Content
68%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The content is well-structured and actionable with executable Mini Program examples, but it lacks a validation/verification feedback loop for destructive database operations and references several companion files that are absent from the bundle.
Suggestions
Add an explicit validation checkpoint for write operations (e.g. verify the result/upsert count, handle permission errors, confirm _openid was not manually set) to satisfy the database-operations feedback-loop requirement.
Either ship the referenced companion files (crud-operations.md, complex-queries.md, pagination.md, aggregation.md, geolocation.md, security-rules.md) or remove the Quick routing links so navigation does not point to missing files.
De-duplicate the Overview use-case list against the Activation Contract to tighten the token budget.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is efficient and assumes Claude's competence, but the Overview section restates use cases already covered by the Activation Contract's 'Use this first when' list, a minor redundancy that could be trimmed. | 4 / 5 |
Actionability | Executable code for initialization, where queries, and doc access is concrete and copy-paste ready, but the Quick routing links point to reference files that are not present in the bundle, leaving a small gap. | 4 / 5 |
Workflow Clarity | A Minimal checklist and numbered Working rules give a clear sequence, but because this skill performs destructive database CRUD there should be an explicit validate/verify feedback loop, whose absence caps workflow clarity at 3. | 3 / 5 |
Progressive Disclosure | The SKILL.md is a well-organized overview with clearly signaled one-level-deep references (Quick routing, Then also read), but the referenced files do not actually exist in the bundle, a minor organization gap. | 4 / 5 |
Total | 15 / 20 Passed |