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.

1.16x

Quality

—

Does it follow best practices?

Impact

85%

1.16x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A reference-rich skill with strong actionability via complete, executable code snippets across JSON, Terraform, and Ansible. Its weaknesses are conciseness (generic best-practice padding and a restated purpose), a missing sequenced workflow with validation checkpoints, and broken asset references.

Suggestions

Create the referenced files under assets/ (api-dashboard.json, infrastructure-dashboard.json, database-dashboard.json) or remove the broken 'See assets/...' references.

Move the full inline API dashboard JSON into assets/ and keep only a concise excerpt plus a one-level-deep reference, trimming the generic Best Practices list to non-obvious items only.

Add a short sequenced 'Build a dashboard' workflow with an explicit validation/check step (e.g. import and verify in Grafana) to raise workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete snippets, but repeats the description in 'Purpose'/'When to Use' and embeds large inline JSON plus a generic 10-item best-practices list (consistent naming, set units, test time ranges) much of which Claude already knows; it could be tightened, so it is 2 not 3.	2 / 3
Actionability	Provides fully executable, copy-paste-ready JSON/YAML/HCL examples with concrete PromQL expressions, Terraform and Ansible snippets, matching the score-3 anchor; it is not 2 because the code is complete rather than pseudocode.	3 / 3
Workflow Clarity	No sequenced procedure for assembling a dashboard and no validation checkpoints or feedback loops are given; the provisioning snippets are individual examples rather than a workflow, capping this at 2 per the missing-validation guideline.	2 / 3
Progressive Disclosure	Sections provide structure and the body points to assets/api-dashboard.json, assets/infrastructure-dashboard.json and assets/database-dashboard.json, but those assets/ files do not exist, so the references are broken and large content that should be separate remains inline; this is 2 rather than 3 (broken refs) but not 1 (sections are present).	2 / 3
	Total	9 / 12 Passed

Description

85%

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

A strong description that clearly states capabilities and includes an explicit 'Use when...' trigger clause, giving it high completeness and specificity. The main gap is trigger-term coverage, which lacks some of the most common natural phrasings a user would say.

Suggestions

Add the most common natural phrasings to the trigger clause (e.g. 'create a Grafana dashboard', 'add a panel', 'set up an alert', 'Grafana dashboard') so users' typical requests match.

Keep the description tight; avoid expanding it with metric-tooling jargon that users rarely say verbatim.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Create and manage production Grafana dashboards', 'real-time visualization of system and application metrics') rather than vague language, matching the score-3 anchor listing several specific actions.	3 / 3
Completeness	Explicitly answers both what ('Create and manage production Grafana dashboards...') and when via an explicit 'Use when...' clause, matching the score-3 anchor; it is not 2 because the when-guidance is explicit, not merely implied.	3 / 3
Trigger Term Quality	Includes relevant triggers ('building monitoring dashboards', 'visualizing metrics', 'observability interfaces') but omits common natural variations a user would say (e.g. 'Grafana dashboard', 'add a panel', 'set up an alert'), so it sits at score 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	The Grafana-dashboards niche is clearly bounded by its triggers and unlikely to fire for unrelated skills, matching the score-3 anchor; minor overlap with prometheus/slo skills is not enough to drop it to 2.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: wshobson/agents
Commit: d7cf7dc

Reviewed: 1 day 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.