CtrlK
BlogDocsLog inGet started
Tessl Logo

dt-obs-services

Service performance monitoring with RED metrics (Rate, Errors, Duration) and runtime-specific telemetry for Java, .NET, Node.js, Python, PHP, and Go. Use when analyzing service health, SLA compliance, or runtime issues. Trigger: "service response time", "error rate", "throughput", "SLA compliance", "service mesh overhead", "JVM GC", "Java heap", "Node.js event loop", ".NET CLR", "Python threads", "PHP OPcache", "Go goroutines", "service performance", "p95 latency", "request failures", "database response time by name". Do NOT use for explaining existing queries, product documentation questions, infrastructure metrics (use dt-obs-hosts), log analysis (use dt-obs-logs), or distributed tracing workflows (use dt-obs-tracing).

71

Quality

86%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

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 well-structured skill with strong actionability and excellent progressive disclosure. The DQL examples are concrete and executable, metric names are specific, and the agent instructions provide clear defaults and decision-making guidance. The main weaknesses are some verbosity in the use-case bullet lists and workflows that lack explicit validation checkpoints and error recovery loops.

Suggestions

Add validation/verification steps to the Common Workflows — e.g., after running a health check query, verify data is returned and handle the 'no data' case before proceeding to analysis.

Trim the 'Use Cases' bullet lists under each capability section, as many overlap with the intent-mapping table in Agent Instructions — keep only the most distinctive use cases inline.

DimensionReasoningScore

Conciseness

The skill is reasonably well-organized but includes some redundancy — the 'Use Cases' bullet lists under each capability section are somewhat verbose and overlap with the intent-mapping table in Agent Instructions. The 'When to Use This Skill' section largely duplicates the frontmatter description. However, most content earns its place with concrete metric names and query patterns.

2 / 3

Actionability

The skill provides executable DQL queries with real metric names, concrete default values (e.g., 1000ms threshold = 1,000,000 µs), unit conversion guidance, and specific tool invocation steps (create-dql → static-threshold-analyzer → get-entity-name). The quick examples are copy-paste ready and the agent instructions give a clear step-by-step workflow for threshold violation requests.

3 / 3

Workflow Clarity

Workflows are listed but most are high-level outlines without explicit validation checkpoints or error recovery steps. The 'Service Health Check' and 'SLA Monitoring' workflows are essentially checklists without feedback loops. The troubleshooting table partially compensates but isn't integrated into the workflows themselves. The threshold violation workflow in Agent Instructions is the strongest, with clear sequencing.

2 / 3

Progressive Disclosure

Excellent progressive disclosure structure — the main skill provides concise overviews with quick examples, then clearly signals one-level-deep references for detailed queries (service-metrics.md) and runtime-specific files (java.md, nodejs.md, etc.). Navigation is well-organized with a dedicated References section and inline links throughout. Each runtime section links directly to its reference file.

3 / 3

Total

10

/

12

Passed

Description

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 evaluation dimensions at the highest level. It provides specific capabilities, comprehensive trigger terms that users would naturally use, explicit 'Use when' and 'Do NOT use for' guidance, and clear boundaries with named alternative skills to minimize conflict risk.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions and domains: RED metrics (Rate, Errors, Duration), runtime-specific telemetry for six named languages, SLA compliance analysis, and service health monitoring. Very concrete and detailed.

3 / 3

Completeness

Clearly answers both 'what' (service performance monitoring with RED metrics and runtime-specific telemetry) and 'when' (explicit 'Use when' clause plus detailed trigger terms and explicit 'Do NOT use for' exclusions that further clarify scope).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms users would say: 'service response time', 'error rate', 'throughput', 'p95 latency', 'JVM GC', 'Node.js event loop', etc. These are terms practitioners naturally use when discussing service performance issues.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with explicit boundary-setting via 'Do NOT use for' clauses that redirect to specific alternative skills (dt-obs-hosts, dt-obs-logs, dt-obs-tracing). The focus on service-level RED metrics and runtime-specific telemetry creates a clear niche.

3 / 3

Total

12

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
Dynatrace/dynatrace-for-ai
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.