promql-generator

Generate PromQL queries for calculating error rates, aggregating metrics across labels, creating histogram percentiles, writing recording rules, and building SLO burn-rate alerts following Prometheus best practices. Use when creating new PromQL queries, implementing monitoring and alerting rules, building observability dashboards, working with Prometheus metrics (counters, gauges, histograms, summaries), or applying RED (Rate, Errors, Duration) and USE (Utilization, Saturation, Errors) monitoring patterns.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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, highly actionable skill body with an excellent validation feedback loop and exemplary progressive disclosure across a real, well-organized bundle. Its main weakness is redundancy: the Mindset section and duplicated burn-rate patterns repeat guidance stated elsewhere, costing token efficiency.

Suggestions

Remove or drastically shrink the 'Mindset' section — all four of its bullets are restated in 'Key Rules' and 'Anti-Patterns' (e.g., the rate-on-gauge rule appears three times in the document).

Keep only the multi-window burn-rate alert inline and point the single-window variant to assets/slo_patterns.promql, since the full SLO patterns are already delegated there.

Consolidate the scenario-to-reference table and the bottom 'References' list into one navigation block to avoid listing every bundle file twice.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight (code blocks, tables, short bullets), but the 'Mindset' section substantially duplicates the 'Key Rules' and 'Anti-Patterns' sections — the rate-on-gauge rule is stated three times — and the burn-rate pattern is inlined twice ('Burn rate' and 'Multi-window burn-rate alert') while also living in assets/slo_patterns.promql, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trim anchor at 4.	3 / 5
Actionability	Fully executable, copy-paste-ready PromQL covering the common cases (request rate, error-rate ratio, P95 for both classic and native histograms, availability, single- and multi-window burn rate) plus concrete YAML alerting/recording rule snippets, an error-handling table with specific fixes, and a documented docs-lookup fallback — matching the top anchor.	5 / 5
Workflow Clarity	The 7-stage workflow is clearly sequenced with an explicit confirmation checkpoint (stage 4, AskUserQuestion with defined options) and an explicit validate→fix→re-validate feedback loop ('Fix any issues and re-validate until all checks pass'), reinforced by a structured Validation Checklist — matching the anchor requiring explicit validation steps and error-recovery loops.	5 / 5
Progressive Disclosure	The body is a genuine overview: core patterns inline with bulk detail pushed to 4 references and 7 asset files, all of which exist, are one level deep, and are clearly signaled — a scenario-to-reference table plus an annotated References section stating when to read each file; no nesting or buried references.	5 / 5
	Total	18 / 20 Passed

Description

100%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: concrete capability list, explicit and specific 'Use when' triggers, third-person voice, and a clearly bounded Prometheus/PromQL niche. No fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	The description enumerates five concrete, distinct capabilities — 'calculating error rates, aggregating metrics across labels, creating histogram percentiles, writing recording rules, and building SLO burn-rate alerts' — which is comprehensive coverage of the skill's domain, matching the top anchor rather than the score-4 anchor ('several specific actions; minor gaps').	5 / 5
Completeness	It explicitly answers both 'what' (generate PromQL queries for the five named tasks) and 'when' with a concrete 'Use when...' clause listing trigger scenarios, exactly matching the score-5 anchor; the score-4 anchor requires a 'when' that could be more specific, which does not apply here.	5 / 5
Trigger Term Quality	Trigger terms are comprehensive and natural: 'creating new PromQL queries', 'monitoring and alerting rules', 'observability dashboards', 'Prometheus metrics (counters, gauges, histograms, summaries)', 'RED' and 'USE' patterns — covering the synonyms a user would plausibly say when needing this skill; not merely good coverage with terms missing (anchor 4).	5 / 5
Distinctiveness Conflict Risk	The niche is unambiguous — PromQL query generation for Prometheus — with distinct triggers (PromQL, recording rules, SLO burn-rate, RED/USE), so minimal conflict risk with sibling skills; generic phrasing that would overlap with other skills (anchors 1–3) is absent.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

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: pantheon-org/tekhne
Path: skills/observability/promql/generator/SKILL.md
Commit: a1083f4

Reviewed: 3 hours ago

Table of Contents

Discovery Implementation Validation

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.