creating-apm-dashboards

Execute this skill enables AI assistant to create application performance monitoring (apm) dashboards. it is triggered when the user requests the creation of a new apm dashboard, monitoring dashboard, or a dashboard for application performance. the skill helps ... Use when generating or creating new content. Trigger with phrases like 'generate', 'create', or 'scaffold'.

Quality

31%

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 ./plugins/performance/apm-dashboard-creator/skills/creating-apm-dashboards/SKILL.md

Quality

Content

12%

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

The body is largely generic template content with placeholder sections and no executable guidance, and it fails to connect to the bundled scripts that do exist. The only structural merit is a present but abstract four-step workflow.

Suggestions

Remove or replace boilerplate sections (Output, Resources, Error Handling, Prerequisites) with APM-specific content, and link the actual bundled scripts (e.g., "Run `python scripts/create_grafana_dashboard.py --type json`").

Add concrete, copy-paste-ready guidance: example dashboard JSON panels for golden signals and the metric queries each platform expects.

Insert a validation checkpoint in the workflow (e.g., validate the generated config and confirm against the target platform before deploying).

Dimension	Reasoning	Score
Conciseness	The body is padded with template boilerplate ("The skill produces structured output relevant to the task.", "Project documentation", "Related skills and commands") and re-explains APM concepts Claude already knows, adding little value per token.	1 / 3
Actionability	No executable code, commands, or sample dashboard configs appear in the body; the examples only describe abstract steps ("Identify the need", "Define dashboard components") and the bundled generator scripts are never referenced or shown in use.	1 / 3
Workflow Clarity	The four "How It Works" steps provide a sequence, but they are abstract and lack validation checkpoints even though deploying a dashboard is an outward-facing operation that warrants verify-before-deploy feedback.	2 / 3
Progressive Disclosure	Real bundle files exist (scripts/create_grafana_dashboard.py, scripts/create_datadog_dashboard.py, references/README.md) but the body never links to them; the "Resources" section is placeholder text, leaving the bundle orphaned with no navigation.	1 / 3
	Total	5 / 12 Passed

Description

50%

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 APM-dashboard niche and includes explicit trigger guidance, but it is marred by malformed text ("the skill helps …") and generic creation-style boilerplate that dilutes specificity and trigger quality. It answers both what and when only adequately.

Suggestions

Rewrite the malformed opening ("Execute this skill enables AI assistant to create…") into clean third-person prose, e.g. "Creates Application Performance Monitoring (APM) dashboards for Grafana, Datadog, and New Relic."

Replace the generic "Use when generating or creating new content. Trigger with phrases like 'generate', 'create', or 'scaffold'" with APM-specific triggers a user would actually say, e.g. "Use when the user asks to create an APM, monitoring, or performance dashboard."

Add concrete actions beyond 'create' (e.g., define golden-signal panels, generate dashboard JSON configs) to raise specificity and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("create application performance monitoring (apm) dashboards") but lists no further specific actions, so it is not comprehensive.	2 / 3
Completeness	It states what the skill does and provides an explicit "it is triggered when…" clause, but the "Use when…" guidance is generic boilerplate and the sentence "the skill helps …" is malformed, leaving the when-portion weak rather than clearly tied to APM.	2 / 3
Trigger Term Quality	It includes some natural terms ("apm dashboard", "monitoring dashboard"), but the appended "Use when generating or creating new content. Trigger with phrases like 'generate', 'create', or 'scaffold'" is generic boilerplate unrelated to APM rather than genuine user phrasings.	2 / 3
Distinctiveness Conflict Risk	The APM-dashboard niche is reasonably distinct, yet the generic "generate", "create", "scaffold" triggers would cause overlap with many other skills, raising conflict risk.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/performance/apm-dashboard-creator/skills/creating-apm-dashboards/SKILL.md
Commit: 15940c5

Reviewed: 2 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.