Content
80%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 commands and a well-structured single-file layout. Its one substantive gap is the absence of validation/verification guidance around the destructive actions the skill exposes.
Suggestions
Add a verify-before-delete checkpoint for destructive actions (e.g. run get-* to confirm the target ID before delete-*, or list and show the to-be-deleted resource), turning the running-actions guidance into a feedback loop.
Trim the influencer/business framing in the opening paragraph and editorial phrases like "This is the fastest way to get a connection" to tighten token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is largely efficient with concrete commands and minimal padding, though a few lines (the influencer framing and "This is the fastest way to get a connection") could be trimmed. | 4 / 5 |
Actionability | It provides fully executable, copy-paste-ready commands for every phase — install, login, connection ensure, action list/run, and proxy requests — covering the common cases. | 5 / 5 |
Workflow Clarity | The connection flow has explicit state-based polling and retry checkpoints, but destructive actions (delete-data, delete-project, delete-link, delete-qr-code) are surfaced with no verification step, capping workflow clarity per the destructive-operations rule. | 3 / 5 |
Progressive Disclosure | The SKILL.md is a single well-organized file with clear sections and no nested or buried references; for a self-contained skill with no needed external bundles, this earns the top anchor. | 5 / 5 |
Total | 17 / 20 Passed |