Content
75%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 action-oriented, giving executable commands and a clearly sequenced connection workflow with validation checkpoints. Main gaps are minor verbosity in the intro and placeholder-only examples rather than a worked end-to-end run.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly lean command examples and a flags table with only minor over-explanation (the intro paragraph describing what Shoprocket is for small businesses), sitting just below the fully lean 5 anchor. | 4 / 5 |
Actionability | Concrete, copy-paste-ready commands appear throughout (login, connection ensure, action run, request proxy with flag table); it falls short of 5 because most examples rely on placeholders (CONNECTION_ID, actionId) with no fully worked end-to-end example. | 4 / 5 |
Workflow Clarity | The connection flow is explicitly sequenced with state-based branching and polling checkpoints (BUILDING/READY/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR), but it lacks an explicit error-recovery loop for action-run failures, keeping it below 5. | 4 / 5 |
Progressive Disclosure | A single, well-sectioned SKILL.md with clear headers and no nested or broken references; with no bundle files present this is good structure, though the proxy/action sections run long enough inline to keep it just under 5. | 4 / 5 |
Total | 16 / 20 Passed |