skills.rest
GoogleDevRelExplorations
GoogleDevRelExplorationsOFFICIAL
Explore all skills by this author →
GitHub

cercano-stats

Summarize Cercano usage into a Markdown report of local versus cloud tokens.

Updated Mar 20, 2026
Search Tags:#telemetry#token-savings#usage-statistics#model-breakdown#cercano#local-tokens#cloud-tokens
One-click install
npx skills add https://github.com/GoogleDevRelExplorations/cercano --skill cercano-stats-googledevrelexplorations
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cercano-stats
Source: https://github.com/GoogleDevRelExplorations/cercano/tree/main/.agents/skills/cercano-stats
Command: npx skills add https://github.com/GoogleDevRelExplorations/cercano --skill cercano-stats-googledevrelexplorations

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps operators quantify Cercano usage by showing how many requests are processed locally versus in the cloud, enabling cost control and privacy-conscious decisions.

Core Features & Use Cases

  • Usage reporting: Generates a concise Markdown report with totals, local tokens, cloud tokens, kept-local percentage, and per-tool/model breakdowns.
  • Telemetry dashboards & planning: Enables telemetry dashboards, cost optimization, and capacity planning for Cercano deployments.
  • Historical context: Includes recent activity (last 7 days) for trend analysis.

Quick Start

Generate the latest Cercano usage report for the past 7 days.

Frequently Asked Questions about cercano-stats

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor local versus cloud token usage for Cercano deployments?▼

You can monitor Cercano token usage by generating a concise Markdown report that reveals local versus cloud token totals, kept-local percentages, and per-tool breakdowns for cost governance and capacity planning.

What is the best way to track cloud token savings from local processing?▼

The best way to track cloud token savings is by computing kept-local tokens via cercano_submit_usage telemetry data, which summarizes the difference between locally processed requests and cloud tokens consumed.

Do I need a Cercano server with telemetry enabled to generate usage statistics?▼

Yes, generating Cercano usage statistics requires a Cercano server with telemetry enabled to actively report usage data through cercano_submit_usage for accurate local and cloud token computation.

Can I view per-tool and per-model breakdowns in my telemetry dashboards?▼

Yes, you can view per-tool and per-model breakdowns in telemetry dashboards by processing Cercano usage telemetry, which outputs detailed markdown reports categorizing token consumption by specific tools and models.

How do I get a 7-day trend analysis of my Cercano token consumption?▼

You can get a 7-day trend analysis of Cercano token consumption by running a usage report that includes recent historical activity, summarizing local tokens, cloud tokens, and savings over the past week.

Why does my Cercano usage report show zero kept-local tokens?▼

Your Cercano usage report shows zero kept-local tokens when the Cercano server telemetry is not properly configured or when all requests are routing to the cloud instead of being processed locally.

Related Skills

Explore More Data & Analytics Skills→
GoogleDevRelExplorationsGoogleDevRelExplorations

cercano-submit-usage

Submit cloud token usage data to Cercano with input and output token counts.

Official
Basic
Aradhya0510Aradhya0510
3

querying-mlflow-metrics

Fetch aggregated trace metrics from MLflow tracking servers.

Community
Intermediate
bryancostanichbryancostanich
8

cercano-stats

Analyze Cercano usage telemetry to quantify local versus cloud inference and token savings.

Community
Intermediate
bryancostanichbryancostanich
8

cercano-submit-usage

Submit cloud token usage data to Cercano for telemetry analytics.

Community
Basic