Guide for using the CockroachDB replicator to continuously replicate changes from PostgreSQL, MySQL, or Oracle to CockroachDB after an initial molt fetch data load. Use when setting up CDC replication, configuring pglogical/mylogical/oraclelogminer, or managing the fetch → replicator cutover workflow.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
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 defines a narrow, specific domain (CockroachDB CDC replication) with concrete actions, explicit trigger conditions, and highly distinctive terminology. It uses proper third-person voice and covers both the 'what' and 'when' comprehensively. The inclusion of specific tool names and source database types makes it easy for Claude to select this skill precisely when needed.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: continuously replicate changes from PostgreSQL/MySQL/Oracle to CockroachDB, configuring pglogical/mylogical/oraclelogminer, managing fetch → replicator cutover workflow. These are concrete, domain-specific actions. | 3 / 3 |
Completeness | Clearly answers both what ('continuously replicate changes from PostgreSQL, MySQL, or Oracle to CockroachDB after an initial molt fetch data load') and when ('Use when setting up CDC replication, configuring pglogical/mylogical/oraclelogminer, or managing the fetch → replicator cutover workflow'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'CDC replication', 'pglogical', 'mylogical', 'oraclelogminer', 'CockroachDB replicator', 'PostgreSQL', 'MySQL', 'Oracle', 'cutover', 'molt fetch'. These cover the specific tools and concepts a user would mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very clear niche: CockroachDB replicator for CDC from specific source databases. The specific tool names (pglogical, mylogical, oraclelogminer, molt fetch) make it extremely unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with a clear multi-step workflow and good validation checkpoints. Its main weakness is length — the source-specific sections are somewhat repetitive and the flags section is extensive inline content that would benefit from being in a referenced file. The broken reference to 'references/flags.md' (no bundle file exists) is a minor issue.
Suggestions
Move the detailed Key Flags section and source-specific setup sections into separate referenced files to improve conciseness and progressive disclosure.
Remove or fix the reference to 'references/flags.md' since no bundle file exists to support it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with concrete commands and tables, but includes some unnecessary elements like the architecture ASCII diagram and explanatory text that Claude would already understand. The source-specific setup sections repeat similar patterns that could be more compressed. | 2 / 3 |
Actionability | Excellent actionability throughout — every step has fully executable, copy-paste-ready commands with realistic connection strings. SQL setup commands, bash invocations, and monitoring commands are all concrete and complete. | 3 / 3 |
Workflow Clarity | The 7-step fetch-to-cutover workflow is clearly sequenced with explicit validation checkpoints (Step 4: preflight test, Step 6: monitor lag, Step 7: cutover with drain confirmation). The cutover procedure includes a clear feedback loop (wait for lag → redirect → drain → confirm → stop). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, but it's fairly long and inline — the source-specific setup sections and full flags reference could be split into separate files. There's a reference to 'references/flags.md' but no bundle file exists to support it. | 2 / 3 |
Total | 10 / 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.
84bc1e4
Table of Contents
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.