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 minimal skill body: concrete commands, explicit exit-status validation with failure handling, and only user-specific context that Claude could not know. The only structural note is that the opening lines partially restate the frontmatter description, which is a negligible cost for orientation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is either operational or user-pipeline-specific (the Minutes watcher, ghost context) — knowledge Claude cannot infer — with no padding or explanation of known concepts, matching the lean-and-efficient anchor. | 5 / 5 |
Actionability | Both commands are copy-paste ready with exact flags ("minutes list --content-type memo --limit 20", "minutes get \"<exact path>\" --json") and cover the common list-then-drill-in cases, matching the fully-executable anchor. | 5 / 5 |
Workflow Clarity | The four steps are clearly sequenced with explicit validation checkpoints ("Require exit status 0" at both invocations) and error-recovery paths ("If the CLI is unavailable or fails, report the memo source unavailable"), plus safe-fallback guidance for the follow-up fetch. | 5 / 5 |
Progressive Disclosure | The skill is under 50 lines, needs no external references (none of references/, scripts/, assets/ exist), and content is organized into clearly headed sections; per the simple-skill guideline this scores full marks. | 5 / 5 |
Total | 20 / 20 Passed |