CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

56

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/observability-monitoring/skills/grafana-dashboards/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

51%Weight 40%Scale 1-5

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

The body is a well-organized, code-rich reference with strong executable examples, but it reads as a topic catalog rather than an operational skill. It lacks any sequenced build/validate/deploy workflow with checkpoints, keeps knowledge Claude already has inline, and buries ~370 lines of reference detail in SKILL.md instead of splitting it into bundle files.

Suggestions

Add a numbered workflow with validation checkpoints, e.g. 1) define data source and variables, 2) build panels from the RED/USE patterns, 3) validate the dashboard JSON (against schema or via grafana CLI import) and fix errors, 4) only then provision/deploy.

Move the panel-type catalog, variables, alerting, and provisioning/Terraform reference into references/ files (e.g. references/panel-types.md, references/provisioning.md) and keep only a quick-start example in SKILL.md.

Trim duplicated framing ('Purpose', 'When to Use' repeating the description) and the RED/USE concept explanations, keeping only how to apply them to panel layout.

DimensionReasoningScore

Conciseness

The body is mostly lean, example-driven code, but "Purpose" and "When to Use" duplicate the title and description, and the RED/USE method explanations restate monitoring concepts Claude already knows. It is mostly efficient with some unnecessary explanation, below the 'minor instances of over-explanation' anchor.

3 / 5

Actionability

It provides extensive executable JSON dashboards, PromQL expressions, provisioning YAML, and Terraform/Ansible blocks. However, the panel-type snippets are fragments (missing gridPos/datasource, needing assembly) and the 'Key Panels' pattern sections are bullet lists without code, so it sits at 'mostly executable with minor gaps' rather than fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

There is no sequenced process for designing, building, validating, and deploying a dashboard; content is organized as a topic reference rather than a workflow. Validation is entirely absent for what is effectively a batch deploy operation (dashboards pushed to production Grafana), matching the 'rough sequence present but many gaps; validation absent' anchor and the feedback-loops cap.

2 / 5

Progressive Disclosure

Sections are clearly headed and navigable, but ~370 lines of separable reference material (panel-type catalog, variables, provisioning, dashboard-as-code, pattern lists) are all inlined with no references/ or scripts/ files at all. This matches 'content that should be separate is inline' with some structure, below the 'most content appropriately placed' anchor.

3 / 5

Total

12

/

20

Passed

Description

78%Weight 40%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.

A strong description that clearly states what the skill does and when to use it, with a well-formed 'Use when...' trigger clause. Its main gaps are limited action specificity (only 'create and manage') and a few missing natural synonyms users might say.

Suggestions

Name 2-3 more concrete capabilities in the description, e.g. 'build panels, templated variables, and alert rules; provision dashboards via file-based config or Terraform'.

Add a few natural trigger synonyms users actually say, such as 'Grafana dashboard', 'Prometheus metrics', or 'SLO/observability monitoring'.

DimensionReasoningScore

Specificity

"Create and manage production Grafana dashboards" names the domain with exactly two concrete actions, matching the anchor for 1-2 concrete actions that are not comprehensive. It does not list finer-grained capabilities (panels, variables, alerting, provisioning), so it falls below the 'several specific actions' anchor.

3 / 5

Completeness

It explicitly 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 concrete trigger phrases. The when-clause is explicit and specific, matching the top anchor rather than the 'could be more explicit' anchor at 4.

5 / 5

Trigger Term Quality

Natural phrases like "building monitoring dashboards", "visualizing metrics", and "operational observability interfaces" give good coverage of what users would say. A few natural terms are missing (e.g. "Grafana dashboard", "Prometheus", "SLO", "metrics dashboard"), keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

Grafana dashboards is a clear niche with distinct triggers, but "visualizing metrics" and "observability interfaces" have minor overlap risk with adjacent monitoring/visualization skills. It is not fully at the clear-niche/minimal-conflict anchor because those phrases are somewhat broad.

4 / 5

Total

16

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

wshobson/agents

Path

plugins/observability-monitoring/skills/grafana-dashboards/SKILL.md

Revision

0874a27

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill