Content
21%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a persona description rather than actionable operational guidance. It spends the vast majority of its token budget listing technologies and capabilities Claude already knows, while providing almost no concrete commands, code examples, or executable workflows. The content would benefit enormously from being replaced with specific runbooks, validation procedures, and copy-paste-ready examples for common DBA tasks.
Suggestions
Replace the extensive capability lists with 3-5 concrete, executable examples (e.g., a Terraform snippet for RDS provisioning, a backup verification script, a failover procedure with validation steps).
Add explicit validation checkpoints for destructive operations like migrations, failovers, and schema changes (e.g., 'Run `pg_isready` to verify connectivity before proceeding').
Move the technology enumeration lists into a separate reference file and keep SKILL.md focused on decision-making guidance and actionable procedures.
Replace 'Example Interactions' (which are just prompts) with worked examples showing input scenarios and the expected structured output or procedure Claude should produce.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive lists of technologies, capabilities, and behavioral traits that Claude already knows. The content reads like a persona description/resume rather than actionable instructions. Most of the 150+ lines are enumerating databases and tools Claude is already familiar with. | 1 / 5 |
Actionability | Almost entirely abstract and descriptive. No concrete code, commands, SQL examples, or executable steps. The 'Response Approach' section lists high-level phases but provides no specific implementation details. The 'Example Interactions' are just prompts, not worked examples with outputs. | 2 / 5 |
Workflow Clarity | The 'Response Approach' provides a rough 9-step sequence but lacks any validation checkpoints, feedback loops, or concrete verification steps. For a skill involving potentially destructive database operations (migrations, failovers, backups), the absence of validation steps is a significant gap. | 2 / 5 |
Progressive Disclosure | References `resources/implementation-playbook.md` for detailed examples, which is appropriate. However, the massive amount of capability listing that's inlined should be in a separate reference file, and no bundle files are provided to verify the reference exists. The structure has headers but the content organization is poor. | 3 / 5 |
Total | 8 / 20 Passed |