skill CX Codex

bigquery-agent-analytics-sdk — Claude Code skill: agent trace

Q: How do I install bigquery-agent-analytics-sdk in Claude?

Run `npx skills add reason-machines/data-skills --skill bigquery-agent-analytics-sdk -a claude-code`. The skill lands in `~/.claude/skills/bigquery-agent-analytics-sdk/SKILL.md`.

A skill for analyzing AI agent telemetry in BigQuery: trace reconstruction, LLM-as-Judge evaluation, and drift detection.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add reason-machines/data-skills --skill bigquery-agent-analytics-sdk -a claude-code

Open on GitHub

What bigquery-agent-analytics-sdk does

The skill brings the bigquery-agent-analytics Python toolkit into your project. It reads agent events from BigQuery, stitches them into traces, and renders each one as an ASCII DAG. Event semantics helpers tell apart agent start, tool invocation, LLM call, and agent end.

Inside you get a Client with get_trace, get_traces_for_session and time-range queries, a ViewManager that splits events by type into BigQuery views, SystemEvaluator plus LLM-as-Judge evaluators, and the bqaa CLI with commands for diagnostics, evaluation, and Agent Context Graph extraction. Periodic materialization can be scheduled — that command provisions Cloud Scheduler and Cloud Run.

You need Python 3.10+, a Google Cloud project with BigQuery enabled, and agent traces already sitting in BigQuery. Auth goes through GOOGLE_APPLICATION_CREDENTIALS or gcloud auth application-default login. Skip that step and the client simply won't reach your dataset, so wire up credentials before the first run.

What it helps with

rebuild agent traces from BigQuery events into one readable graph
score agent responses with an LLM judge against chosen criteria
compare the actual execution path with a golden one
spot drift in agent behavior over a time window
pull agent decisions out of the context graph

Example prompts for the agent

show trace trace-abc-123 and render it as a DAG
run llm-judge evaluation with criteria correctness and hallucination
compare trajectories against the golden path plan,execute,verify

How to install bigquery-agent-analytics-sdk

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill bigquery-agent-analytics-sdk -a claude-code

2Manually: put the files in place

~/.claude/skills/bigquery-agent-analytics-sdk/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/bigquery-agent-analytics-sdk/

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill bigquery-agent-analytics-sdk -a codex

2Manually: put the files in place

.agents/skills/bigquery-agent-analytics-sdk/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill bigquery-agent-analytics-sdk -a cursor

2Manually: put the files in place

.cursor/skills/bigquery-agent-analytics-sdk/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install reason-machines/data-skills bigquery-agent-analytics-sdk

2Manually: put the files in place

.github/skills/bigquery-agent-analytics-sdk/SKILL.md

1Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill bigquery-agent-analytics-sdk -a gemini-cli

2Platform CLI

gemini skills install https://github.com/reason-machines/data-skills --path skills/bigquery-agent-analytics-sdk

Manually: put the files in place

.devin/skills/bigquery-agent-analytics-sdk/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add reason-machines/data-skills --skill bigquery-agent-analytics-sdk -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about bigquery-agent-analytics-sdk

How do I install bigquery-agent-analytics-sdk in Claude?

Run npx skills add reason-machines/data-skills --skill bigquery-agent-analytics-sdk -a claude-code. The skill lands in ~/.claude/skills/bigquery-agent-analytics-sdk/SKILL.md.

What does bigquery-agent-analytics-sdk do?

It analyzes AI agent telemetry in BigQuery: reconstructs traces, builds per-event-type views, runs evaluations, and extracts decisions from the agent context graph.

What do I need before using it?

Python 3.10+, a Google Cloud project with BigQuery, and agent traces stored in BigQuery. Auth is set up via GOOGLE_APPLICATION_CREDENTIALS or gcloud auth application-default login.

bigquery-observability official google This skill helps retrieve BigQuery telemetry and choose the right data source. Use it to inspect jobs, slot contention, queues, reservations, and resource usage. CX Codex 1,800installs bigquery-bigframes official google Generates Python code for BigQuery data processing, analysis, and machine learning with BigFrames. Use it when a DataFrame API fits the task. CX Codex 6,426installs bigquery-pipeline-audit official github Skill audits Python + BigQuery scripts for cost leaks, idempotency, and production readiness. Catches uncontrolled loops, missing query cost limits, and unsafe writes—returns a structured report with exact line numbers. 8,800installs arize-evaluator arize A skill for Arize evaluator workflows: build an LLM judge or a deterministic code evaluator, then run it over spans and experiments. CX Codex +1 3,100installs looker-studio-bigquery akillness Turns BigQuery-backed Looker Studio work into one stakeholder packet: dashboard spec, slow-dashboard triage, refresh shape, audience split or exec handoff. CX Codex +1 389installs gcp-expert personamanagmentlayer A skill that hands your agent working GCP examples: Cloud Functions, BigQuery, Firestore, Pub/Sub and gcloud commands. Useful when the code targets Google Cloud. CX Codex +1 547installs

From the same set22

iac-data-engineering-terraform A skill with ready Terraform patterns for data engineering: S3 buckets, EC2 instances and IAM roles. Useful when you need to stand up pipeline infrastructure declaratively. CX Codex +1 1,800installs terraform-data-engineering-infrastructure A skill with Terraform patterns for data engineering: S3 data lake buckets, EC2 processing nodes, IAM roles. Useful when AWS infrastructure has to be described in code, not clicked together. CX Codex +1 1,800installs harvard-artifacts-etl-pipeline A skill that walks your coding agent through an ETL pipeline from the Harvard Art Museums API to Streamlit charts. CX Codex +1 1,700installs data-analytics-skills-claude A collection of analytics skills for checking data, investigating metrics, and shaping dashboard specs. Use it when an analysis needs a clear workflow and shareable results. CX Codex +1 1,300installs harvard-art-museum-data-engineering A skill that builds an ETL pipeline for the Harvard Art Museums API: pull artifacts, shape them into tables, load into SQL, and chart them in Streamlit. CX Codex +1 1,300installs harvard-art-museums-data-engineering A skill for building ETL pipelines on Harvard Art Museums API data: normalise into MySQL, run SQL analytics, ship a Streamlit dashboard. CX Codex +1 843installs power-bi-salespulse-360-dashboard A skill that walks your agent through building the SalesPulse 360 retail dashboard in Power BI: sales, profit, regions and a 12-month forecast. CX Codex +1 656installs telegram-group-analytics-bot This skill tracks Telegram group activity: member growth, message counts, hourly heatmaps and scheduled reports you can export. CX Codex +1 610installs