inlined-refs

Generate a Kafka consumer group lag dashboard. Use when the user asks to monitor lag, build a dashboard for consumer lag, or wire up Prometheus exporters for Kafka. Do NOT trigger for producer metrics, broker JMX, or Streams-specific monitoring.

Quality

77%

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/confluent-skill-reviewer/evals/mock-skills/inlined-refs/SKILL.md

Quality

Content

60%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.

The body is actionable and clearly sequenced for a simple dashboarding skill, but it defeats progressive disclosure by inlining exporter-comparison content that is duplicated verbatim in references/exporters.md, wasting tokens and making the reference file redundant. Tightening this single section into a pointer would substantially improve the skill.

Suggestions

Replace the inlined 'Exporter comparison' block with a one-line pointer such as 'See [references/exporters.md](references/exporters.md) for the exporter comparison and config snippet' to remove the duplication and restore one-level-deep progressive disclosure.

Add a brief verification checkpoint in Step 1 (e.g., confirm the exporter's /metrics is being scraped by Prometheus before moving to Grafana) to lift workflow clarity.

Make the Grafana and alert steps more executable by including a concrete PromQL example for the lag query and a sample alert rule snippet.

Dimension	Reasoning	Score
Conciseness	The body is generally tight with no concept over-explanation, but it inlines the full exporter comparison and config snippet that already exist verbatim in references/exporters.md, so those tokens are duplicated and could be tightened to a pointer; not a 4 because the duplication is a whole section rather than a minor trim.	3 / 5
Actionability	Provides a copy-paste-ready exporter config snippet plus concrete specifics (Grafana dashboard 7589, metric kafka_consumergroup_lag, 5-minute window, alert threshold lag > 10,000 for 5 min); not a 5 because the Grafana and alert steps stop short of executable commands/queries.	4 / 5
Workflow Clarity	A clear three-step sequence (pick exporter, Grafana dashboard, alerts) with concrete specifics at each step; not a 5 because there is no verification checkpoint (e.g., confirming the exporter is being scraped by Prometheus) before building dashboards/alerts.	4 / 5
Progressive Disclosure	A references/exporters.md file exists, yet the section titled 'Exporter comparison (from references/exporters.md)' inlines the full comparison content instead of linking out, so content that clearly belongs in the separate file is duplicated inline and the reference is effectively buried; not a 3 because the reference is not actually used as a navigable pointer.	2 / 5
	Total	13 / 20 Passed

Description

82%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.

The description is well-constructed: it clearly answers both what and when, uses natural trigger phrasing, and adds explicit negative-trigger boundaries that sharply reduce conflict risk. Its only weakness is modest action specificity, listing just two concrete capabilities.

Suggestions

Consider enumerating one or two more concrete capabilities (e.g., alert rule authoring, dashboard panel configuration) to lift specificity from two actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ('Generate a Kafka consumer group lag dashboard', 'wire up Prometheus exporters for Kafka'), matching the anchor for 1-2 concrete actions without comprehensive coverage; not a 4 because no further distinct actions are enumerated.	3 / 5
Completeness	Explicitly states what ('Generate a Kafka consumer group lag dashboard') and when ('Use when the user asks to monitor lag, build a dashboard for consumer lag, or wire up Prometheus exporters for Kafka') with concrete trigger phrases and negative-trigger guidance.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('monitor lag', 'build a dashboard for consumer lag', 'wire up Prometheus exporters for Kafka') with good coverage; not a 5 because some synonyms and concrete file/extension terms are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Kafka consumer lag dashboarding) with distinct triggers plus explicit exclusion ('Do NOT trigger for producer metrics, broker JMX, or Streams-specific monitoring'), minimizing conflict risk.	5 / 5
	Total	17 / 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: confluentinc/agent-skills
Path: skills/confluent-skill-reviewer/evals/mock-skills/inlined-refs/SKILL.md
Commit: db79f9e

Reviewed: 6 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.