CtrlK
BlogDocsLog inGet started
Tessl Logo

dt-obs-tracing

Distributed traces, spans, service dependencies, and request flow analysis. Use when investigating span-level details, failures, performance bottlenecks, or trace correlation. Trigger: "trace analysis", "slow requests", "failed spans", "service dependencies", "distributed trace", "span details", "HTTP status codes in traces", "database query spans", "messaging spans", "gRPC calls", "Lambda cold starts", "trace ID lookup", "exception analysis", "correlate logs and traces", "request attributes". Do NOT use for explaining existing queries, product documentation or configuration questions, service-level RED metrics (use dt-obs-services), log searching (use dt-obs-logs), or problem analysis (use dt-obs-problems).

73

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 strong reference-style skill: executable DQL patterns throughout, excellent one-level-deep progressive disclosure, and useful Best Practices and Troubleshooting tables. The main improvement opportunities are trimming the duplicated References tail and making the query-validation loop explicit.

Suggestions

Drop the terminal References section (it duplicates the inline "Learn more" links) or keep only the inline links, saving ~15 lines of repeated content.

Add one explicit validation guideline to Best Practices, e.g., 'Exploration: run `fetch spans | limit 1` and verify field names before building aggregations' to turn the implicit check-then-aggregate loop into a stated feedback loop.

Merge the redundant extrapolation guidance (Core Concepts sampling section, span-type table footnote, and Best Practices row) into a single pointer to the sampling-extrapolation reference.

DimensionReasoningScore

Conciseness

Dense and token-efficient — nearly all content is Dynatrace-specific (Grail, DQL, Smartscape, sampling extrapolation) that Claude cannot be assumed to know. Not 5 because the final References section repeats the inline "Learn more" links verbatim and the Best Practices table restates tips already given inline; not 3 because padding is minor and localized.

4 / 5

Actionability

Every pattern is a complete, executable DQL query — root-span filtering, percentile summaries with error rates, toUid trace lookup, multiplicity extrapolation, exception flattening with exemplar traces — plus a concrete troubleshooting table. Copy-paste ready and covering the common cases.

5 / 5

Workflow Clarity

Use cases are structured Goal/Trigger/Done, "fetch spans | limit 1" acts as a validate-first exploration step, and the Best Practices/Troubleshooting tables serve as checkpoints and error recovery. Not 5 because there is no explicit iterate-loop (e.g., run a cheap limited query first, verify fields exist, then aggregate); not 3 because sequence and checkpoints are mostly present and the skill involves no destructive or batch operations.

4 / 5

Progressive Disclosure

Clean overview body with twelve referenced files that all exist, all exactly one level deep (no nested references verified), signaled both inline ("Learn more") and in a References index, with a span-type routing table mapping each span type to its reference.

5 / 5

Total

18

/

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.

An exemplary description: a clear what, an explicit Use-when clause with fifteen natural trigger phrases, and hard negative boundaries that disambiguate sibling skills. The only gap is that the capability statement is noun-heavy ("analysis") without naming the concrete action of writing DQL queries.

DimensionReasoningScore

Specificity

Names the domain and several specific capability areas ("investigating span-level details, failures, performance bottlenecks, or trace correlation", "service dependencies", "request flow analysis"), but the what is noun-heavy and never states the concrete action (writing/running DQL queries against trace data). Not 5 because the action list is not fully concrete; not 3 because coverage is broad, not 1-2 actions.

4 / 5

Completeness

Explicitly answers what ("Distributed traces, spans, service dependencies, and request flow analysis") and when with both a "Use when..." clause and a concrete Trigger list; not below 5 since neither part is missing or vague.

5 / 5

Trigger Term Quality

Fifteen quoted natural trigger phrases with good synonym coverage ("slow requests", "failed spans", "gRPC calls", "Lambda cold starts", "trace ID lookup", "correlate logs and traces") spanning all span types — phrases a user would naturally say when they need this skill.

5 / 5

Distinctiveness Conflict Risk

Clear niche (span-level distributed tracing) with an explicit "Do NOT use for..." clause redirecting to sibling skills (dt-obs-services, dt-obs-logs, dt-obs-problems), minimizing wrong-skill triggering.

5 / 5

Total

19

/

20

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 — 16 / 16 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.