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'.
35
21%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/performance/apm-dashboard-creator/skills/creating-apm-dashboards/SKILL.mdQuality
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 undermines itself with an incomplete sentence ('the skill helps ...'), overly generic trigger guidance that would conflict with many other skills, and a lack of specific concrete actions. The contradiction between the APM-specific first half and the generic 'creating new content' second half creates significant conflict risk.
Suggestions
Remove the generic 'Use when generating or creating new content' clause and replace with APM-specific triggers like 'Use when the user asks to create an APM dashboard, monitoring dashboard, observability panel, or performance metrics visualization.'
Complete the truncated 'the skill helps ...' section with specific actions such as 'configures metric panels, sets up alert thresholds, defines SLI/SLO widgets, and arranges dashboard layouts.'
Remove the imperative 'Execute this skill' phrasing and rewrite in third person (e.g., 'Creates application performance monitoring 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 undermines the specificity of the APM focus. | 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', 'Datadog', 'Grafana', 'New Relic', or 'performance monitoring'. | 2 / 3 |
Distinctiveness Conflict Risk | The generic trigger clause 'Use when generating or creating new content' with triggers like 'generate', 'create', or 'scaffold' would conflict with virtually any content-creation skill. This severely undermines the APM-specific niche established earlier in the description. | 1 / 3 |
Total | 7 / 12 Passed |
Implementation
0%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 claims to generate APM dashboards for Grafana, Datadog, and New Relic but provides zero actual dashboard configurations, JSON/YAML templates, metric queries, or platform-specific instructions. Every section reads like a placeholder that was never filled in with real content.
Suggestions
Add concrete, executable dashboard configuration examples (e.g., actual Grafana JSON dashboard definition with golden signals panels, Datadog dashboard YAML with specific metric queries)
Remove all generic boilerplate sections (Prerequisites, Instructions, Output, Error Handling, Resources, Integration) that contain no skill-specific information
Include specific metric names and queries for each platform (e.g., Prometheus queries for Grafana like 'rate(http_requests_total[5m])', Datadog metric paths like 'trace.servlet.request.hits')
Add a concrete workflow with validation steps, such as how to validate the generated JSON against Grafana's API or how to test-import a dashboard before deploying
| 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. The skill explains obvious concepts and repeats itself across sections. | 1 / 3 |
Actionability | No concrete code, commands, configuration snippets, or executable examples anywhere. The 'examples' describe what the skill 'will do' in abstract terms but never show actual dashboard JSON/YAML configurations for Grafana, Datadog, or New Relic. Instructions like 'Invoke this skill when the trigger conditions are met' and 'Provide necessary context and parameters' are completely vague. | 1 / 3 |
Workflow Clarity | The 'How It Works' steps are abstract descriptions ('Identify Requirements', 'Define Dashboard Components', 'Generate Configuration', 'Deploy Dashboard') with no concrete commands, validation checkpoints, or error recovery loops. The 'Instructions' section is four generic steps that could apply to literally any skill. | 1 / 3 |
Progressive Disclosure | No bundle files exist, yet the skill is a monolithic wall of generic text with no meaningful structure. References to 'Project documentation' and 'Related skills and commands' are vague pointers to nothing. Content that should contain actual dashboard templates or platform-specific configuration guides is entirely absent. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%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 | |
- Commit
3a2d27d
- Reviewed
Table of Contents
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.