Content
65%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 skill is highly actionable with concrete commands and useful gotchas, but it is verbose for a SKILL.md and has a dangling reference to a missing file. Destructive operations lack validation checkpoints, capping workflow clarity.
Suggestions
Fix or remove the dangling reference to references/message-composition.md on line 290 (the file does not exist under references/).
Move the large Python smtplib attachment example and/or the full config.toml block into a reference file to slim the SKILL.md body.
Add a verification step for destructive operations (e.g. confirm the message ID before 'message delete', or list before deleting) to introduce a validation checkpoint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~275-line body is mostly efficient command/gotcha reference, but the large inline Python smtplib block and duplicated 163-mailbox guidance (appearing both in the config section and again in tips) could be tightened or moved to a reference. | 3 / 5 |
Actionability | Provides copy-paste-ready bash commands for every common operation and a complete, executable Python attachment example covering the common cases. | 5 / 5 |
Workflow Clarity | Commands are organized clearly, but destructive operations like 'message delete' and batch moves lack explicit validation/verification checkpoints; the rubric caps workflow clarity at 3 when destructive ops have no validation. | 3 / 5 |
Progressive Disclosure | Section headers give reasonable structure and one real reference (configuration.md) is linked, but the body also references a non-existent references/message-composition.md (dangling), and large blocks (Python attachment, full config) are inlined rather than split out. | 3 / 5 |
Total | 14 / 20 Passed |