Skip to content
cccskills
FreePublished on GitHub

metric-watch

Inspect first-touch radar checks by reviewing query coverage, counts, thresholds, and backtests against incident and clean periods. It helps determine whether a fired alert reflects a meaningful change and calibrate thresholds using observed data and app-specific context.

OriginalShow the original description

Inspect first-touch radar checks, their query coverage, thresholds, and backtests. Use when a watch fires or a metric needs calibration.

BuilderIO/agent-native7,550 stars(GitHub 7,550 + cccskills 0)

Run score Not tested

See how to install

Good for

  • Investigating a fired first-touch alert
  • Calibrating a metric threshold with backtests
  • Reviewing query coverage and denominators

Files included (1)

  • SKILL.md1.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Metric watch

  • Run pnpm --filter analytics radar:watch --window daily; use --window hourly for provisioning and environment-key checks.
  • Read the check status, numerator, denominator, seven-day comparison, and coverage. insufficient is not a pass. unavailable and insufficient remain explicit and make a completed watch exit 1; exit 2 means the run could not complete.
  • Compare daily thresholds with the incident window and an ordinary week before changing them. Record both windows and the observed counts in the PR or report.
  • Use pnpm --filter analytics radar:backtest to compare the Oct 9–23 incident window with the Oct 2–8 clean week.
  • Action success uses a weighted action.response rate. Keep its app-specific threshold below the quiet-week distribution; do not copy the 95% starting value without a backtest.
  • Read signup campaign tags beside signup drops. Paid search changes are context, not proof that product behavior changed.
  • Event first-seen checks require 10 events that day; went-to-zero checks require at least 50 events across the preceding seven days.
  • Read campaign-followup as identified recipient counts after send versus the same recipients' prior seven days, split by recipient and activity app. Anonymous landings cannot be attributed to recipients.
  • The hourly Analytics alert rules cannot express ratios or trailing baselines; do not replace these checks with simple count rules.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

a2a-assets

FreeSummary

Generate, refine, export, and place brand images or videos from an Assets library into another app. The skill covers choosing a library, handling image batches and video runs, and updating selected assets after feedback.

  • Generate brand images for slides or another app
  • Refine an existing asset after feedback
  • Create and export a video asset
BuilderIO/agent-native7.6KUpdated Oct 29, 2026

ab-readout

FreeSummary

Analyze the first-run Builder credits experiment by checking sample balance, group sizes, confidence intervals, and mature cohorts. It helps prepare an evidence-aware readout for onboarding analysis or a weekly radar report, while keeping results associative rather than causal.

  • Reviewing first-run onboarding experiment results
  • Preparing the weekly radar report
  • Checking whether experiment data is mature enough
BuilderIO/agent-native7.6KUpdated Oct 29, 2026

account-health

FreeSummary

Prepare a customer account health, renewal, or contract usage readout. Verify the account identity, use approved metric definitions, compare contracted capacity with actual usage, and trace findings to sources, time windows, and known gaps.

  • Preparing a named customer's account health review
  • Comparing contracted seats or capacity with usage
  • Gathering adoption signals before a renewal or QBR
BuilderIO/agent-native7.6KUpdated Oct 29, 2026

actions

FreeSummary

Create focused app actions that agents can call as tools and frontend code can use through client hooks. Use them to add provider integrations or fetch UI data, with validated inputs and structured results.

  • Adding a new app operation
  • Connecting an external provider API
  • Fetching data for a frontend view
BuilderIO/agent-native7.6KUpdated Oct 29, 2026

adding-a-feature

FreeSummary

Use this checklist when adding a feature or integration to an agent-native app. It covers the user interface, agent-callable actions, instructions, and app-state sync so both the user and agent can work with the capability consistently.

  • Planning a new feature across UI and agent actions
  • Checking that agent changes appear in the UI
  • Documenting actions and feature state for the agent
BuilderIO/agent-native7.6KUpdated Oct 29, 2026

adhoc-analysis

FreeSummary

Investigate complex questions by combining data from multiple sources, then summarize patterns, metrics, and evidence in a clear report. Save requested analyses as dashboards with instructions for future refreshes.

  • Comparing CRM deals with call records
  • Investigating customer health across systems
  • Saving a repeatable performance analysis
BuilderIO/agent-native7.6KUpdated Oct 29, 2026

See all skills by BuilderIO

Report a problem with this skill