This skill should be used when the user asks about "anomalies", "problems", "有異常嗎", "哪些會話有問題", "排查", "診斷", or suspects waste or efficiency issues in Claude Code usage. Scans for 6 types of statistical anomalies with severity scoring and automatic drill-down into suspicious sessions. Can also be routed from the main cta skill.
$npx -y skills add li195111/claude-token-analyzer --skill cta-anomaly-huntInstalls into the current project.
Run `npx skills use "https://github.com/li195111/claude-token-analyzer" --skill "li195111/claude-token-analyzer/cta-anomaly-hunt"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/li195111/claude-token-analyzer" that are relevant to the current task. Run `npx skills add "https://github.com/li195111/claude-token-analyzer"` and select the relevant skills, then follow their instructions.