grafana-dashboards

Create and manage production-ready Grafana dashboards for comprehensive system observability.

Quality

39%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/grafana-dashboards/SKILL.md

Quality

Content

39%Scale 1-5

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 dashboard reference manual than an actionable skill for Claude. It is overly verbose with extensive JSON boilerplate for panel types Claude already knows how to generate, while lacking a clear workflow with validation steps. The referenced bundle files don't exist, undermining the progressive disclosure structure.

Suggestions

Drastically reduce inline JSON examples—keep one complete dashboard example and move panel-type references to actual bundle files (assets/*.json) that are included in the bundle.

Add a clear sequential workflow: 1) Gather requirements, 2) Choose dashboard pattern, 3) Build dashboard JSON, 4) Validate with Grafana API or import test, 5) Verify panels render correctly.

Remove explanations of RED/USE methods and basic panel types—Claude already knows these. Focus on project-specific conventions, naming patterns, and non-obvious configuration gotchas.

Create the referenced bundle files (implementation-playbook.md, dashboard-design.md, asset JSON files) or remove the references to avoid broken links.

Dimension	Reasoning	Score
Conciseness	The skill is significantly verbose. It explains well-known concepts like RED/USE methods, basic panel types, and dashboard design principles that Claude already knows. The extensive JSON examples for every panel type (stat, time series, table, heatmap) are largely boilerplate that Claude could generate on its own. The best practices section is a generic list of obvious advice.	2 / 5
Actionability	The skill provides concrete, executable JSON configurations for dashboards, panels, variables, alerts, and provisioning via Terraform/Ansible. These are copy-paste ready. However, there's no workflow for actually deploying or validating a dashboard end-to-end, and some references (like assets/*.json) don't exist in the bundle.	4 / 5
Workflow Clarity	There is no clear sequential workflow for creating a dashboard. The content is organized as a reference catalog of panel types and patterns rather than a step-by-step process. There are no validation checkpoints—no steps to verify a dashboard works correctly after creation, no feedback loops for fixing issues with queries or panel configurations.	2 / 5
Progressive Disclosure	The skill references multiple external files (assets/api-dashboard.json, resources/implementation-playbook.md, references/dashboard-design.md) but none of these exist in the bundle. Meanwhile, the SKILL.md itself is a monolithic wall of JSON examples that should be split into referenced files. The inline content is far too long for a skill overview.	2 / 5
	Total	10 / 20 Passed

Description

39%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a clear domain (Grafana dashboards) but relies on vague, buzzword-heavy language ('production-ready', 'comprehensive system observability') instead of listing concrete capabilities. It completely lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill over others. The Grafana-specific focus provides reasonable distinctiveness but the description needs significantly more detail and explicit trigger guidance.

Suggestions

Add a 'Use when...' clause with trigger terms like 'Grafana', 'dashboard', 'monitoring', 'metrics visualization', 'observability', 'panels'.

Replace vague qualifiers ('production-ready', 'comprehensive system observability') with concrete actions such as 'configure panels and queries', 'set up alerting rules', 'define template variables', 'import/export JSON dashboards', 'connect to Prometheus/InfluxDB data sources'.

Include common synonyms and related terms users might mention, such as 'monitoring dashboard', '.json dashboard files', 'Prometheus queries', 'PromQL', or 'metrics visualization'.

Dimension	Reasoning	Score
Specificity	Names the domain (Grafana dashboards) and mentions 'create and manage' as actions, but these are generic verbs. No concrete actions like 'configure panels', 'set up alerts', 'define queries', or 'create variables' are mentioned. 'Production-ready' and 'comprehensive system observability' are buzzword-like qualifiers rather than specific capabilities.	2 / 5
Completeness	Has a vague 'what' (create and manage Grafana dashboards) but completely lacks a 'when' clause. There is no 'Use when...' guidance or equivalent trigger phrasing to help Claude know when to select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 3, and the 'what' is also quite vague, placing this at 2.	2 / 5
Trigger Term Quality	'Grafana' and 'dashboards' are strong natural trigger terms users would say. However, it's missing common related terms like 'monitoring', 'metrics', 'panels', 'Prometheus', 'alerts', 'visualization', or 'JSON dashboard'. 'System observability' is somewhat natural but more of a buzzword.	3 / 5
Distinctiveness Conflict Risk	'Grafana dashboards' is a fairly distinct niche that wouldn't easily overlap with most other skills. However, it could potentially conflict with general monitoring/observability skills or other dashboard tools (e.g., Datadog, Kibana). The mention of 'system observability' broadens the scope and slightly increases overlap risk.	4 / 5
	Total	11 / 20 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/grafana-dashboards/SKILL.md
Commit: 57c135b

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.