CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

81%

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

75%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 highly actionable skill whose executable LogQL patterns, BAD/GOOD anti-pattern pairs, and staged planning workflow give Claude exactly what to produce. The main costs are token redundancy — repeated best-practice statements, a recap Guidelines section, and inline function/Loki-3.x details that duplicate the reference files — and a missing final 'verify the query actually runs' step in the workflow.

Suggestions

Collapse the duplication between Stage 5 'Best Practices', the 'Anti-Patterns' section, and the closing 'Guidelines' section into one authoritative location (the Anti-Patterns BAD/GOOD pairs already carry the same guidance).

Add an explicit Stage 6 validation step, e.g. 'Run the final query via logcli or a Grafana explore panel over a narrow time range and confirm non-empty results before delivering' — this also pairs with the existing Error Handling table for the fix-retry loop.

Trim the 'Function and Parser Quick Reference' section to a two-line pointer to references/function_reference.md, and move the Loki 3.x feature details (structured metadata, bloom filters, approx_topk) into references/best_practices.md sections 35-37, which already cover them.

DimensionReasoningScore

Conciseness

The body is mostly tight, query-dense material, but there is real slack: Stage 5a's five-step incremental template is long, the 'Guidelines' section restates the stages above it, the 'Anti-Patterns' section repeats the Stage 5 'Best Practices' (filter ordering, parser choice), and the 'Function and Parser Quick Reference' duplicates content already in references/function_reference.md. This fits anchor 3 — mostly efficient but includes unnecessary explanation that could be tightened — rather than anchor 4, where only minor trimming would be needed.

3 / 5

Actionability

Nearly every section delivers copy-paste-ready LogQL: concrete pipelines ('{job="app", namespace="prod"} |= "error" | json | level="error"'), metric recipes (rate, topk, quantile_over_time, error-percentage ratio), and paired BAD/GOOD examples for each anti-pattern. Examples cover the common cases (filtering, parsing, metrics, alerting, formatting) exactly as the anchor-5 example does.

5 / 5

Workflow Clarity

The workflow is clearly sequenced (Stages 1-6) with user-confirmation checkpoints via AskUserQuestion and incremental test-first steps ('Test this first to confirm logs are flowing', error-handling table with fixes). It falls short of anchor 5 because there is no explicit post-generation validation step — nothing instructs running the final query via logcli/Grafana to verify it returns data before handing it off.

4 / 5

Progressive Disclosure

Structure is good and all three referenced bundle files exist with the cited section numbers (best_practices.md sections 1-5, 15-18, 19-21, 35-37, 39 all verified present), and the query-complexity table navigates to file-plus-section granularity one level deep. It is not a 5 because the 355-line body still inlines content that duplicates the references — the function quick-reference block and the Loki 3.x feature details — so the split between overview and detail files is not fully clean.

4 / 5

Total

16

/

20

Passed

Description

88%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 that pairs a concrete four-part capability statement with an explicit 'Use this skill when...' trigger clause naming the natural use cases (new queries, dashboards, alerting rules, troubleshooting). The only improvements are adding a few synonyms ('Grafana Loki', 'log query') and an explicit non-goal boundary versus PromQL to sharpen distinctiveness.

DimensionReasoningScore

Specificity

The description lists four concrete, distinct capabilities — 'Generate label matchers, line filters, log aggregations, and metric queries in LogQL' — comprehensively covering the skill's output types. It is not a 4 because there are no meaningful gaps in coverage of the query-generation domain; the only soft phrase ('following current standards and conventions') is minor padding, not a missing action.

5 / 5

Completeness

It explicitly answers both questions: what ('Generate label matchers, line filters, log aggregations, and metric queries in LogQL (Loki Query Language)') and when ('Use this skill when creating new LogQL queries, implementing log analysis dashboards, alerting rules, or troubleshooting with Loki'). This matches the anchor-5 example's what-plus-concrete-trigger structure exactly.

5 / 5

Trigger Term Quality

Natural trigger phrases include 'creating new LogQL queries', 'log analysis dashboards', 'alerting rules', and 'troubleshooting with Loki' — terms users would plausibly say. It is not a 5 because common synonyms like 'Grafana Loki', 'logcli', or 'log query' are absent, leaving a few natural entry points uncovered.

4 / 5

Distinctiveness Conflict Risk

The LogQL/Loki niche is clear and the language names the tool three times, keeping conflict risk low. It is not a 5 because generic phrases like 'alerting rules' and 'log analysis dashboards' could also fire a Grafana-dashboard or PromQL skill, and the description does not explicitly fence off the PromQL boundary (that only appears in the body).

4 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pantheon-org/tekhne
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.