dt-dql-essentials
Core DQL syntax rules, common pitfalls, and query patterns. Load this skill when you need to write, build, or fix a DQL query — it prevents syntax errors and guides correct usage. Covers fetch commands, data models, field namespaces, time alignment, entity patterns, metric discovery, and smartscape topology navigation. Trigger: "write a DQL query", "build me a query", "DQL syntax", "how do I query logs/spans/metrics in Dynatrace", "create a timeseries", "fix my DQL", "fetch logs", "smartscapeNodes", "query optimization". Do NOT use for explaining an existing query or answering Dynatrace product questions — those do not require query-construction guidance.
90
86%
Does it follow best practices?
Impact
94%
1.59xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that hits all the key criteria. It provides specific capabilities, comprehensive trigger terms matching natural user language, explicit 'when to use' and 'when not to use' guidance, and clear domain boundaries that minimize conflict with other skills. The description is well-structured and concise without unnecessary padding.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and concepts: fetch commands, data models, field namespaces, time alignment, entity patterns, metric discovery, smartscape topology navigation, and explicitly mentions writing, building, and fixing DQL queries. | 3 / 3 |
Completeness | Clearly answers both 'what' (core DQL syntax rules, common pitfalls, query patterns covering fetch commands, data models, etc.) and 'when' (explicit 'Load this skill when...' clause plus a detailed Trigger list and a 'Do NOT use for' exclusion clause). This is comprehensive. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'write a DQL query', 'build me a query', 'DQL syntax', 'fetch logs', 'fix my DQL', 'create a timeseries', plus domain-specific terms like 'smartscapeNodes' and 'query optimization'. These closely match how users would naturally phrase requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (DQL query construction in Dynatrace) and explicit boundary-setting via the 'Do NOT use for' clause that distinguishes it from query explanation or general Dynatrace product knowledge skills. Domain-specific terms like 'smartscapeNodes', 'DQL', and 'Dynatrace' make conflicts unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, comprehensive DQL reference skill with excellent actionability through concrete code examples and an outstanding syntax pitfalls table. The progressive disclosure is well-structured with clear routing to reference files. Main weaknesses are the duplicated makeTimeseries section, the very large inline DQL Reference Index that could be a separate file, and the lack of explicit validation/verification steps in multi-step patterns.
Suggestions
Remove the duplicate makeTimeseries section — the content appears twice with slightly different code examples (one uses curly braces around aggregations, one doesn't). Merge into a single section showing both syntaxes.
Consider moving the large DQL Reference Index table to a separate reference file (e.g., references/dql-function-index.md) and linking to it, to reduce the inline token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with well-structured tables and code examples, but there is some redundancy — the makeTimeseries section appears twice with slightly different content, and some explanations could be tighter. The DQL Reference Index table is extremely long and could arguably be a separate reference file rather than inline. | 2 / 3 |
Actionability | The skill provides highly concrete, executable DQL snippets throughout — from fetch commands to timeseries queries, lookup patterns, metric discovery, and sampling. The syntax pitfalls table with wrong vs. right examples is exceptionally actionable and copy-paste ready. | 3 / 3 |
Workflow Clarity | The skill covers many individual patterns clearly but lacks explicit multi-step workflow sequences with validation checkpoints. For example, the chained lookup pattern shows steps but doesn't include verification steps. The 'When to Load References' table provides good routing but the overall document reads more as a reference than a guided workflow. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear reference routing table at the top, well-signaled one-level-deep references throughout (semantic-dictionary, optimization, summarization, iterative-expressions, operators, smartscape-topology-navigation, and detailed DQL spec files), and the main content serves as a concise overview pointing to deeper materials. | 3 / 3 |
Total | 10 / 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
7cbe1ef
- 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.