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

21%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/performance/apm-dashboard-creator/skills/creating-apm-dashboards/SKILL.md

Quality

Discovery

42%

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 (APM dashboards) but is undermined by an incomplete sentence ('the skill helps ...'), overly generic trigger conditions that would conflict with many other skills, and a lack of specific concrete actions. The mix of APM-specific language with broad 'create new content' triggers creates a contradictory and unreliable selection signal.

Suggestions

Remove the overly generic 'Use when generating or creating new content' clause and replace it with APM-specific triggers, e.g., 'Use when the user asks to create an APM dashboard, monitoring dashboard, or performance metrics visualization.'

Complete the truncated 'the skill helps ...' section with specific concrete actions such as 'configures metric panels, sets up alert thresholds, defines service-level indicators, and arranges dashboard layouts.'

Fix the voice: remove 'Execute this skill enables AI assistant to' and use third person like 'Creates application performance monitoring (APM) dashboards with...'

Dimension	Reasoning	Score
Specificity	It names the domain (APM dashboards) and the general action (create/generate), but lacks specific concrete actions like 'configure metrics panels, set alert thresholds, define SLI/SLO widgets'. The phrase 'the skill helps ...' is literally incomplete with an ellipsis.	2 / 3
Completeness	It addresses both 'what' (create APM dashboards) and 'when' (trigger phrases like 'generate', 'create', 'scaffold'), but the 'what' is incomplete (literal ellipsis 'the skill helps ...') and the 'when' clause is overly generic ('generating or creating new content') which doesn't specifically tie to APM dashboards.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'apm dashboard', 'monitoring dashboard', 'application performance', 'generate', 'create', 'scaffold', but misses natural variations users might say such as 'observability', 'metrics dashboard', 'Grafana', 'Datadog', or specific APM tool names.	2 / 3
Distinctiveness Conflict Risk	The generic trigger 'Use when generating or creating new content' with phrases like 'generate', 'create', or 'scaffold' would conflict with virtually any content-creation skill. The APM-specific portion is undermined by this overly broad trigger clause.	1 / 3
	Total	7 / 12 Passed

Implementation

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

This skill is almost entirely generic boilerplate with no actionable content. It lacks any concrete dashboard configurations, executable code, specific metric queries, or real examples. Every section reads like a template placeholder that was never filled in with actual implementation details.

Suggestions

Add concrete, copy-paste-ready dashboard configuration examples (e.g., Grafana JSON with actual panel definitions, PromQL queries for golden signals, Datadog dashboard JSON with specific widget configurations).

Remove all generic boilerplate sections (Prerequisites, Instructions, Output, Error Handling, Resources) that contain no specific information, and replace with actual metric query examples for each supported platform.

Include specific PromQL/Datadog/NRQL query examples for common golden signal metrics (e.g., `rate(http_requests_total[5m])` for traffic, `histogram_quantile(0.99, rate(http_request_duration_seconds_bucket[5m]))` for latency).

Add a validation step showing how to verify the generated dashboard configuration is valid before deploying (e.g., Grafana API validation endpoint, JSON schema validation).

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive filler content. Sections like 'Overview', 'How It Works', 'When to Use This Skill', 'Integration', 'Prerequisites', 'Instructions', 'Output', 'Error Handling', and 'Resources' are all generic boilerplate that provide no actionable information Claude doesn't already know. The entire file reads like a template with placeholders never filled in.	1 / 3
Actionability	There is zero executable code, no concrete dashboard JSON/YAML configurations, no specific metric queries (PromQL, Datadog queries, NRQL), and no actual commands. The examples describe what the skill 'will do' in abstract terms without showing any actual output or configuration. Instructions like 'Invoke this skill when the trigger conditions are met' are completely vacuous.	1 / 3
Workflow Clarity	The 'How It Works' steps are abstract descriptions ('Identify Requirements', 'Define Dashboard Components', 'Generate Configuration', 'Deploy Dashboard') with no concrete details, no validation checkpoints, and no error recovery. The 'Instructions' section is a generic 4-step placeholder that could apply to literally any skill.	1 / 3
Progressive Disclosure	The content is a monolithic wall of generic text with no references to external files, no linked resources, and no meaningful structure. The 'Resources' section just says 'Project documentation' and 'Related skills and commands' without any actual links. Content that should contain detailed platform-specific configurations is entirely absent.	1 / 3
	Total	4 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: c8a915c

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.