Readwise Reader 读者画像构建技能 - 基于阅读历史分析，实现个性化内容推荐与体验优化

build-persona by readwiseio/readwise-skills

101 周安装量

109 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/readwiseio/readwise-skills --skill build-persona

自动化数据分析知识管理

🇨🇳中文介绍

您正在基于用户的 Readwise Reader 库构建一个读者画像。此画像文件将被其他技能（如 triage、quiz 等）用来个性化他们的体验。

Readwise 访问

检查 Readwise MCP 工具是否可用（例如 mcp__readwise__reader_list_documents）。如果可用，请全程使用它们（并将此上下文传递给子代理）。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>、readwise highlights <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。

欢迎语

以简短介绍开始：

构建画像 · Readwise Reader

我将分析您的阅读历史——保存项、高亮和标签——并在当前目录中构建一个 reader_persona.md 个人资料。其他技能（triage、quiz）将使用此文件来个性化他们的输出，以匹配您的偏好。

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

联系我们

第一阶段：快速扫描

子代理应进行重点扫描，以快速构建一个坚实的初始画像：

收集数据。 并行运行以下所有操作（一批工具调用）：
- 4 次高亮搜索： 使用 mcp__readwise__readwise_search_highlights 和 4 个宽泛的查询（例如 "ideas strategy product"、"learning technology culture"、"writing craft creativity"、"business leadership growth"），每个查询设置 limit=50。这些是语义/向量搜索，因此宽泛的多词查询效果很好。高亮内容成本低且信息量大——可以广泛撒网。
- 4 次文档列表： 从每个非订阅源位置使用 mcp__readwise__reader_list_documents：location="new"、location="later"、location="shortlist" 和 location="archive"，每个设置 limit=100。如果合并结果非常稀疏（总计 < 20 个文档），也可以尝试不使用位置过滤器或使用 location="feed" 作为后备方案。仅获取元数据：response_fields=["title", "author", "category", "tags", "site_name", "summary", "saved_at", "published_date"]。不要获取完整内容。
- 标签： 使用 mcp__readwise__reader_list_tags 来了解他们的组织系统。
高效解析结果。 文档列表的 JSON 响应可能非常大（超过 25k 个令牌）。不要尝试使用 Read 工具读取它们——这会达到令牌限制并浪费重试次数。相反，使用一个包含 python3 脚本的 Bash 调用来一次性提取和汇总所有数据。该脚本应一起解析所有结果文件并输出：
- 按类别统计的文档数量
- 前 20 个网站、作者和标签
- 每月保存速度
- 最近 3 周内保存的所有文档（标题、类别、作者、日期）
- 具有代表性的高亮文本样本及其来源标题/作者
撰写画像。 将 reader_persona.md 写入当前工作目录，包含以下部分：
- 身份与角色 —— 他们看起来是谁（职业、角色、行业）
- 核心兴趣 —— 主要主题和话题，按频率和新近度排序
- 阅读个性 —— 他们如何阅读（大量保存但有选择性地阅读？大量高亮？偏好短篇还是长篇？）
- 当前关注点 —— 过去 2-3 周他们保存/阅读最多的内容
- 目标与抱负 —— 从模式中推断出他们似乎在努力实现什么
- 品味与鉴赏力 —— 他们倾向于哪种思想家和风格（反传统？务实？哲学？技术？）
- 非兴趣 —— 明显缺失或回避的话题
- 筛选指导 —— 如何向此人推荐文档的具体说明（例如："以实际应用性为先导"、"连接到他们对 X 的兴趣"、"对于 AI 内容门槛很高——当内容真正新颖时再标记"）
返回画像的简要摘要（3-5 句话）以及文件的绝对路径。

子代理速度规则：

不要调用 readwise_list_highlights —— 它经常出错，并且与搜索功能重复。
不要尝试读取大型 JSON 工具结果文件——通过 Bash 使用 python3 解析它们。
将所有分析合并到一个 python 脚本中，而不是多个顺序脚本。
最大化并行工具调用。步骤 1 中的每个 API 获取都应该是单个并行批次。

第二阶段：深度扫描（可选）

在快速扫描子代理返回后，向用户展示结果并询问他们是否想要更深入的分析。如果是，则启动第二个子代理，该代理：

根据第一阶段发现的信息，使用不同的、更具体的查询获取另外 4-6 次高亮搜索（例如，如果画像显示对 AI 工具感兴趣，则搜索 "AI agents workflows automation"；如果他们阅读小说，则搜索 "fiction narrative storytelling"），每个查询设置 limit=50
使用第一阶段结果中的 next_page_cursor 对每个位置的前 100 个文档进行分页——获取每个位置的下 100-200 个文档以构建更大的样本
读取现有的 reader_persona.md，并用额外的数据丰富/重写它——更细致的部分、更有力的证据、更清晰的筛选指导
返回更改内容的摘要

每个子代理返回后

显示文件链接。 始终告诉用户：reader_persona.md 已写入 {absolute_path}。显示完整路径，以便他们可以打开它。
显示画像摘要（使用子代理返回的摘要）。
第一阶段之后：询问他们是否想要深度扫描，或者快速版本是否足够好。同时询问他们是否想要调整任何内容。
第二阶段之后（如果运行）：显示更改内容并询问他们是否想要调整任何内容。
如果需要调整， 根据他们的反馈直接编辑文件。
确认保存。 告诉他们文件已保存，以及哪些技能现在将使用它（triage、quiz、feed-catchup 等）。

🇺🇸English

You are building a reader persona for the user based on their Readwise Reader library. This persona file is used by other skills (triage, quiz, etc.) to personalize their experience.

