optimization.metric_review
Conduct a metric review that contextualizes performance trends, flags anomalies, and recommends actions.
npx skills add majiayu000/claude-skill-registry --skill metric-review-edwardmonteiro-aiskillinpractice-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Purpose Support continuous optimization by providing a structured prompt for reviewing performance data and identifying next steps. # Pre-run Checklist - ✅ Export relevant metric data (CSV or dashboard snapshots). - ✅ Align on segments and filters to analyze. - ✅ Confirm data freshness and quality. # Invocation Guidance ```bash codex run --skill optimization.metric_review \ --input data/{{goal_metric}}-{{period}}.csv \ --vars "goal_metric={{goal_metric}}" \ "period={{period}}" \ "comparison_period={{comparison_period}}" \ "segments={{segments}}" ``` # Recommended Input Attachments - CSV exports or BI dashboard screenshots. - Notes from recent experiments or launches impacting the metric. # Claude Workflow Outline 1. Summarize the goal metric, period, and comparison baseline. 2. Provide visual or tabular trend analysis highlighting significant movements. 3. Identify anomalies or inflections, offering hypotheses tied to events or segments. 4. Recommend actions, owners, and expected impact. 5. List questions or data gaps to investigate further. # Output Template ``` ## Metric Review — {{goal_metric}} ({{period}}) ### Performance Summary - Trend Overview: - % Change vs {{comparison_p
codex run --skill optimization.metric_review \
What does the optimization.metric_review skill do?
Conduct a metric review that contextualizes performance trends, flags anomalies, and recommends actions.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill metric-review-edwardmonteiro-aiskillinpractice-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.