leaky-data

Enrich a customer-orders stream with loyalty tier using Flink SQL on Confluent Cloud. Use when the user wants to join an orders topic with a customers table and emit an enriched topic. Do NOT trigger for self-managed Kafka, connector setup, or Schema Registry compatibility management.

Quality

78%

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/leaky-data/SKILL.md

Quality

Content

57%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 short, well-structured skill body, but its actionable core is weakened by placeholder SQL, missing output-validation steps, and execution-irrelevant meta-commentary padding the intro.

Suggestions

Replace the 'SELECT ... JOIN ...' ellipsis with a complete, executable Flink SQL example so step 3 is copy-paste ready.

Add a validation/verification step after statement creation (e.g., check the enriched_orders topic is receiving records with the expected loyalty tier) to satisfy the destructive/stream-emit feedback-loop requirement.

Trim the test-fixture meta-commentary from the intro, or move it to a non-executed comment, so the body stays focused on guidance Claude can act on.

Dimension	Reasoning	Score
Conciseness	The Steps list is lean, but the opening meta-commentary ('INTENTIONALLY LEAKY TEST FIXTURE', 'exists so the PII scanner has a positive target') is padding that does not aid execution. Not 4 because the unnecessary explanation is more than minor; not 2 because the actionable section itself is efficient.	3 / 5
Actionability	Step 3 shows a SQL skeleton ('INSERT INTO enriched_orders SELECT ... JOIN ...') with ellipsis placeholders rather than complete executable code. Not 4 because key details of the SELECT/JOIN are missing; not 2 because the skeleton plus topic/table-gathering steps give more than high-level hints.	3 / 5
Workflow Clarity	A clear 4-step sequence with a confirmation checkpoint (step 4), but no validation or feedback loop on the emitted result, and the destructive/stream-emit cap limits the ceiling. Not 4 because validation gaps are non-minor; not 2 because the sequence is coherent and explicit.	3 / 5
Progressive Disclosure	Under 50 lines, no external references needed, with well-organized sections (intro, example record, Steps) — the simple-skill exception applies. Not 4 because structure is clean and navigation is trivial.	5 / 5
	Total	14 / 20 Passed

Description

87%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 well-crafted description that explicitly answers both what and when, with concrete actions and strong negative-trigger boundaries. Minor room to expand action coverage and add trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'Enrich a customer-orders stream with loyalty tier using Flink SQL', 'join an orders topic with a customers table and emit an enriched topic' — covering enrich/join/emit. Not 5 because the narrow domain yields only ~3 distinct actions rather than a comprehensive multi-action list.	4 / 5
Completeness	Explicitly states both what ('Enrich a customer-orders stream with loyalty tier using Flink SQL on Confluent Cloud') and when ('Use when the user wants to join an orders topic with a customers table and emit an enriched topic'), plus negative-trigger guidance.	5 / 5
Trigger Term Quality	Includes natural terms a Confluent user would say ('Flink SQL', 'Confluent Cloud', 'orders topic', 'customers table', 'join', 'enriched topic'). Not 3 because coverage is solid; not 5 because synonyms and file/extension variants are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Flink SQL on Confluent Cloud order/customer joins) with explicit negative triggers ('Do NOT trigger for self-managed Kafka, connector setup, or Schema Registry compatibility management') minimizing conflict risk.	5 / 5
	Total	18 / 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/leaky-data/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.