Content
96%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 concise, actionable SKILL.md body: exact commands, complete parameter documentation, explicit dry-run validation, and error-code recovery guidance with no wasted tokens. The only structural weakness is that the referenced script path cannot be verified against the provided bundle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean and entirely operational — workflow steps, a flag table, constraints, and output fields — with zero padding or explanation of concepts Claude already knows; every token earns its place. | 5 / 5 |
Actionability | Fully executable guidance: exact commands ('python scripts/publish_wechat.py <输入> --dry-run'), a complete argument list, required config fields (app_id/app_secret/author), expected JSON output fields, and concrete error-code remedies — copy-paste ready for the common cases. | 5 / 5 |
Workflow Clarity | The 5-step workflow is clearly sequenced with an explicit validation checkpoint ('发布前优先做 --dry-run,检查标题、摘要和渲染 HTML') and error-recovery guidance for 48001 (keep draft, publish manually) and 41005 (retry with --cover-image), matching the anchor with validation steps and feedback for error recovery. | 5 / 5 |
Progressive Disclosure | A short, well-sectioned single-file skill whose only reference ('scripts/publish_wechat.py') is one level deep and clearly signaled, but that referenced script is not present in the bundle (no scripts/ directory exists), leaving a minor verification gap that keeps it below anchor 5. | 4 / 5 |
Total | 19 / 20 Passed |