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 concrete CLI commands and a strong connection-state workflow, but it carries an unnecessary marketing intro and lacks validation guidance for its destructive document operations. Splitting the action catalogue into a reference file and adding confirmation steps would meaningfully improve it.
Suggestions
Remove or trim the opening background paragraph ("Eversign is a cloud-based platform...") since Claude does not need the product pitch.
Add an explicit confirmation/validation step before destructive actions, e.g. verify the document hash with get-document and confirm with the user before running delete-document, trash-document, or cancel-document.
Move the Popular actions table into a referenced file (e.g. references/actions.md) and link to it from SKILL.md to keep the overview lean.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient command-focused guidance, but the opening marketing paragraph ("Eversign is a cloud-based platform that provides legally binding e-signatures...") and prose like "so you can focus on the integration logic rather than auth plumbing" explain background Claude does not need. | 3 / 5 |
Actionability | It provides copy-paste-ready commands throughout (install, login, connection ensure, action list/run, request) plus concrete flag tables and a popular-actions table, covering the common cases with executable specifics. | 5 / 5 |
Workflow Clarity | The connection setup has a clear state-machine sequence with polling feedback loops, but destructive actions (delete-document, trash-document, cancel-document) are listed without any validation or confirmation checkpoint, capping this dimension at 3. | 3 / 5 |
Progressive Disclosure | The skill is a single well-organized file with clear section headers and no nested references (no bundle files exist), so structure is good; it sits just below a 5 because the popular-actions table is somewhat bulky inline and there are no signaled reference files for deeper detail. | 4 / 5 |
Total | 15 / 20 Passed |