google-agents-cli-observability

The google-agents-cli-observability skill provides guidance and configuration support for monitoring, tracing, and logging ADK (Agent Development Kit) agents. It covers native Google Cloud integrations like Cloud Trace, prompt-response logging, and BigQuery Agent Analytics, alongside various third-party observability platforms.

50.5K

Installs

Use cases

5/10

Quality

Is google-agents-cli-observability safe to install?

Review the source first

Review the source first: our audit of google-agents-cli-observability's source files found 2 shell commands, 11 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands for infrastructure provisioning and fetches external documentation URLs.

How we audit skills: our security review methodology.

Who is this skill for?

Developers and engineers working with Google ADK agents who need to implement, debug, or optimize observability, logging, and tracing in their applications.

What can you do with it?

Setting up distributed tracing with Cloud Trace
Configuring prompt-response logging to GCS and BigQuery
Enabling BigQuery Agent Analytics for structured event tracking
Integrating third-party observability tools like AgentOps, Phoenix, or MLflow
Troubleshooting telemetry data gaps and configuration issues

How good is this skill?

Quality score: 5/10. The skill provides clear, structured guidance on observability tiers and troubleshooting steps. It maintains a consistent reference to external documentation and CLI commands.

What does the skill file contain?

SKILL.md

# ADK Observability Guide

> **Cloud Trace** works out of the box — no infrastructure needed. **Prompt-response logging** and **BigQuery Agent Analytics** require Terraform-provisioned infrastructure (service account, GCS bucket, BigQuery dataset). Run `agents-cli infra single-project --project PROJECT_ID` to provision these resources. See `references/cloud-trace-and-logging.md` for details, env vars, and verification commands. If your project isn't scaffolded yet, see `/google-agents-cli-scaffold` first.

### Order of operations for `agent_runtime` deployments

For `deployment_target = agent_...

Frequently asked questions

How do I provision infrastructure for prompt-response logging?

Run the command 'agents-cli infra single-project --project PROJECT_ID' to provision the necessary service account, GCS bucket, and BigQuery dataset.

Can I use this skill to set up deployment targets?

No. Use the 'google-agents-cli-deploy' skill for deployment setup.

How do I enable BigQuery Agent Analytics?

Enable the plugin using the '--bq-analytics' flag during the initial project scaffolding process.

What should I do if my traces are missing tool execution spans?

Check the trace explorer filters, as tool execution spans are nested under the 'execute_tool' span.

Data sourced from google/agents-cli on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Install

Works with Claude Code, Cursor, Codex CLI, and 50+ agents.

Manual install paths per agent

Claude Code: .claude/skills/ or ~/.claude/skills/

Codex CLI: .codex/skills/ or ~/.codex/skills/

GitHub Copilot: .github/skills/ or ~/.copilot/skills/

Amp: .agents/skills/ or ~/.config/agents/skills/

Copy the skill folder (with SKILL.md) into the project or global directory.

Security audit

high risk

Commands

URLs

Yes

File I/O

The skill executes shell commands for infrastructure provisioning and fetches external documentation URLs.

View commands and endpoints

$ agents-cli infra single-project --project PROJECT_ID

$ agents-cli deploy

https://adk.dev/integrations/cloud-trace/index.md

https://adk.dev/observability/logging/index.md

https://adk.dev/observability/index.md

https://adk.dev/integrations/bigquery-agent-analytics/index.md

https://adk.dev/integrations/agentops/index.md

https://adk.dev/integrations/arize-ax/index.md

https://adk.dev/integrations/phoenix/index.md

https://adk.dev/integrations/mlflow-tracing/index.md

Sourcegoogle/agents-cli

Installs50.5K

Quality5/10

observability monitoring tracing logging ADK Google Cloud

Related skills

azure-diagnostics

440.1K

Cloud engineers, DevOps professionals, and site reliability engineers managing Azure production environments

The azure-diagnostics skill provides a structured framework for troubleshooting Azure production issues. It integrates with AppLens, Azure Monitor, and resource health tools to identify root causes for services including App Service, Function Apps, AKS, and messaging services like Event Hubs and Service Bus.

highAzureDiagnosticsmicrosoft

google-agents-cli-scaffold

48.9K

Developers building AI agents using the Google ADK who need to automate project setup, infrastructure configuration, and deployment scaffolding

The google-agents-cli-scaffold skill provides commands to initialize, enhance, and upgrade projects within the Google Agent Development Kit (ADK). It manages project structure, deployment configurations, and CI/CD pipeline scaffolding.

highgoogleadkgoogle

google-agents-cli-workflow

45.1K

Developers building and deploying AI agents on Google Cloud using the Agent Development Kit (ADK)

The google-agents-cli-workflow skill provides a structured development lifecycle for building, evaluating, and deploying agents using the Agent Development Kit (ADK) and the agents-cli tool. It mandates a multi-phase process covering project scaffolding, implementation, behavioral evaluation, and deployment to Google Cloud.

highgoogle-cloudadkgoogle

google-agents-cli-adk-code

42.7K

Developers using the Google ADK Python SDK to build and maintain agent code

The google-agents-cli-adk-code skill provides a reference for Python ADK API patterns, including agent definitions, tool creation, callbacks, and state management. It serves as a guide for developers building agents with the Google Agent Development Kit.

highgoogleadkgoogle