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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%Weight 40%Scale 1-5

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

A well-structured query-reference skill: executable DQL patterns throughout, clear use-case framing, correct-field guidance, and a genuinely useful troubleshooting table. Its weaknesses are redundancy (dedup and status-value guidance repeated three times) and slightly uneven reference signaling for the four bundle files.

Suggestions

Consolidate the duplicate "never use OPEN, use ACTIVE/CLOSED" and "always filter not(dt.davis.is_duplicate)" guidance into one place and let Best Practices/Troubleshooting reference it instead of restating it.

Add a load-when condition for problem-merging.md in the "When to Load References" section so all four bundle files are equally discoverable.

Trim the "Problem Trending" section's inline key-techniques summary, which previews content already covered in references/problem-trending.md, to a single pointer plus use-case triggers.

Dimension	Reasoning	Score
Conciseness	The body is dense with tables and executable DQL and avoids explaining generic concepts, but repeats the same guidance multiple times — the duplicate-filter rule and the "OPEN does not exist / use ACTIVE" warning each appear in Correct Status Values, Best Practices, and Troubleshooting, which could be consolidated.	4 / 5
Actionability	Every section provides copy-paste-ready DQL covering the common cases (active problems, blast radius, recurring root causes, K8s correlation), plus a wrong/right field-name table and a troubleshooting matrix — fully executable guidance with specific examples.	5 / 5
Workflow Clarity	Use Cases define Goal/Trigger/Done per workflow, a Standard Query Pattern anchors query construction, and "Test incrementally" / "Run with \| limit 1" give validation checkpoints with a troubleshooting table for recovery; it lacks an explicit numbered validate-then-retry sequence, keeping it just below the top anchor.	4 / 5
Progressive Disclosure	Four real, one-level-deep reference files are well signaled through the "When to Load References" section and the References list, but the trending pointer is stated twice and problem-merging.md is listed without a load-when condition — minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, concrete capability statement, an explicit Use-when clause with abundant natural trigger phrases, and a clear negative-scope clause that minimizes conflict with adjacent observability skills. The only minor gap is that some capabilities (trending, listing) are conveyed only through triggers rather than stated outright.

Dimension	Reasoning	Score
Specificity	"DAVIS problem analysis including root cause identification, impact assessment, and correlation with other telemetry" names the domain and several concrete actions, but capabilities like trending and problem listing are only implied through trigger phrases rather than stated, so it falls just short of comprehensive coverage.	4 / 5
Completeness	It explicitly answers both what ("root cause identification, impact assessment, and correlation with other telemetry") and when ("Use when querying or investigating detected problems" plus a concrete trigger list), matching the top anchor.	5 / 5
Trigger Term Quality	The trigger list ("active problems", "blast radius", "P-12345 details", "problems affecting Kubernetes", "problem history") comprehensively covers natural phrasings users would say, including synonyms and concrete ID examples.	5 / 5
Distinctiveness Conflict Risk	The DAVIS problem-analysis niche is distinct and the explicit "Do NOT use for ... generic log searching, distributed tracing, or host-level resource monitoring" clause cleanly demarcates it from the closely related skills it lists.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Dynatrace/dynatrace-for-ai
Path: skills/dt-obs-problems/SKILL.md
Commit: 47528b0

Reviewed: 6 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.