analyze-zhihu-question — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited analyze-zhihu-question (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
对一个具体的知乎问题进行深度分析,阅读高赞回答全文和评论,输出观点总结。
用户输入问题 URL 或 ID
│
├─ Step 1: 解析输入,获取 question_id
│
├─ Step 2: 获取问题详情和回答列表
│
├─ Step 3: 逐个阅读高赞回答全文
│
├─ Step 4: 获取高争议回答的评论
│
└─ Step 5: 输出深度分析从用户输入中提取 question_id:
https://www.zhihu.com/question/12345678 → question_id = 12345678https://www.zhihu.com/question/12345678/answer/87654321 → question_id = 1234567812345678 → 直接使用get_question_detail(question_id="12345678")从结果中获取:
向用户简要汇报问题概况:
问题:{标题}
话题:{话题1}、{话题2}
{回答数} 个回答 · {关注数} 人关注 · {浏览数} 次浏览
正在阅读 Top {N} 高赞回答...根据回答列表,选取点赞数最高的 3-5 个回答,逐个获取全文:
get_answer_detail(question_id="12345678", answer_id="回答ID")对每个回答,提取:
如果回答内容很长,提取关键段落和结论,不需要逐字复述。
对以下回答获取评论:
get_comments(url="回答URL", count=15)关注评论中的:
## {问题标题}
> {回答数} 个回答 · {关注数} 人关注 · {浏览数} 次浏览
> 话题:{话题列表}
### 观点分布
**阵营 A:{观点概括}**(约 X 位答主)
- {作者1}({点赞数} 赞):{核心观点}
- {作者2}({点赞数} 赞):{核心观点}
**阵营 B:{观点概括}**(约 X 位答主)
- {作者3}({点赞数} 赞):{核心观点}
### 共识
- 大部分回答都认同的点
### 争议焦点
- 争议 1:A 认为... 但 B 认为...
- 争议 2 ...
### 高质量回答推荐
1. [{作者}的回答]({URL}) — {点赞数} 赞,{一句话推荐理由}
2. ...
### 评论区亮点
- {评论摘要}(来自 {作者} 回答下的评论)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.