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.
The content is highly actionable with copy-paste CLI commands and a well-structured connection workflow, but it carries some filler and lacks validation guidance for destructive Backlog operations. Organization is solid for a single-file skill.
Suggestions
Remove filler (e.g., "Use action names and parameters as needed.") and either populate or drop the empty Description column in the Popular actions table.
Add a validation/confirmation step before destructive actions (e.g., confirm issue state or list-before-delete for delete-issue) to lift workflow clarity past the destructive-cap of 3.
Clarify the "skip to Step 2" references by explicitly labeling Step 1 and Step 2 sections so the connection-to-action flow is unambiguous.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly command-driven and efficient, but includes filler ("Use action names and parameters as needed"), explanatory fluff about auth plumbing, and a Popular actions table with empty description columns, fitting the mostly-efficient-with-some-unnecessary-explanation anchor. | 3 / 5 |
Actionability | Commands like `npm install -g @membranehq/cli@latest`, `membrane connection ensure "https://backlog.com/" --json`, and `membrane action run <actionId> ... --input '{...}'` are copy-paste ready and cover the common cases, matching the fully-executable anchor. | 5 / 5 |
Workflow Clarity | The connection flow has clear state-checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED) and polling, but destructive actions like delete-issue lack any validation or confirmation step, so the destructive-operation cap of 3 applies even though the connection sequence is otherwise strong. | 3 / 5 |
Progressive Disclosure | No bundle files are present and the single SKILL.md is organized into clear, well-signaled sections with no nested references, but the inlined Popular actions and proxy-flag tables represent minor organization gaps rather than a perfectly split overview. | 4 / 5 |
Total | 15 / 20 Passed |