Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alizeeblack-code/zhihu-mcp --skill research-on-zhihugit clone --depth 1 https://github.com/alizeeblack-code/zhihu-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alizeeblack-code/zhihu-mcp/research-on-zhihu)<a href="https://agentmods.dev/skills/alizeeblack-code/zhihu-mcp/research-on-zhihu"><img src="https://agentmods.dev/badge/skills/alizeeblack-code/zhihu-mcp/research-on-zhihu/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alizeeblack-code/zhihu-mcp/research-on-zhihu"><img src="https://agentmods.dev/badge/skills/alizeeblack-code/zhihu-mcp/research-on-zhihu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01041 |
| Opus 5 | $0.00028 | $0.00521 |
| Sonnet 5 | $0.00011 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
research-on-zhihu scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
知乎话题研究
根据用户提供的关键词或话题,在知乎上进行系统性研究,输出结构化报告。
适用场景
- 用户说"帮我研究一下 XXX"、"知乎上怎么看 XXX"、"XXX 的口碑如何"
- 用户想了解某个话题在知乎上的讨论情况
- 竞品分析、舆情调研、观点收集
工作流程
用户输入关键词/话题
│
├─ Step 1: 搜索知乎内容
│
├─ Step 2: 筛选高质量问题
│
├─ Step 3: 逐个获取问题详情和高赞回答
│
├─ Step 4: 读取关键回答的评论(可选)
│
└─ Step 5: 综合分析,输出研究报告
Step 1: 搜索内容
使用 search_content 搜索关键词,获取相关内容列表。
search_content(keyword="用户关键词", sort="relevance", count=10)
- 默认按相关性排序
- 如果用户关心最新讨论,改用
sort="newest" - 如果用户关心最热讨论,改用
sort="most_upvoted"
检查搜索结果,如果结果太少或不相关,尝试:
- 调整关键词(同义词、更宽泛/更具体的表述)
- 切换排序方式
- 告知用户搜索结果有限
Step 2: 筛选高质量问题
从搜索结果中筛选出最相关的 2-3 个问题(type 为 "question" 或 "answer")。
筛选标准:
- 标题与用户关心的话题高度相关
- 优先选择有较多回答的问题
- 忽略明显偏题或过于宽泛的问题
Step 3: 获取问题详情和高赞回答
对筛选出的每个问题,使用 get_question_detail 获取详情:
get_question_detail(question_id="问题ID")
返回内容包含:
- 问题标题、描述、话题标签
- 关注数、浏览数、回答数
- Top 回答列表(作者、摘要、点赞数、answer_id、url)
对于高赞回答(点赞数较高的前 2-3 个),使用 get_answer_detail 获取完整内容:
get_answer_detail(question_id="问题ID", answer_id="回答ID")
Step 4: 读取评论(可选)
如果需要更深入的分析,或用户明确要求,对关键回答获取评论:
get_comments(url="回答的完整URL", count=10)
评论可以揭示:
- 对回答观点的补充和反驳
- 真实用户的使用体验
- 争议焦点
仅在以下情况读取评论:
- 用户明确要求看评论
- 回答的评论数很高(>50),说明有争议
- 需要验证回答中的说法
Step 5: 输出研究报告
综合所有收集的信息,输出结构化报告:
## 知乎研究报告:{话题}
### 概览
- 搜索关键词:XXX
- 相关问题数:X 个
- 分析回答数:X 个
- 总浏览量:约 X 万
### 主流观点
1. **观点一**(来源:问题标题 / 作者名,X 赞)
- 核心论点摘要
2. **观点二** ...
### 争议与分歧
- 争议点 A:正方观点 vs 反方观点
- 争议点 B ...
### 关键洞察
- 洞察 1
- 洞察 2
### 数据来源
- [问题标题1](URL) — X 个回答,X 关注
- [问题标题2](URL) — X 个回答,X 关注
注意事项
- 如果搜索结果为空,先告知用户,建议换个关键词
- 不要一次性获取太多回答详情,2-3 个高赞回答通常足够
- 保持客观,如实呈现不同观点,不要过度总结或偏向某一方
- 注明数据来源(问题链接、作者、点赞数),方便用户验证
- 如果话题敏感或涉及专业领域,提醒用户知乎观点仅供参考
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 135 lines · 55 tokens per session scan A 0570560ad706
research-on-zhihu is a skill published in the GitHub repository alizeeblack-code/zhihu-mcp (4 stars, last pushed 6mo ago), licensed MIT. It adds 55 tokens to every session and 1,041 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…