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 delivers highly actionable, copy-paste-ready Membrane commands and a clear connection workflow, but it pads the opening with business context Claude already infers and omits validation checkpoints before destructive operations like deleting customers or canceling subscriptions. It is a strong, well-structured skill that would benefit from trimming fluff and adding verify-before-destructive-action steps.
Suggestions
Add an explicit validation/verification step before destructive actions: e.g. before running delete-customer or cancel-subscription, fetch and confirm the target with the user, then re-fetch to verify the resulting state.
Trim the opening overview paragraph ("Billsby is a subscription billing platform... used by businesses of all sizes...") to a one-line context statement; Claude does not need the business primer.
Consider moving the popular-actions catalog and proxy flag reference into a separate references file so SKILL.md stays a lean overview with one-level-deep navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with concrete commands, but the opening business-context paragraph ("Billsby is a subscription billing platform... used by businesses of all sizes...") and some redundant connection-state prose pad what Claude does not need, matching the mostly-efficient-but-could-be-tightened anchor. | 3 / 5 |
Actionability | Copy-paste-ready membrane commands (install, login, connection ensure, action list/run, request) plus a concrete popular-actions table and proxy flag reference fully cover the common integration cases, matching the fully-executable anchor. | 5 / 5 |
Workflow Clarity | The install-authenticate-connect-poll-search-run sequence is clear with state-based decision guidance, but destructive/batch actions (delete-customer, cancel-subscription, list operations) lack any validation or verify-before-proceeding checkpoint, which caps workflow clarity at 3 per the rubric. | 3 / 5 |
Progressive Disclosure | The skill is well organized with clear section headers and navigable structure; no bundle files exist so everything is inline, and the popular-actions and proxy-option tables could arguably live in separate reference files, giving minor organization gaps rather than the ideal one-level-deep reference split. | 4 / 5 |
Total | 15 / 20 Passed |