prometheus-configuration

Complete guide to Prometheus setup, metric collection, scrape configuration, and recording rules.

Quality

47%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/prometheus-configuration/SKILL.md

Quality

Content

50%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 skill provides comprehensive, concrete Prometheus configuration examples with good actionability, but suffers from significant verbosity by inlining content that should live in the referenced files. The workflow lacks a clear sequential process with validation feedback loops, and the referenced bundle files don't exist, undermining the progressive disclosure structure.

Suggestions

Move the detailed recording rules, alert rules, and scrape configuration variants into the referenced files (references/recording-rules.md, references/scrape-configs.md) and keep only a minimal example inline.

Remove the architecture diagram and explanatory text about what Prometheus does—Claude already knows this. Cut the generic best practices list or reduce to the 3 most critical, non-obvious items.

Add an explicit numbered workflow: 1) Create/edit prometheus.yml → 2) Validate with promtool check config → 3) If errors, fix and re-validate → 4) Reload config → 5) Verify targets are scraped.

Provide the actual bundle files (assets/prometheus.yml.template, scripts/validate-prometheus.sh, etc.) so the references are functional rather than dead links.

Dimension	Reasoning	Score
Conciseness	The skill is significantly verbose. It includes an architecture diagram Claude doesn't need, explains what Prometheus does (Claude already knows), and inlines massive YAML blocks for configuration, recording rules, alert rules, and multiple service discovery patterns that should be in referenced files. The best practices section is a generic list that adds little value.	2 / 5
Actionability	The skill provides concrete, copy-paste ready configuration examples, executable helm/docker commands, and specific promtool validation commands. Minor gaps exist—the instructions section is vague ('Clarify goals, constraints, and required inputs') and doesn't guide Claude on how to adapt configurations to user needs.	4 / 5
Workflow Clarity	There is no clear end-to-end workflow sequence. The validation section exists but is disconnected from the configuration steps—there's no explicit 'configure → validate → fix → re-validate' feedback loop. For a skill involving configuration changes that could break monitoring, the lack of integrated validation checkpoints caps this at 3.	3 / 5
Progressive Disclosure	The skill references external files (assets/prometheus.yml.template, references/scrape-configs.md, references/recording-rules.md, scripts/validate-prometheus.sh) which is good structure, but no bundle files are provided, making these references dead ends. Additionally, massive YAML blocks for recording rules, alert rules, and multiple scrape config patterns are inlined when they should be in the referenced files, defeating the purpose of the references.	3 / 5
	Total	12 / 20 Passed

Description

45%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.

The description identifies a clear technology domain (Prometheus) and lists relevant topic areas, but reads more like a table of contents than an actionable skill description. It lacks a 'Use when...' clause, which is critical for Claude to know when to select this skill, and the capabilities are described as categories rather than concrete actions.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases like 'Use when the user asks about Prometheus setup, monitoring configuration, PromQL queries, scrape targets, or recording rules.'

Replace the generic 'Complete guide to' framing with concrete actions, e.g., 'Configures Prometheus scrape targets, writes PromQL recording rules, sets up metric collection pipelines, and troubleshoots prometheus.yml configuration.'

Include additional natural trigger terms and synonyms such as 'monitoring', 'PromQL', 'exporters', 'alertmanager', 'prometheus.yml', and 'time-series metrics'.

Dimension	Reasoning	Score
Specificity	Names the domain (Prometheus) and lists several areas (setup, metric collection, scrape configuration, recording rules), but these are more like topic categories than concrete actions. It doesn't describe what specific actions the skill performs (e.g., 'configure scrape targets', 'write PromQL recording rules', 'set up alerting').	3 / 5
Completeness	Provides a reasonable 'what' (Prometheus setup, metric collection, scrape configuration, recording rules) but has no 'when' clause at all. The rubric states a missing 'Use when...' clause should cap completeness at 3, and since the 'what' is also somewhat vague (described as a 'guide' rather than concrete actions), a score of 2 is appropriate.	2 / 5
Trigger Term Quality	Includes relevant Prometheus-specific terms like 'scrape configuration', 'recording rules', and 'metric collection', which users might naturally mention. However, it's missing common synonyms and related terms like 'PromQL', 'alerting', 'exporters', 'targets', 'prometheus.yml', or 'monitoring'.	3 / 5
Distinctiveness Conflict Risk	Prometheus is a specific technology, which makes this fairly distinct from other monitoring or infrastructure skills. However, it could overlap with broader monitoring/observability skills or Grafana-related skills. The mention of specific Prometheus concepts like 'scrape configuration' and 'recording rules' helps differentiate it.	4 / 5
	Total	12 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/prometheus-configuration/SKILL.md
Commit: 57c135b

Reviewed: 3 days 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.