Search skills/

google-agents-cli-observability skill

Covers monitoring deployed agents: Cloud Trace, prompt-response logging, BigQuery Agent Analytics and third-party tools such as Phoenix or AgentOps.

in google/agents-cli Skill & agent toolingCloud & DevOps
Our verdict Recommended

Practical guidance with a useful deployment-order warning; it assumes Google Cloud and the agents-cli workflow.

3/5 Depth expertise shipped Note Security Review before installing 2d Maintenance Updated 2 days ago 519K Adoption installs OK License Apache-2.0, commercial OK

What the google-agents-cli-observability skill does

The observability skill explains how to see what a deployed agent is doing. It sorts options into tiers: Cloud Trace, which works without extra infrastructure; prompt-response logging to Cloud Storage; and BigQuery Agent Analytics, which need Terraform-provisioned resources (a service account, bucket and dataset). It also mentions third-party integrations such as AgentOps, Phoenix and MLflow.

A key section deals with order of operations: if you ran agents-cli deploy before applying Terraform, the skill warns against applying Terraform afterward because it owns the whole Agent Runtime engine, and gives two ways out (delete and redeploy, or keep the instance and set environment variables and IAM roles by hand). Four reference files cover Cloud Trace and logging, the BigQuery analytics plugin, ADK documentation pages and a user-feedback endpoint that logs structured feedback to BigQuery. The SKILL.md is about 12 KB. It notes that some features exist for Python only.

Good for

  • Debugging production traffic of a deployed ADK agent
  • Adding tracing and analytics to an agents-cli project

Not for

  • Observability for non-Google stacks
  • Agents that are not deployed yet

Depth 3/5

A 12 KB SKILL.md with four reference files; no scripts or evals.

Dependencies and costs

  • agents-cli (uv tool install google-agents-cli), Python 3.11+, uv and Node.js
  • A Google Cloud project and credentials for deployment and cloud features (an AI Studio API key is enough for local create, run and eval)
  • Telemetry: The agents-cli tool sends one usage signal per command (command name, exit code, error class, duration, CLI and Python versions, OS), written as a log entry to your own Google Cloud project's Cloud Logging, never file contents or arguments. Opt out with AGENTS_CLI_TELEMETRY=0; agents-cli info shows the current state.

Security review

Review before installing

Markdown-only guide to tracing and logging deployed agents (Cloud Trace, prompt-response logging, BigQuery Agent Analytics, third-party platforms). Following it makes your agent send traces and optionally prompt/response content to Google Cloud and, if you choose, a third-party SaaS; the skill says to ask the user which platform to use. The agents-cli tool was not reviewed and sends usage telemetry unless you opt out.

Worth knowing

  • Relies on a CLI or package we could not reviewRequires the agents-cli binary (install: uv tool install google-agents-cli), whose code is not in the skill folder.SKILL.md:20
  • Installs packages or toolsInstall step is uv tool install google-agents-cli.SKILL.md:20
  • Makes network requestsTells the agent to fetch adk.dev integration docs, and describes exporting traces and logs to Google Cloud Trace/Logging/BigQuery and optional third-party platforms.SKILL.md:93
  • Sends usage data by default (can be turned off)The agents-cli tool this skill drives sends per-command usage telemetry by default; the repo README (outside the skill folder) documents AGENTS_CLI_TELEMETRY=0 and DO_NOT_TRACK=1 to opt out.README.md:195

What we checked

The skill folder (5 files) on Oct 29, 2026. Not a full review: it relies on code outside the repository: agents-cli (PyPI package google-agents-cli, installed with uv tool install); terraform invoked by the documented infra commands.

NVIDIA SkillSpector static scan: 5 pattern hits (analysis-evasion 5). All five hits are 'partial analysis' notes about reference markdown files that exist in the folder; telemetry matches are the skill's subject (OpenTelemetry tracing of the user's own agent).

A review, not a certification. Skills change after we check them — read the files before installing.

License

Apache-2.0 — commercial use allowed.

Can it run unattended?

Not really. It sets up monitoring rather than running long unattended work.

Alternatives

Cloudflare Skills

cloudflare/skills

Cloudflare's official 19-skill pack for building on Workers, Durable Objects, the Agents SDK, Cloudflare One and more, with an optional bundled MCP server.

Recommended Check first Depth 4/5

Google Agent Skills

google/skills

Google's official collection of about 180 skills for Google Cloud, Gemini APIs, Analytics, Data Manager, sign-in and other Google products.

Recommended Broad access Depth 3/5

Mastra Agent Skills

mastra-ai/skills

Mastra's official skills: a framework guide that routes to current docs and ten references, and a Factory supervisor skill for the mastra api CLI.

With caveats Broad access Depth 3/5

FAQ

What is google-agents-cli-observability?

Covers monitoring deployed agents: Cloud Trace, prompt-response logging, BigQuery Agent Analytics and third-party tools such as Phoenix or AgentOps.

How do I install google-agents-cli-observability?

It ships in the google/agents-cli repository. Run uvx google-agents-cli setup or npx skills add google/agents-cli; the skill expects the agents-cli binary (uv tool install google-agents-cli).

Does enabling observability store my prompts?

Prompt-response logging writes completions to a Cloud Storage bucket in your project and BigQuery analytics store agent events, so prompts and outputs may be retained. Check your data policies before turning them on.

Sources: GitHub repository; install counts from skills.sh via Best Skills (CC BY 4.0). Review based on the published SKILL.md.