Skip to main content
affpapa.org
RU EN
skill CX Codex GP ChatGPT official · OpenAI

metric-diagnostics — Codex skill: what it does, how to install

This skill investigates metric changes, anomalies, gaps, and mismatches with expectations. Use it when you need evidence for likely drivers.

Install into Codex · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add openai/plugins --skill metric-diagnostics -a codex
Open on GitHub

What metric-diagnostics does

The skill frames the diagnostic question before searching for causes. It clarifies the metric meaning, comparison window, population, grain, and owning source, then reproduces the calculation and measures the size, timing, and scope of the movement.

It searches relevant data surfaces, compares overlapping sources, and checks definitions, filters, joins, freshness, lineage, and aggregation. Driver analysis can use semantic layers, dashboards, tables, and other source-of-truth surfaces; fresh SQL or Python work can be recorded with jupyter-notebooks.

When a required source cannot be accessed, the skill stops that analysis path and asks for the source or a reviewed fallback. Related skills cover business context, data quality, and recommendations after the diagnosis.

What it helps with

  • explain why a metric moved
  • reproduce a comparison against a baseline
  • rank the segments driving a change
  • reconcile a gap between data sources
  • test whether a spike reflects data-quality issues

Example prompts for the agent

  • Diagnose why conversion changed between the two periods and quantify the segment contributions.
  • Investigate the mismatch between the dashboard metric and the source table.
  • Analyze the error spike: locate its onset, affected slices, and verified drivers.

How to install metric-diagnostics

1Skills CLI (Vercel)

npx skills add openai/plugins --skill metric-diagnostics -a codex

2Manually: put the files in place

.agents/skills/metric-diagnostics/SKILL.md

For all projects use ~/.agents/skills/

Step by step, with commands for each platform: Codex skills: how to install, where they live, how to call them

Questions about metric-diagnostics

How do I install metric-diagnostics in Codex?

Run npx skills add openai/plugins --skill metric-diagnostics, then npx skills add openai/plugins --skill metric-diagnostics -a codex. The skill file is placed at .agents/skills/metric-diagnostics/SKILL.md.

What does metric-diagnostics do?

It reconstructs the metric, defines a valid comparison, measures the movement, and tests likely drivers across relevant cuts and data sources.

What happens when the required metric source is unavailable?

The skill stops that analysis path and asks for the required source or a reviewed fallback. A weaker substitute is not treated as equivalent.

Similar skills

All skills for Data and databases →
kibana-anomaly-detection elastic Investigates Elastic ML anomalies, explains detector scores, and troubleshoots failed datafeeds. Useful for root-cause analysis across Elasticsearch jobs. CX Codex +1 3,100installs cloud-monitoring-metric-selection official google This skill finds relevant Google Cloud Monitoring metric descriptors for a service or resource. Use it when you need to choose metric types for a monitoring query. CX Codex 5,453installs dt-obs-predictive-analytics Dynatrace A Dynatrace skill that forecasts metric values, tracks trends and flags anomalies across hosts and services. Useful for capacity planning and spotting what shifted. CX Codex +1 2,100installs launchdarkly-metric-create launchdarkly Walks you from picking a metric kind to creating it in LaunchDarkly: events get instrumented first, then the metric is created and verified. CX Codex +1 3,200installs elasticsearch-anomaly-detection-explainer elastic Explains Elasticsearch ML anomaly scores: why a record scored high or low, what the gap between initial and current scores means, and where to look next. CX Codex +1 1,000installs iot-anomalies ruvnet Detects and categorizes telemetry anomalies across Cognitum Seed devices. Helpful for diagnosing erratic device behavior or vetting metrics before rolling out a firmware canary. CX Codex +1 730installs

From the same set528

The whole set →
sentry This skill queries Sentry in read-only mode to inspect issues, events, and basic health data. Use it when checking recent production errors. CX Codex GP ChatGPT 4installs user-context Manages local user context, preferences, and onboarding state for the Public Equity Investing plugin. Runs strictly on explicit user request. CX Codex GP ChatGPT 4installs user-context Stores product and design references for future Product Design work. Use it when an agent needs the same files, links, and preferences across tasks. CX Codex GP ChatGPT 4installs validate-data Audits analytical reports, SQL queries, metrics, and charts before sharing them with stakeholders or basing decisions on them. CX Codex GP ChatGPT 4installs build-report Builds analytical reports with findings, tables, and visuals for executives, product teams, or technical audiences. CX Codex GP ChatGPT 4installs define-security-policy Helps author, review, and update SECURITY.md files so Codex Security knows project boundaries, invariants, and out-of-scope targets. CX Codex GP ChatGPT 4installs sandbox-sdk A Codex skill for building with Cloudflare Sandbox SDK, from command and code execution to sandbox files and preview URLs. Use it when a Worker needs to run untrusted or AI-generated code. CX Codex GP ChatGPT 4installs circleci-cli Operates and troubleshoots CircleCI pipelines via the CircleCI CLI. Useful for validating configs, checking build failures, and triggering jobs directly from Codex. CX Codex GP ChatGPT 4installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor