dt-app-dashboards
Work with Dynatrace dashboards - create, modify, query, and analyze dashboard JSON including tiles, layouts, DQL queries, variables, and visualizations. Supports dashboard creation, updates, data extraction, structure analysis, and best practices.
60
70%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/dt-app-dashboards/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description with excellent specificity and domain-specific trigger terms that clearly identify the Dynatrace dashboard niche. Its main weakness is the lack of an explicit 'Use when...' clause, which means Claude must infer when to select this skill rather than having clear trigger guidance. Adding explicit trigger conditions would elevate this from good to excellent.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Dynatrace dashboards, dashboard JSON configuration, DQL queries, or dashboard tiles and layouts.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: create, modify, query, analyze dashboard JSON, and further specifies sub-elements like tiles, layouts, DQL queries, variables, and visualizations. Also mentions creation, updates, data extraction, structure analysis, and best practices. | 3 / 3 |
Completeness | The 'what' is well-covered with specific actions and components, but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. The 'when' is only implied by the domain terms. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Dynatrace', 'dashboards', 'dashboard JSON', 'tiles', 'layouts', 'DQL queries', 'variables', 'visualizations'. These are terms a Dynatrace user would naturally use when requesting help. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific 'Dynatrace dashboards' domain and specialized terms like 'DQL queries', 'tiles', and 'dashboard JSON'. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that excels at progressive disclosure and provides a solid overview of Dynatrace dashboard operations. Its main weaknesses are that most actionable, executable content is deferred to reference files (which weren't provided for evaluation), and the SKILL.md itself is somewhat meta/verbose in explaining its own loading strategy. The mandatory workflow is clearly sequenced but would benefit from explicit error-recovery loops.
Suggestions
Add a complete, minimal end-to-end example in SKILL.md (e.g., a small dashboard JSON with one tile, one layout entry, and the dtctl commands to validate and deploy it) to improve actionability without requiring reference file loading.
Add an explicit feedback loop to the validation section: 'If validation fails → identify error → fix → re-validate → only deploy when all checks pass' to strengthen workflow clarity.
Trim the 'When to Load References' section—the loading strategy explanation is meta-commentary that Claude doesn't need; the reference table at the bottom already serves this purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary framing (e.g., explaining what progressive disclosure is, the 'Tip' callout about reference files, and the 'When to Load References' section is somewhat meta). The overview section explaining what dashboards contain is borderline—Claude likely knows JSON structure concepts—but the Dynatrace-specific details earn their place. | 2 / 3 |
Actionability | Provides concrete JSON structure examples and jq path references, plus a specific validation command (`dtctl query "<DQL>" --plain`). However, most actionable detail is deferred to reference files. The SKILL.md itself lacks executable end-to-end examples—the JSON snippets are structural templates rather than copy-paste-ready workflows. | 2 / 3 |
Workflow Clarity | The 7-step mandatory creation/modification workflow is clearly sequenced and includes validation steps (steps 4, 6). However, the validation section lacks explicit error-recovery feedback loops (validate → fix → re-validate), and the full workflow details are deferred to reference files. The analyzing and querying workflows are barely outlined. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: SKILL.md serves as a clear overview with well-signaled one-level-deep references via a summary table and inline arrows (→). Each reference file is mapped to a specific use case. Content is appropriately split between overview and deep-dive topics. | 3 / 3 |
Total | 9 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Dynatrace/dynatrace-for-ai
- Commit
4991356
- 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.