monitoring-expert
Configures monitoring systems, implements structured logging pipelines, creates Prometheus/Grafana dashboards, defines alerting rules, and instruments distributed tracing. Implements Prometheus/Grafana stacks, conducts load testing, performs application profiling, and plans infrastructure capacity. Use when setting up application monitoring, adding observability to services, debugging production issues with logs/metrics/traces, running load tests with k6 or Artillery, profiling CPU/memory bottlenecks, or forecasting capacity needs.
92
88%
Does it follow best practices?
Impact
95%
1.17xAverage score across 6 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly enumerates specific capabilities across monitoring, logging, dashboards, alerting, tracing, load testing, and profiling. It includes an explicit 'Use when...' clause with natural trigger terms covering both tool-specific (Prometheus, Grafana, k6, Artillery) and conceptual (observability, capacity needs, production issues) language. The description is well-structured, distinctive, and comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: configures monitoring systems, implements structured logging pipelines, creates Prometheus/Grafana dashboards, defines alerting rules, instruments distributed tracing, conducts load testing, performs application profiling, and plans infrastructure capacity. | 3 / 3 |
Completeness | Clearly answers both 'what' (configures monitoring, implements logging, creates dashboards, etc.) and 'when' with an explicit 'Use when...' clause covering multiple trigger scenarios like setting up monitoring, debugging production issues, running load tests, and profiling bottlenecks. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: monitoring, logging, Prometheus, Grafana, dashboards, alerting, distributed tracing, load testing, k6, Artillery, profiling, CPU/memory bottlenecks, capacity, observability, logs/metrics/traces. Good coverage of both tool names and conceptual terms. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around observability, monitoring, and performance engineering with distinct triggers like Prometheus, Grafana, k6, Artillery, distributed tracing, and capacity planning that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with executable examples and a clear workflow that includes validation checkpoints. Its main weakness is that it's trying to serve as both a concise overview and a detailed reference — the inline code examples are extensive enough that they should largely live in the referenced files, with the SKILL.md showing only minimal snippets. The reference table is well-designed and the constraints section adds clear guardrails.
Suggestions
Move the detailed code examples (Prometheus metrics, OpenTelemetry tracing, k6 load test) into their respective reference files and keep only 2-3 line snippets inline to demonstrate the pattern
Trim the structured logging example to just the 'good' pattern — Claude doesn't need the anti-pattern shown inline when the constraint section already covers it
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some verbosity. The inline code examples are quite long (especially the Prometheus metrics and OpenTelemetry sections) and could be trimmed or moved to reference files. The good/bad logging comparison is useful but the overall body is heavy for a SKILL.md that already has 8 reference files. | 2 / 3 |
Actionability | All examples are fully executable, copy-paste ready code with real libraries (Pino, prom-client, OpenTelemetry SDK, k6). The alerting rule YAML is complete and deployable. Each example includes specific configuration values like histogram buckets and threshold definitions. | 3 / 3 |
Workflow Clarity | The 5-step core workflow is clearly sequenced with explicit validation checkpoints: 'verify data arrives before proceeding' in step 3 and 'validate no false-positive flood before shipping' in step 5. This provides clear feedback loops for the monitoring setup process. | 3 / 3 |
Progressive Disclosure | The reference table is well-structured with clear 'Load When' guidance, but the main file includes substantial inline code examples that would be better placed in the referenced files. The SKILL.md tries to be both an overview and a detailed tutorial, undermining the progressive disclosure pattern. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jeffallan/claude-skills
- Commit
3d95bb1
- Reviewed
Table of Contents
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.