Content
100%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.
An exemplary short skill: lean, fully executable, and well-organized, with genuinely non-obvious gotchas and an explicit validation checkpoint in its read-back workflow. Nothing material is missing for a skill of this scope.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~40-line body is lean and assumes competence: a commented command block plus terse Gotchas that each convey non-obvious facts (stdout/stderr split, frontmatter-date sorting, in-progress exclusion). No padding or explanations of known concepts, matching the top anchor; not 4 because there is nothing to trim. | 5 / 5 |
Actionability | All commands are copy-paste ready and cover the common cases: `minutes list`, `--limit 20`, `-t memo`/`-t meeting`, `minutes get "<exact path>" --json`, and `minutes status`. Fully executable with concrete expected output fields (`title`, `date`, `content_type`, `path`); not 4 because no key detail is missing. | 5 / 5 |
Workflow Clarity | This is a simple single-purpose skill whose one action is unambiguous, and the read-back workflow carries an explicit validation checkpoint ("require exit status 0") plus an error-avoidance rule ("Never reopen a result path with the host Read tool"). Not a destructive/batch operation, so no validation cap applies; not 4 because the sequence and checkpoints present are already explicit. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines with no need for external references (none exist in the bundle), and content is organized into clear Usage / Output / Gotchas sections — the rubric's stated condition for a top score. Not 4 because there is no inline content that belongs in a separate file. | 5 / 5 |
Total | 20 / 20 Passed |