CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/logql-generator

Generate label matchers, line filters, log aggregations, and metric queries in LogQL (Loki Query Language) following current standards and conventions. Use this skill when creating new LogQL queries, implementing log analysis dashboards, alerting rules, or troubleshooting with Loki.

71

Quality

89%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a well-sequenced, checkpointed workflow, but it is longer than necessary due to redundancy between Best Practices and Anti-Patterns, and its progressive-disclosure references could not be verified against actual bundle files. Tightening repetition and confirming the referenced files ship with the skill would lift the weakest dimensions.

Suggestions

Consolidate the duplicated guidance between the "Best Practices" section and the "Anti-Patterns" section (filter order, parser performance order) into one location and cross-reference it, to remove redundancy and recover token budget.

Verify and ship the referenced bundle files (assets/common_queries.logql, references/best_practices.md, references/function_reference.md); if any are not bundled, either inline the essential content or remove the dangling references so progressive disclosure resolves to real files.

Trim overlapping query examples across "Core Query Patterns", "Advanced Techniques", and "Stage 5" so each pattern appears once, keeping the body lean while detailed variants live in common_queries.logql.

DimensionReasoningScore

Conciseness

The body is mostly high-signal LogQL/Loki detail, but ~340 lines with redundancy — "Best Practices" (filter order, parser performance) is restated as "Anti-Patterns" and core patterns overlap "Advanced Techniques" — so it could be tightened rather than earning the lean score-3.

2 / 3

Actionability

It provides abundant copy-paste-ready, executable LogQL examples (filtering, json/logfmt/pattern parsing, metrics, alerting, formatting), matching the fully-executable score-3 anchor.

3 / 3

Workflow Clarity

The 6-stage workflow is clearly sequenced with checkpoints — Stage 4 plan confirmation via AskUserQuestion, Stage 5a "Test this first to confirm logs are flowing", and an Error Handling recovery table — satisfying the explicit-validation anchor.

3 / 3

Progressive Disclosure

Navigation/signaling is well designed (a complexity-to-file table, external-doc triggers, one-level-deep references), but the referenced bundle files (assets/common_queries.logql, references/best_practices.md, references/function_reference.md) are not present to verify, so the promised split is unconfirmed rather than clearly delivered.

2 / 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.

The description is strong across all dimensions: it lists concrete capabilities, includes natural trigger terms, gives an explicit Use-when clause, and occupies a clear non-conflicting niche. No changes needed.

DimensionReasoningScore

Specificity

"Generate label matchers, line filters, log aggregations, and metric queries" enumerates multiple concrete actions, matching the score-3 anchor; it is not merely a domain-plus-some-actions (score 2) formulation.

3 / 3

Completeness

It explicitly answers both what ("Generate ... in LogQL") and when ("Use this skill when creating new LogQL queries ..."), mirroring the score-3 example with an explicit Use-when clause.

3 / 3

Trigger Term Quality

Natural user-facing terms are well covered — "LogQL queries", "log analysis dashboards", "alerting rules", and "troubleshooting with Loki" are phrases a user would actually say, satisfying the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

The LogQL/Loki query-generation niche is specific and the triggers are distinct, making it unlikely to fire for an unrelated skill.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

referenced_paths_exist

Referenced path issues: 11 missing

Warning

Total

14

/

16

Passed

Reviewed

Table of Contents