llm-monitoring-dashboard

Auto-generates an LLM usage monitoring page in a PM admin dashboard. Tokuin CLI-based token/cost/latency tracking + user ranking system + inactive user tracking + data-driven PM insights + Cmd+K global search + per-user drilldown navigation. Supports OpenAI/Anthropic/Gemini/OpenRouter.

1.86x

Quality

52%

Does it follow best practices?

Impact

99%

1.86x

Average score across 3 eval scenarios

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent-skills/llm-monitoring-dashboard/SKILL.md

Evaluation results

97%

55%

LLM Usage Metrics Collection Pipeline

Privacy-safe metrics collection pipeline

Criteria

Without context

With context

No hardcoded API keys

100%

dry-run default

100%

JSONL output path

100%

Prompt hashing

100%

Prompt categorization

100%

Keyword-based classification

100%

User context fields

100%

Latency fields

100%

is_dry_run field

62%

.env in .gitignore

100%

Tokuin CLI usage

100%

status_code field

100%

43%

LLM Usage Monitoring Dashboard

Dashboard design tokens and drilldown navigation

Criteria

Without context

With context

Background token --bg-base

50%

100%

CSS design token variables

100%

3-level traffic light system

100%

Traffic light hex values

100%

Badge elements for status

100%

Monospace font for metrics

100%

Tabular numeric alignment

100%

User drilldown navigation

100%

Auto-generated PM insights

100%

Chart.js for charts

100%

Colorblind-friendly series colors

100%

Ranking medal colors

100%

39%

LLM Cost Monitoring: Automated Reporting and Alerting

PM report automation and cost alerting

Criteria

Without context

With context

safety-guard.sh exists

87%

100%

PM report Markdown format

100%

User ranking by cost

100%

Inactive user section

100%

Adoption rate metric

50%

100%

Report filename pattern

25%

100%

95% SLA success rate check

12%

100%

Configurable cost threshold

70%

100%

Alert exit code 1

100%

Slack webhook from env var

100%

Weekly report cron Monday 9am

100%

Cost alert cron hourly

100%

Repository: supercent-io/skills-template
Commit: c033769

Evaluated: 28 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

LLM Usage Metrics Collection Pipeline LLM Usage Monitoring Dashboard LLM Cost Monitoring: Automated Reporting and Alerting

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.