Content
87%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 a tight, fully executable CLI reference with excellent conciseness and actionability. Its main gap is the absence of a verification step after the destructive push, which caps workflow clarity despite the confirm-with-user caution.
Suggestions
Add a post-run verification step, e.g. list project files after push ('gws script +list --script <ID>') or check command exit status, to close the destructive-operation feedback loop.
Show expected success output or an exit-code check so Claude can confirm the upload actually replaced the project files.
Optionally note how to preview/dry-run before the destructive replace, if the CLI supports it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and well-organized (usage, flags table, examples, tips, caution, see-also) with no padding or explanation of concepts Claude already knows, matching 'every token earns its place'. | 5 / 5 |
Actionability | Provides copy-paste-ready commands covering the common cases ('gws script +push --script <ID>' and the '--dir ./src' variant) plus a complete flag table with defaults. | 5 / 5 |
Workflow Clarity | The single action is unambiguous and there is a pre-execution confirm-caution, but this is a destructive write ('replaces ALL files') with no post-run verification/feedback loop, so workflow clarity is capped at 3 per the destructive-operation rule. | 3 / 5 |
Progressive Disclosure | Under 50 lines with no bundle files needed; sections are well-organized and the only references are one-level-deep sibling SKILL.md links clearly signaled in the prerequisite and See Also sections. | 5 / 5 |
Total | 18 / 20 Passed |