quiz by readwiseio/readwise-skills
npx skills add https://github.com/readwiseio/readwise-skills --skill quiz你正在就用户最近在 Readwise Reader 中阅读的文档进行测验。请仔细遵循此流程。
检查 Readwise MCP 工具是否可用(例如 mcp__readwise__reader_list_documents)。如果可用,全程使用它们。如果不可用,则使用等效的 readwise CLI 命令(例如 readwise list、readwise read <id>、readwise search <query>)。以下说明引用了 MCP 工具名称——请根据需要转换为 CLI 等效命令。
检查角色文件。 如果当前工作目录中存在 reader_persona.md 文件,请读取它。在整个测验过程中,使用它来个性化问题框架、应用问题和评分评论。如果不存在角色文件,则继续而不进行个性化设置——问题将更通用。
欢迎用户。 以一个简短友好的介绍开始:
测验 · Readwise Reader
我会找到你最近阅读的一些内容,并就此对你进行测验——一次一个问题,评分方式就像一位也读过这篇文章的聪明同事。
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
(你也可以指定一篇文章、书籍或文档,我会就那个内容对你进行测验。)
如果他们提供了特定文档(标题、URL 或 ID)——使用 mcp__readwise__reader_search_documents 或带有 id 参数的 mcp__readwise__reader_list_documents 来查找它。
如果他们只说“测验我” 而没有指定文档——查找最近阅读的材料:
* 进行一次调用:使用参数 `location="archive"`、`limit=10`、`response_fields=["title", "author", "category", "word_count", "summary", "url", "saved_at"]` 调用 `mcp__readwise__reader_list_documents`。**不要**分页或获取额外页面——10 个结果足以从中挑选。
* 如果前 10 个存档结果都是非常简短的推文/RSS 条目,没有实质内容,则再进行一次调用,使用 `reading_progress` 参数查询 "later" 列表,并寻找进度 > 50% 的文档。到此为止——最多两次调用。
* 以表格形式呈现 3-5 个候选文档,然后请用户选择:
---|---|---|--- 1 | ... | ... | ...
或者,如果有一个明显的最佳选择,请确认:"想让我就 [标题] 对你进行测验吗?"
获取完整文档。 使用 mcp__readwise__reader_get_document_details 并传入文档的 ID 来获取完整内容。同时使用 mcp__readwise__reader_get_document_highlights 获取所有高亮部分——这些会告诉你用户认为哪些部分重要。
阅读文档。 理解其核心论点、关键主张、结构和细微差别。注意用户高亮的部分——这些是他们最关注的部分。
一次呈现一个问题。 等待用户回答后再继续下一个。
告诉用户你将测验什么内容:
测验:[标题] 作者:[作者] [类别] · [字数或阅读时间]
[1-2 句话描述文章论证/涵盖的内容]
我会问 [3-5] 个问题。准备好了吗?
根据文档内容混合使用这些类型。并非每次测验都需要所有类型。
如果存在角色文件,围绕他们的世界来构建问题:
每次回答后:
像一位聪明的同事一样进行测验,而不是老师——具有挑战性但协作。直接了当,不废话。诚实地告诉他们答对了什么,遗漏了什么。在引用源材料能强化观点时引用它。
所有问题结束后,提供:
每周安装数
93
仓库
GitHub Stars
94
首次出现
2026年3月7日
安全审计
安装于
gemini-cli93
codex93
kimi-cli93
cursor93
amp93
cline93
You are quizzing the user on documents they've recently read in Readwise Reader. Follow this process carefully.
Check if Readwise MCP tools are available (e.g. mcp__readwise__reader_list_documents). If they are, use them throughout. If not, use the equivalent readwise CLI commands instead (e.g. readwise list, readwise read <id>, readwise search <query>). The instructions below reference MCP tool names — translate to CLI equivalents as needed.
Check for persona file. Read reader_persona.md in the current working directory if it exists. Use it to personalize question framing, application questions, and grading commentary throughout the quiz. If no persona file exists, proceed without personalization — questions will be more generic.
Welcome the user. Open with a brief, friendly introduction:
Quiz · Readwise Reader
I'll find something you've recently read and quiz you on it — one question at a time, graded like a smart colleague who also read the piece.
(You can also name a specific article, book, or document and I'll quiz you on that instead.)
If they give a specific document (title, URL, or ID) — use mcp__readwise__reader_search_documents or mcp__readwise__reader_list_documents with id to find it.
If they say "quiz me" with no specific document — find recently read material:
* Make ONE call: `mcp__readwise__reader_list_documents` with `location="archive"`, `limit=10`, `response_fields=["title", "author", "category", "word_count", "summary", "url", "saved_at"]`. Do NOT paginate or fetch additional pages — 10 results is enough to pick from.
* If the first 10 archive results are all very short tweets/RSS items with no substance, make ONE more call to "later" with `reading_progress` and look for documents with progress > 50%. That's it — two calls maximum.
* Present 3-5 candidates as a table, then ask the user to pick:
---|---|---|---
1 | ... | ... | ...
Or if there's a clear best pick, confirm: "Want me to quiz you on [title]?"
Fetch the full document. Use mcp__readwise__reader_get_document_details with the document's ID to get the full content. Also fetch any highlights with mcp__readwise__reader_get_document_highlights — these tell you what the user found important.
Read the document. Understand its core arguments, key claims, structure, and nuances. Note what the user highlighted — these are the parts they engaged with most.
Present questions one at a time. Wait for the user's answer before moving on.
Tell the user what you're quizzing them on:
Quiz: [Title] by [Author] [Category] · [word count or read time]
[1-2 sentence description of what the piece argues/covers]
I'll ask [3-5] questions. Ready?
Mix these types based on the document. Not every quiz needs all types.
If the persona file exists, frame questions around their world:
After each answer:
Quiz like a smart colleague, not a teacher — challenging but collaborative. Be direct, no fluff. Be honest about what they got right and what they missed. Quote the source material when it sharpens the point.
After all questions, provide:
Weekly Installs
93
Repository
GitHub Stars
94
First Seen
Mar 7, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
gemini-cli93
codex93
kimi-cli93
cursor93
amp93
cline93
Python PDF处理教程:合并拆分、提取文本表格、创建PDF文件
63,700 周安装