confluent-cloud-cdc-tableflow

Set up end-to-end Change Data Capture (CDC) pipelines on Confluent Cloud using Debezium source connectors, Flink for transformation, and Tableflow for data lake integration. Supports JSON_SR, Avro, and Protobuf formats. Handles schemaless topics (plain JSON without SR) and multi-event topics. This skill handles the complete workflow from database to Iceberg/Delta tables. Use this skill when users want to capture database changes and materialize them into Iceberg or Delta Lake tables via Confluent Cloud Tableflow. Trigger phrases include "CDC to Tableflow", "database to Iceberg", "database to Delta Lake", "stream database changes to data lake", "set up Tableflow pipeline", "schemaless topic to Tableflow", or "multi-event topic to Iceberg". Do NOT trigger for general CDC, Debezium, or database replication requests that do not involve Tableflow or Iceberg/Delta Lake as the destination.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

92%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 a well-structured, highly actionable multi-phase workflow with strong validation checkpoints and clean one-level-deep progressive disclosure. Its only weakness is mild verbosity in the fallback and clarification sections.

Suggestions

Tighten the CLI fallback block in Phase 0.1 and the REST fallback note — consolidate to the essential commands and rely on references/rest-api.md for the rest, since the same patterns are partly repeated in Phase 3.

The 'Important Clarifications' and 'Critical Architecture Rules' sections overlap on the Tableflow-is-not-a-connector and changelog-mode points; deduplicate to reduce tokens.

Collapse the repeated per-database Tableflow enable CLI examples in 3.4 into a single parameterized example plus a one-line note on DELTA/Azure variants.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and focused on domain-specific operational knowledge Claude would not already know (MCP tool signatures, changelog-mode immutability, cleanup ordering), but a few sections restate points and the CLI/REST fallback block could be trimmed without losing clarity.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: concrete MCP tool calls with parameter signatures, CLI commands, SQL CREATE/INSERT examples, and JSON config blocks covering common cases including the DynamoDB-vs-SQL CDC decode difference.	5 / 5
Workflow Clarity	Sequenced across Phases 0–5 with explicit validation checkpoints (poll read-connector tasks, verify schemas, SHOW TABLES discovery, Flink job RUNNING check), feedback loops for error recovery, and a destructive-operations checklist (cleanup order, "Never delete CDC source Kafka topics while the connector is still running").	5 / 5
Progressive Disclosure	SKILL.md is an overview that points one level deep to real, clearly-signaled reference files (connector-configs.md, database-prerequisites.md, flink-sql-patterns.md, troubleshooting.md, rest-api.md), each verified present, with bulk detail appropriately split out and a consolidated References section.	5 / 5
	Total	19 / 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.

The description is third-person, concise, and explicitly covers what the skill does and when to use it, with concrete trigger phrases and a negative-trigger boundary. It is among the strongest examples in the reference set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Set up end-to-end Change Data Capture (CDC) pipelines", "using Debezium source connectors, Flink for transformation, and Tableflow for data lake integration", "Handles schemaless topics ... and multi-event topics", "materialize them into Iceberg or Delta Lake tables" — with comprehensive coverage of the pipeline stages.	5 / 5
Completeness	Explicitly answers both "what" ("Set up end-to-end CDC pipelines ... from database to Iceberg/Delta tables") and "when" ("Use this skill when users want to capture database changes and materialize them ... via Confluent Cloud Tableflow") with concrete trigger phrases and a negative-trigger clause.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger phrases a user would actually say — "CDC to Tableflow", "database to Iceberg", "database to Delta Lake", "stream database changes to data lake", "set up Tableflow pipeline", "schemaless topic to Tableflow", "multi-event topic to Iceberg" — covering synonyms and format variants.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (CDC materialized to Iceberg/Delta via Confluent Cloud Tableflow) and adds an explicit anti-trigger ("Do NOT trigger for general CDC, Debezium, or database replication requests that do not involve Tableflow or Iceberg/Delta Lake"), minimizing overlap with adjacent skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (523 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: confluentinc/agent-skills
Path: skills/confluent-cloud-cdc-tableflow/SKILL.md
Commit: edec375

Reviewed: 12 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.