Content
76%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 highly actionable with executable CLI commands and a clear connection-state workflow, though it lacks validation safeguards around destructive actions and inlines reference-style bulk content rather than splitting it out.
Suggestions
Add an explicit validation/confirmation checkpoint before running destructive actions (e.g. verify the target ID and confirm with the user before delete-* actions).
Move the 14-row Popular actions table into a separate reference file and link to it from SKILL.md to improve progressive disclosure.
Trim the introductory paragraph's product-marketing framing ("Think of it as a low-code alternative...") to assume Claude's competence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient, with command blocks and state tables carrying the content, but the intro ("Think of it as a low-code alternative...") and a few auth-plumbing explanations over-explain context Claude largely knows. | 4 / 5 |
Actionability | It provides copy-paste-ready executable commands throughout (install, login, connection ensure, action list/run with JSON input, request proxy) plus a full actions table and proxy-flag table covering the common cases. | 5 / 5 |
Workflow Clarity | The connection lifecycle is clearly sequenced with polling and a state-decision tree, but destructive actions (delete-upload, delete-headless-import, delete-import-schema) are listed with no validation checkpoint before execution, capping this dimension per the destructive/batch guideline. | 3 / 5 |
Progressive Disclosure | The body is a well-organized single overview with clear section headers and no nested references, but the sizable inlined actions table and API-style material could live in a separate reference file, leaving minor organization gaps. | 4 / 5 |
Total | 16 / 20 Passed |