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

85%

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

75%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 highly actionable, well-structured domain reference with executable DQL throughout and clear reference signaling. Its main weakness is conciseness: core filters and patterns are repeated across sections, inflating the token budget without adding guidance value.

Suggestions

Consolidate the repeated deduplication/ACTIVE-status boilerplate: state the standard filter once in the Standard Query Pattern and reference it (or use a shared snippet) instead of restating it in every Common Query and Root Cause example.

Trim the "What are Problems?" overview and Problem Categories prose to the minimum domain context Claude needs, leaning on the tables and query examples that already carry the information.

Consider moving the longer Root Cause Analysis Patterns (blast radius, recurring root causes, cause-category breakdown) into a reference file, keeping only the Basic Root Cause Query inline to reduce SKILL.md length.

Dimension	Reasoning	Score
Conciseness	Mostly actionable but noticeably redundant: the deduplication filter (`not(dt.davis.is_duplicate)`) and ACTIVE-status pattern are re-explained across the Standard Query Pattern, Common Query Patterns, and multiple Root Cause sections, and the "What are Problems?" section restates domain basics; could be tightened without losing clarity, so it sits at the mostly-efficient anchor rather than 4.	3 / 5
Actionability	Provides many copy-paste-ready, executable DQL queries covering the common cases (active triage, high-impact, blast radius, recurring root causes, Kubernetes correlation), plus a concrete field-name mistake table and troubleshooting fixes — fully executable guidance.	5 / 5
Workflow Clarity	Clear sequenced guidance via the Standard Query Pattern foundation, numbered Essential Rules, Query Development steps, and incremental validation checkpoints ("Test fields first: Run with \| limit 1"); not a 5 because the use-case sections are pattern catalogs rather than a single tightly sequenced workflow with explicit error-recovery loops.	4 / 5
Progressive Disclosure	Good structure with a dedicated "When to Load References" section and a one-level-deep reference list (problem-trending, problem-correlation, impact-analysis, problem-merging — all verified present); not a 5 because the inlined Root Cause Analysis Patterns section is lengthy and could itself be partly offloaded to a reference file.	4 / 5
	Total	16 / 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, third-person description with concrete capabilities, an extensive natural trigger list, and explicit negative boundaries. It cleanly answers both what and when and is well-differentiated from related telemetry skills.

Dimension	Reasoning	Score
Specificity	Names the DAVIS problem domain and three concrete actions ("root cause identification, impact assessment, and correlation with other telemetry"), matching the anchor that lists several specific actions with minor coverage gaps; not a 5 because the action set is fairly narrow for a triage/investigation skill.	4 / 5
Completeness	Explicitly answers both what ("DAVIS problem analysis including root cause identification, impact assessment, and correlation") and when ("Use when querying or investigating detected problems. Trigger: ...") with concrete trigger phrases, plus a "Do NOT use for" exclusion list.	5 / 5
Trigger Term Quality	Comprehensive natural-language trigger list ("active problems", "root cause analysis", "problem impact", "affected users", "P-12345 details", "recurring problems", "blast radius", "problems affecting Kubernetes") covers synonyms and concrete phrasings a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (DAVIS problem analysis) with distinct triggers and an explicit negative-boundary list ("Do NOT use for ... generic log searching, distributed tracing, or host-level resource monitoring") that minimizes conflict with sibling observability skills.	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: 3287f9d

Reviewed: 5 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.