Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a lean, executable command reference organized into four sequenced SOPs with explicit validation feedback loops, supported by real one-level-deep reference files and scripts. It assumes Claude's competence and splits detail appropriately across the bundle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is command-dense reference material — exact flags, tables, and SOPs — with no explanation of concepts Claude already knows; every line earns its place. | 3 / 3 |
Actionability | Provides fully executable, copy-paste-ready commands (e.g. 'dws todo task create --title … --executors <userId> --priority <10/20/30/40> --format json') plus runnable scripts and exact priority/ISO/recurrence mappings. | 3 / 3 |
Workflow Clarity | Each SOP is numbered with 解析/执行/验证 stages, mandatory 回读 validation checkpoints, explicit 禁止 lists, and batch (SOP-4) plus destructive (delete confirmation) feedback loops. | 3 / 3 |
Progressive Disclosure | SKILL.md is an overview pointing via clear markdown links to one-level-deep references (todo.md, 02-task.md, intent-guide.md, lite-recipes.md) and separate scripts — all verified to exist at the cited relative paths. | 3 / 3 |
Total | 12 / 12 Passed |