CtrlK
BlogDocsLog inGet started
Tessl Logo

dt-obs-logs

Log querying, filtering, pattern analysis, and error rate calculation. Use when searching application or infrastructure logs, analyzing error patterns, or correlating log data. Trigger: "show error logs", "search logs for keyword", "log error rate", "recent errors", "logs from last hour", "find log entries", "top error messages", "log patterns", "parse JSON logs", "logs by process group", "log trends over time", "log entry counts per minute". Do NOT use for explaining existing queries, product documentation questions, distributed tracing or span analysis (use dt-obs-tracing).

68

Quality

83%

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

71%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.

The body is highly actionable — every workflow ships executable DQL that a user can run verbatim — and the troubleshooting table adds real recovery value. Its weaknesses are token efficiency and organization: four overlapping overview sections and an inlined function reference pad the file instead of being consolidated or moved to a references bundle.

Suggestions

Collapse "What This Skill Covers", "Use Cases", "Common Operations", and "Integration Points" into one concise capability overview; they repeat the same list four times.

Move the "Key Functions" catalog and duplicate "Common Patterns" examples into a references/ file (e.g., references/dql-functions.md), keeping only the top 5-6 patterns inline in SKILL.md.

Add a lightweight validation step to each core workflow (e.g., confirm non-empty results before aggregating, or verify log ingestion when a query returns nothing) to lift workflow clarity.

DimensionReasoningScore

Conciseness

The DQL examples are lean and information-dense, but four overview sections — "What This Skill Covers", "Use Cases", "Common Operations", and "Integration Points" — restate the same capability list in slightly different words, and "Best Practices" repeats notes already attached inline. It is mostly efficient but could be tightened by collapsing the redundant lists, which is anchor 3 rather than anchor 2 (no concept explanations Claude already knows).

3 / 5

Actionability

Every section provides complete, copy-paste-ready DQL queries — search, multi-criteria filtering, pattern analysis, error rate over time buckets, top errors, process-group filtering, and JSON parsing with follow-up notes on parse ordering. The examples cover the common cases comprehensively, matching anchor 5.

5 / 5

Workflow Clarity

The three core workflows each list a sequenced 4-5 step procedure with a full example, and the troubleshooting table provides problem/cause/solution recovery guidance. It falls short of anchor 5 because the workflows lack explicit validation checkpoints (e.g., verifying log ingestion or result sanity), but read-only queries make the missing-validation cap inapplicable.

4 / 5

Progressive Disclosure

The file is well-sectioned with clear headers, but it is a ~250-line monolith: the "Key Functions" section is an inlined API reference and "Common Patterns" duplicates the workflow examples — content that belongs in a references file. No bundle files exist to offload it into, so structure is present but content that should be separate is inline (anchor 3), not the well-split structure of anchor 4.

3 / 5

Total

15

/

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 voice, concrete capabilities, an explicit use-when clause with a dozen natural trigger phrases, and a do-not-use boundary that routes adjacent requests to the right sibling skill. The only improvement space is folding the remaining capabilities (aggregation, JSON parsing) into the opening capability sentence.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "Log querying, filtering, pattern analysis, and error rate calculation" — naming the domain and specific capabilities, but minor coverage gaps remain (aggregation/grouping and JSON parsing appear only in trigger phrases, not the capability sentence). It sits above anchor 3 (only 1-2 actions) and below anchor 5 (comprehensive action list).

4 / 5

Completeness

It explicitly answers both questions: what ("Log querying, filtering, pattern analysis, and error rate calculation") and when ("Use when searching application or infrastructure logs, analyzing error patterns, or correlating log data" plus concrete trigger phrases and a "Do NOT use" exclusion). This matches the anchor 5 example structure exactly.

5 / 5

Trigger Term Quality

Twelve natural phrases users would actually say — "show error logs", "log error rate", "recent errors", "logs from last hour", "top error messages", "parse JSON logs" — give comprehensive coverage including synonyms and variations. This matches the anchor 5 example's breadth; file extensions are not applicable to log queries.

5 / 5

Distinctiveness Conflict Risk

The log-analysis niche is clearly distinct, and the explicit boundary "Do NOT use for ... distributed tracing or span analysis (use dt-obs-tracing)" minimizes conflict risk with sibling observability skills. Only trivial overlap exists with dt-dql-essentials, which is a syntax companion rather than a competitor.

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.