Content
68%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.
A highly actionable skill body with concrete CLI commands and clear connection-state handling. Its weak spots are background padding that hurts conciseness and the absence of validation guardrails around destructive operations.
Suggestions
Trim the introductory platform description and the product-overview tree, which restate knowledge Claude already has.
Add an explicit validation/confirmation checkpoint before destructive actions, e.g. require a user confirmation or a dry-run before running delete-user, delete-course, or delete-bundle.
Move the popular-actions table and proxy flag reference into a reference file referenced one level deep from SKILL.md to improve progressive disclosure and reduce token load.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with executable commands, but includes unnecessary background Claude already knows ("Knorish is a platform that enables individuals and businesses to create and sell online courses...") and a large product-overview tree that could be trimmed, matching anchor 3. | 3 / 5 |
Actionability | It provides fully executable, copy-paste-ready commands for every stage (install, login, connection ensure, action list/run, request) plus a popular-actions table and a flag-reference table, covering the common cases as anchor 5 requires. | 5 / 5 |
Workflow Clarity | The connection setup flow is well sequenced with state-polling checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED), but destructive actions (delete-user, delete-course, delete-bundle) are listed with no validation or confirmation step, triggering the destructive-operation cap at 3. | 3 / 5 |
Progressive Disclosure | No bundle files exist and the skill is a single ~180-line document with clear, well-organized section headers; structure is good with only minor organization gaps, matching anchor 4 rather than 5 (which expects explicit one-level-deep references). | 4 / 5 |
Total | 15 / 20 Passed |