prometheus-configuration

Set up Prometheus for comprehensive metric collection, storage, and monitoring of infrastructure and applications. Use when implementing metrics collection, setting up monitoring infrastructure, or configuring alerting systems.

Install with Tessl CLI

npx tessl i github:wshobson/agents --skill prometheus-configuration

What are skills?

Review — 70%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

16%

SRE Metrics Pre-computation for API Service

Recording rule design

Criteria

Without context

With context

Naming convention

100%

Request rate aggregation

100%

Error rate rule

100%

Error rate percentage rule

100%

P95 latency uses histogram_quantile

100%

P95 le aggregation

100%

API group interval

100%

Resource group interval

100%

CPU utilization formula

100%

Memory utilization formula

100%

Disk utilization formula

100%

Without context: $0.3241 · 5m 34s · 12 turns · 138 in / 5,971 out tokens

With context: $0.3720 · 2m 45s · 18 turns · 1,031 in / 3,842 out tokens

83%

23%

Production Alerting for API Service and Infrastructure

Alert rule configuration

Criteria

Without context

With context

for: clause present

100%

Critical for: 1m

Warning for: 5m

40%

Severity label

100%

summary annotation

100%

description annotation

100%

Template variables in annotations

100%

Recording rule references

100%

90%

Error rate threshold 5%

100%

CPU threshold 80%

100%

Memory threshold 85%

100%

Disk threshold 90%

100%

Without context: $0.3653 · 6m 38s · 12 turns · 97 in / 6,675 out tokens

With context: $0.4555 · 9m 50s · 15 turns · 98 in / 6,846 out tokens

100%

12%

Prometheus Setup for Multi-Service Production Environment

Prometheus configuration

Criteria

Without context

With context

scrape_interval 15s

100%

evaluation_interval 15s

100%

external_labels present

100%

Alertmanager port 9093

100%

rule_files wildcard

100%

Self-monitoring job

100%

Instance relabeling

100%

Dynamic service discovery

100%

Scrape intervals in range

100%

promtool validation

100%

Static target labels

100%

Without context: $0.2749 · 3m 15s · 14 turns · 105 in / 3,741 out tokens

With context: $0.3843 · 2m 48s · 18 turns · 390 in / 3,733 out tokens

Evaluated: about 19 hours ago
Agent: Claude Code

Table of Contents

SRE Metrics Pre-computation for API Service Production Alerting for API Service and Infrastructure Prometheus Setup for Multi-Service Production Environment

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.