app-observability
Grafana Cloud Application Observability (APM), Frontend Observability (RUM/Faro), and AI Observability. Covers RED metrics (Rate/Error/Duration), service maps, span metrics from traces, Faro JavaScript/React SDK for browser instrumentation, session replay, AI/LLM model monitoring, and integration with traces/logs/profiles for full-stack correlation. Use when setting up APM, configuring frontend monitoring, analyzing service performance, or monitoring AI/LLM applications.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 defines its scope across three Grafana Cloud observability domains with specific technical capabilities listed. It includes an explicit 'Use when...' clause with practical trigger scenarios and uses natural terminology that practitioners would employ. The description is well-structured, concise, and highly distinctive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and capabilities: RED metrics, service maps, span metrics from traces, Faro JavaScript/React SDK for browser instrumentation, session replay, AI/LLM model monitoring, and full-stack correlation with traces/logs/profiles. | 3 / 3 |
Completeness | Clearly answers both 'what' (APM, Frontend Observability, AI Observability with specific features listed) and 'when' with an explicit 'Use when...' clause covering setup, configuration, analysis, and monitoring scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: APM, frontend monitoring, RUM, Faro, RED metrics, service maps, session replay, AI/LLM monitoring, browser instrumentation, service performance. These are terms practitioners naturally use when working with Grafana observability. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Grafana Cloud's specific observability products (Application Observability, Faro, AI Observability). The combination of Grafana-specific terminology like Faro SDK, RED metrics, and service maps makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable skill covering three related Grafana Cloud products with real, executable code examples and concrete configuration snippets. Its main weaknesses are the monolithic structure (could benefit from splitting into sub-files for each product area) and the lack of validation/verification steps in setup workflows. Some introductory explanations could be trimmed to improve token efficiency.
Suggestions
Add validation checkpoints to setup workflows - e.g., after Alloy configuration, include a step to verify traces are arriving (query Tempo or check Service Inventory), and after Faro setup, verify signals appear in Frontend Observability.
Split the three product sections (APM, Frontend/Faro, AI Observability) into separate referenced files to reduce the main SKILL.md to an overview with quick-start snippets and links to detailed guides.
Trim or remove 'What It Is' subsections - Claude doesn't need explanations of what APM, RUM, or LLM monitoring are; jump directly to configuration and usage details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive and mostly efficient, but includes some unnecessary explanations (e.g., 'What It Is' sections explaining concepts Claude likely knows, describing what RUM stands for, explaining what RED metrics are). Some sections like the Service Map description could be tightened. However, the code examples and tables are lean and well-structured. | 2 / 3 |
Actionability | Excellent actionability throughout - fully executable code examples for Alloy configuration (River syntax), Faro SDK setup (npm, CDN, React), OpenLIT Python setup, environment variables with concrete values, and step-by-step UI navigation paths. Code is copy-paste ready with real package versions and actual API patterns. | 3 / 3 |
Workflow Clarity | The 'Common Tasks' section provides clear multi-step workflows for debugging scenarios, and the 'Setup Path' for AI Observability is well-sequenced. However, there are no explicit validation checkpoints or error recovery steps in the setup workflows - e.g., no 'verify traces are arriving' step after Alloy configuration, no troubleshooting guidance if metrics don't appear, and no validation after Faro SDK initialization. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and a logical flow from APM to Frontend to AI Observability. However, at ~350+ lines this is a monolithic document that would benefit from splitting detailed configurations (Alloy config, React setup, AI evaluations) into separate referenced files. The References section at the end links to external docs but there are no bundle files for progressive disclosure within the skill itself. | 2 / 3 |
Total | 9 / 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
- grafana/skills
- Commit
8f1ba27
- 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.