Content
82%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, highly actionable workflow doc with concrete commands, a clear sequence, and a useful processing checklist. Its only notable gaps are mild redundancy between the scenario list/diagram and the prose, and the absence of explicit validation feedback loops.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and avoids explaining known concepts; critical gotchas (ISO 8601-only dates, mandatory --complete=false) earn their tokens. It is not a 5 because the '适用场景' list partly duplicates the description's triggers and the ASCII diagram overlaps with the step prose. | 4 / 5 |
Actionability | Provides fully executable, copy-paste-ready commands covering the common cases (today default, ISO date range, pending filter, --due-end, --page-all) plus a concrete output template and specific RSVP/sorting/conflict rules — matching the fully-executable anchor. | 5 / 5 |
Workflow Clarity | A clear 3-step sequence with an ASCII flow diagram and a 6-rule processing checklist for the summary step. It is not a 5 because there are no explicit validation steps or error-recovery feedback loops, though the read-only nature means the destructive/batch cap does not apply. | 4 / 5 |
Progressive Disclosure | References to sibling skills (lark-shared, lark-calendar, lark-task) are well-signaled via the critical top note and a dedicated 参考 section, one level deep, with command detail appropriately delegated outward. It is not a 5 because the skill is a single inline file with no local reference bundle to split sub-feature detail into. | 4 / 5 |
Total | 17 / 20 Passed |