skill-monitor

Summarize per-skill effectiveness signals from session metrics into dashboard snapshots.

7|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/slbug/claude-ruby-grape-rails --skill skill-monitor
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-monitor
Source: https://github.com/slbug/claude-ruby-grape-rails/tree/main/.claude/skills/skill-monitor
Command: npx skills add https://github.com/slbug/claude-ruby-grape-rails --skill skill-monitor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Summarize observational signals about how skills perform across contributor sessions so teams can prioritize transcript review and recommend improvements without mistaking correlation for causation.

Core Features & Use Cases

  • Read and parse session metrics to extract per-skill effectiveness signals, sample sizes, and outcome distributions for exploratory monitoring.
  • Provide provider- and time-window scoping, per-skill filtering, low-sample confidence warnings, and dominant outcome summaries to surface candidates for manual review.
  • Support an improvement mode that delegates to a skill-effectiveness-analyzer, cite session evidence and confounders, and write dashboard snapshots under .claude/skill-metrics for historical tracking.
  • Use cases include triaging which skills to inspect in transcript review, corroborating docs-check or lab/eval results, and generating prioritized, evidence-framed recommendations.

Quick Start

Run the skill to generate an observational dashboard from .claude/session-metrics/metrics.jsonl for a chosen time window, provider, or specific skill.

Frequently Asked Questions about skill-monitor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor skill effectiveness from session metrics?

Skill effectiveness monitoring works by reading the metrics.jsonl ledger to compute weighted aggregates and outcome distributions, producing exploratory dashboards that surface candidates for manual transcript review without modifying the source data.

How do I build an exploratory dashboard for per-skill triage?

Building a per-skill triage dashboard involves parsing session metrics to extract effectiveness signals and outcome distributions, using flags for skill selection, time window, and provider to scope the results for prioritized review.

Does session metrics monitoring work with provider and time-window scoping?

Yes, session metrics monitoring supports provider-scoped and time-window-scoped dashboards, allowing you to filter effectiveness signals and outcome distributions by specific providers or time periods for targeted triage.

Do I need a metrics.jsonl ledger to generate skill effectiveness dashboards?

Yes, generating skill effectiveness dashboards requires the metrics.jsonl ledger at .claude/session-metrics/metrics.jsonl, as the monitoring process reads and parses this file to extract observational signals without modifying the source.

What are the limitations of using session metrics for skill triage?

A key limitation is that session metrics monitoring summarizes observational signals to prioritize review without mistaking correlation for causation, relying on confounder citations and low-sample confidence warnings rather than proving direct causality.