grafana-dashboards
Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.
69
56%
Does it follow best practices?
Impact
85%
1.16xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/observability-monitoring/skills/grafana-dashboards/SKILL.mdQuality
Discovery
89%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 solid description with explicit 'Use when' triggers and good keyword coverage for the Grafana monitoring domain. Its main weakness is that the capability listing is somewhat general ('create and manage') rather than enumerating specific concrete actions like configuring panels, setting up alerting rules, or defining data source connections. Overall it performs well for skill selection purposes.
Suggestions
Expand the 'what' portion with more specific concrete actions, e.g., 'configure dashboard panels, set up alert rules, define template variables, connect data sources' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Grafana dashboards) and some actions ('create and manage production Grafana dashboards'), but doesn't list multiple specific concrete actions like configuring panels, setting up alerts, creating variables/templates, or defining data source queries. | 2 / 3 |
Completeness | Clearly answers both 'what' (create and manage production Grafana dashboards for real-time visualization of system and application metrics) and 'when' (Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'Grafana', 'dashboards', 'monitoring', 'metrics', 'visualization', 'observability'. These are terms users would naturally use when requesting this kind of work. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Grafana dashboards specifically, with distinct triggers like 'Grafana', 'monitoring dashboards', and 'observability interfaces' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a Grafana JSON reference manual than an actionable skill for Claude. It's bloated with boilerplate JSON examples and generic best practices while lacking a clear workflow for actually creating dashboards. The content would benefit greatly from being restructured into a concise overview with linked reference files, and adding explicit step-by-step processes with validation checkpoints.
Suggestions
Replace the monolithic JSON catalog with a concise workflow: 1) Determine dashboard type (RED/USE), 2) Create dashboard JSON with required fields, 3) Validate JSON structure, 4) Provision via API/file, 5) Verify panels render correctly. Add validation checkpoints at each step.
Move panel type JSON examples and provisioning configs into separate reference files (e.g., PANEL_TYPES.md, PROVISIONING.md) and link from the main skill with clear descriptions of when to use each.
Remove explanations of RED/USE methods, generic best practices, and the 'Purpose'/'When to Use' sections — Claude already knows these concepts. Focus tokens on project-specific conventions, gotchas, and concrete patterns.
Provide a single complete, valid dashboard JSON example (with all required fields like uid, schemaVersion, version) rather than multiple incomplete fragments.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive JSON examples that are largely boilerplate. The 'Purpose' and 'When to Use' sections restate the obvious. RED/USE method explanations are concepts Claude already knows. The panel type examples are essentially Grafana documentation copy-pasted in, and the best practices list is generic advice that adds little value. | 1 / 3 |
Actionability | The JSON snippets are concrete and mostly copy-paste ready, which is good. However, they're incomplete dashboard definitions (missing required fields like uid, schemaVersion, etc.), and the referenced asset files (assets/api-dashboard.json, etc.) don't appear to actually exist. The skill describes what panels to use but doesn't provide a complete workflow for creating a dashboard from scratch. | 2 / 3 |
Workflow Clarity | There is no clear workflow or sequence of steps for creating a dashboard. The content is a reference catalog of panel types and JSON snippets without any process guidance. No validation steps are mentioned (e.g., validating JSON, testing dashboard imports, verifying data sources are connected). For a skill involving production dashboards, this lack of workflow and validation is a significant gap. | 1 / 3 |
Progressive Disclosure | References to asset files and related skills are present, which is good. However, the main file is a monolithic wall of JSON examples that should be split into separate reference files. The panel types catalog, alert configuration, and provisioning examples would be better as linked references, keeping the SKILL.md as a concise overview. | 2 / 3 |
Total | 6 / 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
- wshobson/agents
- Commit
91fe43e
- 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.