Readwise Access

Check if Readwise MCP tools are available (e.g. mcp__readwise__reader_list_documents). If they are, use them throughout (and pass this context to the subagent). If not, use the equivalent readwise CLI commands instead (e.g. readwise list, readwise read <id>, readwise search <query>, readwise highlights <query>). The instructions below reference MCP tool names — translate to CLI equivalents as needed.

Welcome

Open with a brief introduction:

Build Persona · Readwise Reader

I'll analyze your reading history — saves, highlights, and tags — and build a reader_persona.md profile in the current directory. Other skills (triage, quiz) will use this to personalize their output to you.

I'll start with a quick pass (~1-2 min) and then you can decide if you want a deeper analysis.

Process

IMPORTANT: This skill involves fetching a lot of data. To keep the main conversation context clean, launch a Task subagent to do all the heavy lifting.

Phase 1: Quick Pass

The subagent should do a focused scan to build a solid initial persona fast:

Gather data. Run ALL of these in parallel (one batch of tool calls):
- 4 highlight searches: mcp__readwise__readwise_search_highlights with 4 broad queries (e.g. "ideas strategy product", "learning technology culture", "writing craft creativity", "business leadership growth") with limit=50 each. These are semantic/vector searches so broad multi-word queries work well. Highlights are cheap and high-signal — cast a wide net.
- 4 document lists: mcp__readwise__reader_list_documents from each non-feed location: location="new", location="later", location="shortlist", and location="archive" with limit=100 each. If the combined results are very sparse (< 20 docs total), also try without a location filter or with as a fallback. Only fetch metadata: . Do NOT fetch full content.

Subagent speed rules:

Do NOT call readwise_list_highlights — it often errors and is redundant with search.
Do NOT try to Read large JSON tool-result files — parse them with python3 via Bash.
Combine all analysis into ONE python script, not multiple sequential scripts.
Maximize parallel tool calls. Every API fetch in step 1 should be a single parallel batch.

Phase 2: Deep Pass (optional)

After the quick-pass subagent returns, show the user the results and ask if they want a deeper analysis. If yes, launch a second subagent that:

Fetches 4-6 more highlight searches with different, more specific queries informed by what phase 1 found (e.g. if the persona shows interest in AI tooling, search "AI agents workflows automation"; if they read fiction, search "fiction narrative storytelling") with limit=50 each
Paginates beyond the first 100 docs per location using next_page_cursor from phase 1 results — fetch the next 100-200 per location to build a much larger sample
Reads the existing reader_persona.md and enriches/rewrites it with the additional data — more nuanced sections, stronger evidence, sharper triage guidance
Returns a summary of what changed

After Each Subagent Returns

Show the file link. Always tell the user: reader_persona.md was written to {absolute_path}. Display the full path so they can open it.
Show a summary of the persona (use the subagent's returned summary).
After phase 1: Ask if they want the deep pass or if the quick version is good enough. Also ask if they want to adjust anything.
After phase 2 (if run): Show what changed and ask if they want to adjust anything.
If adjustments needed, edit the file directly based on their feedback.
Confirm saved. Tell them the file is saved and which skills will now use it (triage, quiz, feed-catchup, etc.).

Weekly Installs

101

Repository

readwiseio/read…e-skills

GitHub Stars

109

First Seen

Mar 7, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

github-copilot101

gemini-cli101

codex101

kimi-cli101

amp101

cline101

Python PDF处理教程：合并拆分、提取文本表格、创建PDF文件

62,800 周安装

response_fields=["title", "author", "category", "tags", "site_name", "summary", "saved_at", "published_date"]

Tags: mcp__readwise__reader_list_tags to understand their organizational system.

Parse results efficiently. The JSON responses from document lists can be large (25k+ tokens). Do NOT try to read them with the Read tool — it will hit token limits and waste retries. Instead, use a single Bash call with a python3 script to extract and summarize all the data at once. The script should parse all result files together and output:

Document counts by category
Top 20 sites, authors, and tags
Save velocity by month
All docs saved in the last 3 weeks (title, category, author, date)
A representative sample of highlight texts with their source titles/authors

Write the persona. Write reader_persona.md to the current working directory with these sections:

Identity & Role — Who they appear to be (profession, role, industry)
Core Interests — Top themes and topics, ranked by frequency and recency
Reading Personality — How they read (saves a lot but reads selectively? highlights heavily? prefers short or long-form?)
Current Obsessions — What they've been saving/reading most in the last 2-3 weeks
Goals & Aspirations — What they seem to be working toward, inferred from patterns
Taste & Sensibility — Thinkers and styles they gravitate toward (contrarian? practical? philosophical? technical?)
Anti-interests — Topics notably absent or avoided
Triage Guidance — Specific instructions for how to pitch documents to this person (e.g. "lead with practical applicability", "connect to their interest in X", "bar is high for AI content — flag when it's genuinely novel")

Return a brief summary (3-5 sentences) of the persona AND the absolute path to the file.