Content
67%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 body delivers executable CLI guidance with a clear, validated connection workflow and well-organized sections. Its main weakness is token efficiency, with marketing padding and repeated auth explanations that could be trimmed.
Suggestions
Cut marketing-fluff sentences like "so you can focus on the integration logic rather than auth plumbing" and consolidate the repeated Membrane-auth explanations.
Fix the broken step numbering by labeling the post-connection step as "Step 2" (or remove the "skip to Step 2" reference) so the workflow cross-references resolve.
Move the popular-actions table and proxy flags table into a reference file, keeping SKILL.md a lean overview with one-level-deep links, to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with concrete command examples, but padded with marketing fluff ("focus on the integration logic rather than auth plumbing") and repeated explanations of Membrane auth, matching anchor 3 rather than 4. | 3 / 5 |
Actionability | Provides copy-paste-ready CLI commands across install, login, connection, action search/run, and proxy, plus a flags table and popular-actions table, with only minor gaps from placeholder values, matching anchor 4 and approaching 5. | 4 / 5 |
Workflow Clarity | The connection workflow is sequenced with state-based validation checkpoints and a re-poll feedback loop for CLIENT_ACTION_REQUIRED, but the "skip to Step 2" reference points at an unlabeled step, leaving a minor gap at anchor 4. | 4 / 5 |
Progressive Disclosure | No bundle files exist, and the single ~150-line file is organized into clear sections (Overview, Working with Clearbit, Popular actions, Best practices) with good navigation, matching anchor 4. | 4 / 5 |
Total | 15 / 20 Passed |