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
86%
1.17xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/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 clear 'what' and 'when' clauses and good trigger term coverage around Grafana, monitoring, and observability. Its main weakness is that the specificity of capabilities could be improved by listing more concrete actions beyond 'create and manage' (e.g., configuring panels, setting up alerting rules, defining data source connections, creating template variables).
Suggestions
Expand the capability list with more specific actions, e.g., 'configure panels, set up alert rules, define data source queries, create template variables' 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) with an explicit 'Use when...' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Grafana', 'dashboards', 'monitoring', 'metrics', 'visualization', 'observability'. These cover the main terms a user would naturally use when requesting this kind of work. | 3 / 3 |
Distinctiveness Conflict Risk | The mention of 'Grafana' specifically, combined with 'monitoring dashboards' and 'observability', creates a clear niche that is unlikely to conflict with other skills. It's distinctly about Grafana dashboard creation rather than generic data visualization or other monitoring tools. | 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 guide. It's bloated with large JSON blocks for every panel type, explains concepts Claude already knows (RED/USE methods), and lacks a clear workflow for actually building and validating dashboards. The content would benefit greatly from moving detailed JSON examples to reference files and replacing them with a concise, step-by-step dashboard creation workflow with validation checkpoints.
Suggestions
Move the detailed JSON panel examples to a separate reference file (e.g., `references/panel-types.md`) and keep only one concise example in the main skill file.
Add a clear step-by-step workflow: 1) Define metrics to monitor, 2) Create dashboard JSON, 3) Validate queries against Prometheus, 4) Provision dashboard, 5) Verify panels render correctly.
Remove the RED/USE method explanations and the 'Purpose'/'When to Use' sections — Claude already knows these concepts and they waste tokens.
Add validation checkpoints such as testing PromQL queries before embedding them in dashboards and verifying provisioned dashboards load without errors.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose with large JSON blocks that are essentially reference documentation. The 'Purpose' and 'When to Use' sections restate the obvious. The RED/USE method explanations are concepts Claude already knows. Multiple panel type examples could be condensed significantly or moved to reference files. | 1 / 3 |
Actionability | The JSON examples are concrete and mostly copy-paste ready, which is good. However, there's no clear workflow for actually creating a dashboard end-to-end — it's more of a reference catalog of panel types and configurations than actionable step-by-step guidance. Missing context on how to deploy or validate these dashboards. | 2 / 3 |
Workflow Clarity | There is no clear sequential workflow for creating a dashboard. The content is organized as a reference catalog (panel types, variables, alerts) without a coherent process flow. No validation steps are mentioned — no guidance on testing dashboards, verifying queries return data, or checking for errors in provisioned dashboards. | 1 / 3 |
Progressive Disclosure | References to external files (assets/*.json, references/dashboard-design.md) are present and clearly listed at the bottom. However, the main file is a monolithic wall of JSON examples that should largely live in those referenced files instead. The inline content is far too detailed for an overview skill file. | 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
- Dicklesworthstone/pi_agent_rust
- Commit
6e3d68c
- 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.