipeline/SKILL.md"
click node_experiments "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-experiment-analyzer/SKILL.md"
click node_expbootstrap "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-experiment-bootstrap/SKILL.md"
click node_annotations "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-build-eval-from-annotations/SKILL.md"
click node_autoexperiment "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-auto-experiment/SKILL.md"
click node_replay "https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-replay-trace/SKILL.md"
click node_rum "https://github.com/datadog-labs/agent-skills/blob/main/dd-instrument-rum/SKILL.md"
click node_browser "https://github.com/datadog-labs/agent-skills/blob/main/dd-browser-sdk/SKILL.md"
click node_apps "https://github.com/datadog-labs/agent-skills/blob/main/dd-apps/datadog-app/SKILL.md"
click node_recommender "https://github.com/datadog-labs/agent-skills/blob/main/dd-product-recommender/SKILL.md"
click node_audit "https://github.com/datadog-labs/agent-skills/blob/main/dd-audit/SKILL.md"
click node_securityskill "https://github.com/datadog-labs/agent-skills/blob/main/dd-security/csm/ownership-agent/SKILL.md"
click node_delivery "https://github.com/datadog-labs/agent-skills/blob/main/dd-software-delivery/unblock-pr/SKILL.md"
click node_cloud "https://github.com/datadog-labs/agent-skills/blob/main/dd-aws-integration/SKILL.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_pup,node_monitors,node_logs,node_apm,node_docs toneBlue
class node_session,node_rca,node_evalbootstrap,node_pipeline,node_experiments,node_expbootstrap,node_annotations,node_autoexperiment,node_replay toneAmber
class node_rum,node_browser,node_apps,node_recommender toneMint
class node_audit,node_securityskill,node_delivery,node_cloud toneRose
class node_engineer,node_agent,node_datadog,node_rumsignals,node_localcode toneIndigo
```

## Components

### Core Datadog

- [Pup CLI](https://github.com/datadog-labs/agent-skills/blob/main/dd-pup/SKILL.md): `dd-pup/SKILL.md`
- [Monitor Management](https://github.com/datadog-labs/agent-skills/blob/main/dd-monitors/SKILL.md): `dd-monitors/SKILL.md`
- [Log Search](https://github.com/datadog-labs/agent-skills/blob/main/dd-logs/SKILL.md): `dd-logs/SKILL.md`
- [APM Guidance](https://github.com/datadog-labs/agent-skills/blob/main/dd-apm/SKILL.md): `dd-apm/SKILL.md`
- [Documentation Search](https://github.com/datadog-labs/agent-skills/blob/main/dd-docs/SKILL.md): `dd-docs/SKILL.md`

### Agent Observability

- [Session Classification](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-session-classify/SKILL.md): `agent-observability/agent-observability-session-classify/SKILL.md`
- [Trace RCA](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-trace-rca/SKILL.md): `agent-observability/agent-observability-trace-rca/SKILL.md`
- [Evaluator Bootstrap](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-eval-bootstrap/SKILL.md): `agent-observability/agent-observability-eval-bootstrap/SKILL.md`
- [Eval Pipeline](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-eval-pipeline/SKILL.md): `agent-observability/agent-observability-eval-pipeline/SKILL.md`
- [Experiment Analysis](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-experiment-analyzer/SKILL.md): `agent-observability/agent-observability-experiment-analyzer/SKILL.md`
- [Experiment Bootstrap](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-experiment-bootstrap/SKILL.md): `agent-observability/agent-observability-experiment-bootstrap/SKILL.md`
- [Annotation Evaluator](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-build-eval-from-annotations/SKILL.md): `agent-observability/agent-observability-build-eval-from-annotations/SKILL.md`
- [Prompt Optimization](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-auto-experiment/SKILL.md): `agent-observability/agent-observability-auto-experiment/SKILL.md`
