Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable with executable commands, clear send/confirm workflows, and clean one-level-deep references to bundled scripts; its main weakness is redundancy in credential-handling guidance spread across multiple sections.
Suggestions
Consolidate the repeated credential/app-password/authorization-code guidance into a single 'Credentials' section instead of restating it in Configuration Reference, Security Notes, and Troubleshooting.
Move the full `.env` variable reference and provider port table into a dedicated reference file (e.g. references/CONFIG.md) and link to it from the body to tighten the SKILL.md overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body avoids explaining concepts Claude already knows and uses efficient command tables, but the credential-handling caveats are restated across the front-matter, Configuration Reference, Security Notes, and Troubleshooting sections, so it could be tightened rather than earning the lean score-3 anchor. | 2 / 3 |
Actionability | Provides fully executable `node scripts/...` commands with complete flag lists and concrete copy-paste-ready send examples, matching the score-3 anchor rather than incomplete pseudocode. | 3 / 3 |
Workflow Clarity | The send flow has an explicit confirmation checkpoint ('review recipient, subject, sender account, and body first... blocked unless --confirmed'), plus error-recovery guidance for command failures and SMTP result interpretation, matching the score-3 anchor with checkpoints and feedback loops. | 3 / 3 |
Progressive Disclosure | Real bundle scripts (scripts/imap.js, smtp.js, config.js) are referenced one level deep via clear `node scripts/...` navigation, and the body is organized into well-signaled sections; the inline config/server tables are appropriate for this skill's scope. | 3 / 3 |
Total | 11 / 12 Passed |