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.
The body is highly actionable with copy-paste-ready commands, accurate parameter tables, and an explicit output schema, all well-organized with clear references to real script files. Minor conciseness loss comes from repeated fallback disclaimers and a slightly scattered workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly lean: parameter tables, real command examples, and an output schema earn their place; not a 5 because the 小红书/微博 fallback disclaimer is repeated ~5 times across sections and could be consolidated. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready commands with concrete examples (e.g. `python3 scripts/bilibili_search.py "机器学习教程" --limit 5`), full parameter tables, env-var conventions, and a documented JSON output schema covering the common cases. | 5 / 5 |
Workflow Clarity | Sections are logically sequenced (credentials → stability → deps → cookie → params → output) with fallback checkpoints ("若安装失败…改用 browser-use"); not a 5 because there is no explicit validate-output/retry loop and recovery guidance is scattered rather than a single ordered workflow. | 4 / 5 |
Progressive Disclosure | Well-organized into clear headers with one-level-deep references to real bundle files (scripts/bilibili_search.py, zhihu_search.py, douyin_search.py); not a 5 because per-script parameter docs are inlined in SKILL.md rather than split into separate reference files, though the size makes inline placement reasonable. | 4 / 5 |
Total | 17 / 20 Passed |