- [Trace Replay](https://github.com/datadog-labs/agent-skills/blob/main/agent-observability/agent-observability-replay-trace/SKILL.md): `agent-observability/agent-observability-replay-trace/SKILL.md`

### Application Workflows

- [RUM Instrumentation](https://github.com/datadog-labs/agent-skills/blob/main/dd-instrument-rum/SKILL.md): `dd-instrument-rum/SKILL.md`
- [Browser SDK](https://github.com/datadog-labs/agent-skills/blob/main/dd-browser-sdk/SKILL.md): `dd-browser-sdk/SKILL.md`
- [Datadog Apps](https://github.com/datadog-labs/agent-skills/blob/main/dd-apps/datadog-app/SKILL.md): `dd-apps/datadog-app/SKILL.md`
- [Product Recommender](https://github.com/datadog-labs/agent-skills/blob/main/dd-product-recommender/SKILL.md): `dd-product-recommender/SKILL.md`

### Security and Delivery

- [Audit Investigations](https://github.com/datadog-labs/agent-skills/blob/main/dd-audit/SKILL.md): `dd-audit/SKILL.md`
- [Security Ownership](https://github.com/datadog-labs/agent-skills/blob/main/dd-security/csm/ownership-agent/SKILL.md): `dd-security/csm/ownership-agent/SKILL.md`
- [Delivery Workflows](https://github.com/datadog-labs/agent-skills/blob/main/dd-software-delivery/unblock-pr/SKILL.md): `dd-software-delivery/unblock-pr/SKILL.md`
- [Cloud Integrations](https://github.com/datadog-labs/agent-skills/blob/main/dd-aws-integration/SKILL.md): `dd-aws-integration/SKILL.md`

### Other components

- **Engineer**
- **AI Agent**
- **Datadog Platform**
- **RUM Signals**
- **Local Application**

## Connections

- Engineer → AI Agent: requests task
- AI Agent → Pup CLI: uses guidance
- AI Agent → Monitor Management: uses guidance
- AI Agent → Log Search: uses guidance
- AI Agent → APM Guidance: uses guidance
- AI Agent → Documentation Search: uses guidance
- Pup CLI → Datadog Platform: authenticates and operates
- Monitor Management → Datadog Platform: manages monitors
- Log Search → Datadog Platform: searches logs
- APM Guidance → Datadog Platform: investigates traces
- Documentation Search → Datadog Platform: searches documentation
- AI Agent → Session Classification: uses guidance
- AI Agent → Trace RCA: uses guidance
- AI Agent → Eval Pipeline: uses guidance
- AI Agent → Experiment Analysis: uses guidance
- AI Agent → Experiment Bootstrap: uses guidance
- AI Agent → Annotation Evaluator: uses guidance
- AI Agent → Prompt Optimization: uses guidance
- AI Agent → Trace Replay: uses guidance
- Eval Pipeline → Session Classification: classifies sessions
- Eval Pipeline → Trace RCA: diagnoses failures
- Eval Pipeline → Evaluator Bootstrap: builds evaluators
- Eval Pipeline → Datadog Platform: publishes and runs evaluations
- Session Classification → RUM Signals: combines behavioral signals
- AI Agent → RUM Instrumentation: uses guidance
- AI Agent → Browser SDK: uses guidance
- AI Agent → Datadog Apps: uses guidance
- AI Agent → Product Recommender: uses guidance
- RUM Instrumentation → Datadog Platform: sends RUM data
- Browser SDK → Datadog Platform: guides SDK telemetry
- Datadog Apps → Datadog Platform: queries platform data
- AI Agent → Audit Investigations: uses guidance
- AI Agent → Security Ownership: uses guidance
- AI Agent → Delivery Workflows: uses guidance
- AI Agent → Cloud Integrations: uses guidance
- Audit Investigations → Datadog Platform: investigates audit data
- Security Ownership → Datadog Platform: uses security context
- Delivery Workflows → Datadog Platform: uses MCP and Pup
- Trace Replay → Local Application: replays trace against
- Prompt Optimization → Local Application: scores code changes
- Experiment Analysis → Datadog Platform: analyzes experiments
- Experiment Bootstrap → Datadog Platform: uses LLM observability SDKs
- Annotation Evaluator → Datadog Platform: publishes evaluator draft