kafka-schema-registry
Scan a project to identify Kafka applications, extract schemas from data models, tag PII fields, generate Terraform for Confluent Schema Registry registration, and produce a migration report with rollout ordering. Use this skill when a user asks to analyze a folder or repo for Kafka usage, extract schemas, audit producer/consumer configurations, or generate Terraform for Schema Registry.
68
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates multiple concrete capabilities in a specific technical domain. It includes an explicit 'Use this skill when...' clause with natural trigger terms, and the combination of Kafka + Schema Registry + Terraform + PII tagging makes it highly distinctive. The description is well-structured, uses third person voice, and balances detail with conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: scan for Kafka applications, extract schemas from data models, tag PII fields, generate Terraform for Confluent Schema Registry, and produce a migration report with rollout ordering. | 3 / 3 |
Completeness | Clearly answers both 'what' (scan project, extract schemas, tag PII, generate Terraform, produce migration report) and 'when' with an explicit 'Use this skill when...' clause listing specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Kafka', 'schemas', 'PII', 'Terraform', 'Confluent Schema Registry', 'producer/consumer configurations', 'migration report', 'analyze a folder or repo'. These cover the domain well with natural variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Kafka, Schema Registry, Terraform generation, and PII tagging. Very unlikely to conflict with other skills due to the specific technology stack and workflow described. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized, comprehensive skill for a complex multi-phase workflow. Its strongest aspect is the clear phased workflow with explicit categorization criteria and validation steps. The main weaknesses are the absence of executable code examples (Terraform snippets, actual grep commands, schema file examples) in the body itself, and the missing bundle files that the skill heavily references for detailed patterns and templates.
Suggestions
Add at least one concrete, executable example for key outputs—e.g., a sample Terraform resource block for a schema registration, a sample .avsc file with PII tags, and example grep commands for detection patterns.
Provide the referenced bundle files (references/detection-patterns.md, references/terraform-templates.md, etc.) or inline the most critical content, since without them the skill lacks the detailed actionable guidance it promises.
Reduce repetition by showing the output directory structure only once and consolidating the category definitions into a single authoritative location rather than repeating across multiple sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-structured and avoids explaining basic concepts Claude already knows (e.g., what Kafka is), but there is notable repetition—the output directory structure is shown twice, category definitions appear in multiple places, and some sections like 'CRITICAL' formatting requirements restate what's already implied. Could be tightened by ~20-30%. | 2 / 3 |
Actionability | The skill provides concrete directory structures, file naming conventions, categorization criteria, and specific grep patterns to look for, which is good. However, it lacks executable code examples—no actual Terraform snippets, no schema file examples, no grep commands. The references that would contain these details are not provided in the bundle, so the actionability of the main file alone is incomplete. | 2 / 3 |
Workflow Clarity | The 8-phase workflow (Phase 0-7) is clearly sequenced with explicit steps within each phase. Validation checkpoints exist (e.g., 'Call schema_lint(path: schemas/, fix: true)', validate formatting requirements, check for existing infrastructure). The categorization system provides clear decision criteria, and the migration rollout ordering gives explicit sequencing by category with feedback considerations. | 3 / 3 |
Progressive Disclosure | The skill has excellent structure with 6 clearly signaled reference documents covering detection patterns, schema inference, categorization, Terraform templates, report templates, and code migration. However, no bundle files were provided, meaning all these references are broken links. The main SKILL.md also includes substantial detail that could be in references (e.g., the full categorization table, directory structures repeated), suggesting the split between overview and detail isn't optimal. | 2 / 3 |
Total | 9 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- confluentinc/agent-skills
- Commit
8b85616
- 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.