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
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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 key dimensions thoroughly. It provides specific capabilities, extensive natural trigger terms, clear 'what' and 'when' guidance, and explicit exclusion boundaries to prevent conflicts with related skills. The 'Do NOT use' clause with a redirect to the tracing skill is a particularly strong disambiguation practice.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'log querying, filtering, pattern analysis, and error rate calculation.' These are distinct, actionable capabilities rather than vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (log querying, filtering, pattern analysis, error rate calculation) and 'when' (searching application/infrastructure logs, analyzing error patterns, correlating log data) with explicit trigger phrases and even a 'Do NOT use' exclusion clause for disambiguation. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: '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', etc. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to log-specific operations with explicit boundary-setting via the 'Do NOT use' clause that distinguishes it from tracing/span analysis and documentation skills. The mention of 'dt-obs-tracing' as an alternative further reduces conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent executable DQL examples covering a wide range of log analysis scenarios. Its main weaknesses are verbosity (redundant sections like 'What This Skill Covers', 'Use Cases', 'Key Concepts', and 'Integration Points' that overlap significantly) and a monolithic structure that could benefit from splitting detailed references into separate files. The workflows lack explicit validation/verification steps.
Suggestions
Remove or consolidate redundant sections: merge 'What This Skill Covers', 'Use Cases', and 'Key Concepts' into a single concise overview, eliminating duplication with the examples that follow.
Add validation checkpoints to workflows, e.g., 'If no results returned, widen time range or verify log ingestion before adding more filters.'
Extract the 'Key Functions' reference and 'Common Patterns' examples into separate bundle files (e.g., references/functions.md, references/patterns.md) and link from the main skill to improve progressive disclosure.
Remove the 'Integration Points' section entirely — it restates capabilities already demonstrated in the examples without adding new information.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary sections like 'What This Skill Covers' (duplicated by 'Use Cases'), 'Integration Points' (restates what's already shown in examples), and 'Key Concepts' which largely repeats information from the examples and function reference. The 'Use Cases' section explains when to use the skill, which is already covered by the frontmatter description. However, the core examples and function references are reasonably tight. | 2 / 3 |
Actionability | The skill provides fully executable DQL queries for every use case — log searching, filtering, pattern analysis, error rate calculation, JSON parsing, and more. Each example is copy-paste ready with realistic field names and syntax. The troubleshooting table provides concrete solutions to specific problems. | 3 / 3 |
Workflow Clarity | The workflows list steps clearly (define time range, filter, aggregate, sort), but there are no validation checkpoints or feedback loops. For log queries that could return no results or unexpected data, there's no guidance on verifying results or iterating. The troubleshooting table partially compensates but isn't integrated into the workflow steps themselves. | 2 / 3 |
Progressive Disclosure | The content is a monolithic file with no bundle files to reference. At ~200+ lines, sections like the full function reference, all common patterns, and the troubleshooting table could be split into separate reference files. The one cross-reference to 'dt-dql-essentials/references/smartscape-topology-navigation.md' is well-signaled, but the skill would benefit from offloading detailed pattern examples and the function reference to separate files. | 2 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
7cbe1ef
Table of Contents
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.