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.
An exemplary short skill body: lean, fully actionable commands, a clearly sequenced cross-org workflow with validation checkpoints, and clean section organization. No meaningful weaknesses found.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense, lean Chinese prose that assumes Claude's competence — no basic-concept explanations — where every line states a rule, command, or decision; well below 50 lines and free of padding. | 3 / 3 |
Actionability | Concrete executable commands (dws profile list --format json, dws profile switch <selector|->, dws auth login/status) with explicit selector formats and JSON field names (corpId, isOrgCurrent) make guidance copy-paste ready. | 3 / 3 |
Workflow Clarity | The cross-org aggregation is laid out as numbered steps ①–④ with explicit decision checkpoints ("命中即用，全部组织都没有才追问用户") and destructive-op confirmation guardrails, satisfying the validation-checkpoint requirement. | 3 / 3 |
Progressive Disclosure | Under 50 lines with no external bundle references, organized into clearly headed sections (触发条件/命令/跨组织铁律/聚合/安全护栏) — meeting the rubric's "under 50 lines, no external references" exception for a score of 3. | 3 / 3 |
Total | 12 / 12 Passed |