Content
82%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 concrete, copy-paste-ready CLI commands and a clear workflow including validation via state polling. The main gaps are minor: some editorial padding and inconsistent step numbering.
Suggestions
Fix the step numbering: label "Step 1a/1b" and "Step 2" consistently, or remove the dangling "skip to Step 2" references.
Trim the editorial "Best practices" framing into terse imperative bullets to reduce token cost.
Consider moving the proxy flag reference table into a separate reference file so SKILL.md stays a lean overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean executable commands with brief explanations and a tight flag table; minor editorial padding (the "Best practices" bullets and the Membrane-value framing) could be trimmed without losing clarity. | 4 / 5 |
Actionability | It provides copy-paste-ready commands for every common case (install, login, connection ensure/get, action list/run, request proxy) with documented flags and JSON output examples, fully executable end to end. | 5 / 5 |
Workflow Clarity | A clear install→auth→connect→search→run sequence with an explicit state machine (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and feedback loops ("poll again", "keep polling until"), but step numbering is inconsistent ("skip to Step 2" with no labeled Step 2; "1b" without a "1a"). | 4 / 5 |
Progressive Disclosure | Well-organized into clear headed sections with no nested references and no bundle files to misroute, though the single file mixes overview, command reference, and a flag table that could live in a separate reference for a cleaner overview. | 4 / 5 |
Total | 17 / 20 Passed |