dt-obs-problems
DAVIS problem analysis including root cause identification, impact assessment, and correlation with other telemetry. Use when querying or investigating detected problems. Trigger: "active problems", "root cause analysis", "problem impact", "affected users", "list problems", "P-12345 details", "recurring problems", "problem history", "problem trending", "blast radius", "which entity caused the problem", "problems affecting Kubernetes", "problems by service". Do NOT use for explaining existing queries, product documentation questions, generic log searching, distributed tracing, or host-level resource monitoring.
75
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
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 covers all key dimensions thoroughly. It provides specific capabilities, extensive natural trigger terms, clear 'Use when' guidance, and explicit exclusion boundaries via a 'Do NOT use' clause. The description is concise yet comprehensive, making it easy for Claude to correctly select this skill from a large pool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: root cause identification, impact assessment, correlation with other telemetry, querying detected problems, and investigating problems. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (DAVIS problem analysis including root cause identification, impact assessment, correlation) and 'when' (explicit 'Use when' clause plus extensive trigger terms). Also includes a 'Do NOT use' clause which further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'active problems', 'root cause analysis', 'problem impact', 'affected users', 'list problems', 'P-12345 details', 'recurring problems', 'blast radius', 'problems affecting Kubernetes', 'problems by service'. These are highly natural and varied. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around DAVIS problem analysis. The explicit 'Do NOT use' clause for related but different skills (log searching, distributed tracing, host-level monitoring) significantly reduces conflict risk with adjacent skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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, well-structured skill with excellent actionability through numerous executable DQL query patterns and a clear progressive disclosure strategy. The main weakness is moderate verbosity — the 'What are Problems?' explanatory section and some descriptive text could be trimmed since Claude doesn't need conceptual explanations of Dynatrace problems. The troubleshooting table, field name correction table, and disambiguation of cause category vs. root cause entity are particularly valuable additions.
Suggestions
Remove or significantly condense the 'What are Problems?' section — Claude doesn't need an explanation of what Dynatrace problems are; the actionable query patterns already demonstrate this implicitly.
Trim the 'Event Kinds' table unless it's directly used in problem queries — it appears informational rather than actionable for this skill's scope.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary explanatory content that Claude already knows (e.g., 'What are Problems?' section explaining what problems are, the Problem Lifecycle section). The field reference tables and query patterns are valuable, but the overall document could be tightened by ~20-30% without losing actionable content. | 2 / 3 |
Actionability | Excellent actionability with numerous copy-paste-ready DQL queries covering all major use cases. Every pattern includes executable code with correct field names, filters, and sorting. The common field name mistakes table and correct status values are highly actionable for avoiding errors. | 3 / 3 |
Workflow Clarity | Clear workflows for problem triage, root cause investigation, and trending analysis. The document provides explicit sequencing (start simple, test fields, add complexity), validation guidance (test with limit 1, filter early), and a troubleshooting table that serves as an error recovery reference. The 'Cause Category vs. Root Cause Entity' section clearly disambiguates two common confusion points. | 3 / 3 |
Progressive Disclosure | Well-structured with clear navigation. The main SKILL.md provides essential patterns inline while deferring advanced topics (trending, correlation, impact analysis, problem merging) to clearly referenced files. The 'When to Load References' section explicitly tells Claude when each reference file is needed, which is excellent progressive disclosure design. | 3 / 3 |
Total | 11 / 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.