Content
88%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.
A well-structured, actionable skill body with concrete commands and an explicit validation checkpoint. It is efficient rather than fully lean, and at ~90 lines it is slightly past the simple-skill threshold where structure alone would justify a top progressive-disclosure score.
Suggestions
Tighten the 'Search coaching' section by collapsing the four vague-query bullets into a single short decision rule to improve conciseness.
Consider moving the 'Gotchas' list into a separate references file to bring SKILL.md closer to a lean overview and lift progressive_disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Efficient and assumes Claude's competence (no concept explanations), with copy-paste commands and a tight flags table; the 'Search coaching' and 'Tips' sections are somewhat verbose but actionable, so it sits between efficient and lean. | 4 / 5 |
Actionability | Fully executable guidance throughout — concrete `minutes search` examples, a flags table, exact `minutes get "<path>" --json` reauthorization, a config.toml snippet, and helper commands like `date -v-7d +%Y-%m-%d` and `qmd update && qmd embed`. | 5 / 5 |
Workflow Clarity | Single-purpose skill with an unambiguous action and an explicit validation checkpoint ('require exit status 0, and use only that response') for the reauthorize step; the simple-skill exception applies and there are no destructive/batch operations triggering the cap. | 5 / 5 |
Progressive Disclosure | Well-organized into clear sections (Usage, Flags, Output, How search works, Search coaching, Tips, Gotchas) with no nested references, but at ~90 lines it exceeds the under-50-line simple-skill threshold and the coaching/gotchas content could plausibly live in a separate reference. | 4 / 5 |
Total | 18 / 20 Passed |