Content
65%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 body is well-structured and actionable with strong CLI examples and a clear connection/polling flow, but it pads an unnecessary intro, lacks validation before destructive actions, and inlines a reference-grade action table rather than splitting it out.
Suggestions
Add an explicit validation or confirmation checkpoint before running destructive actions (delete-user, delete-organization) and surface the action's expected effects.
Trim the introductory "what Clerk is" paragraph and the auth-plumbing filler since Claude already knows these concepts.
Move the "Popular actions" table into a references file (e.g. ACTIONS.md) and link to it from SKILL.md to reduce inlined bulk.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely efficient with copy-paste commands and tables, but the introductory paragraph explaining what Clerk is and filler like "so you can focus on the integration logic" could be trimmed. | 4 / 5 |
Actionability | Concrete, executable bash commands cover install, auth, connection, search, and running actions, with a parameter-passing example and proxy flag table, though the action table carries "No description" placeholders leaving minor gaps. | 4 / 5 |
Workflow Clarity | A reasonable sequence with a polling feedback loop exists, but destructive actions (delete-user, delete-organization) are invoked via `membrane action run` with no validation checkpoint, capping the score per the destructive-operations guidance. | 3 / 5 |
Progressive Disclosure | Sections are present but the skill exceeds 50 lines with no bundle files, and the large inlined "Popular actions" table is content that could live in a separate reference; references are not signaled. | 3 / 5 |
Total | 14 / 20 Passed |