Agent skill

Yao Weread Skill

by yaojingang in yaojingang/yao-open-skills

当用户需要分析微信读书阅读历史、生成读书报告、可视化阅读统计、笔记、书架、词云、热力图、雷达图,或导出精排 HTML 报告时使用。也适用于创建 AI 创业者示例阅读报告。不用于通用图书推荐,或不生成报告的原始微信读书 API 查询。

MITAuto-check passed

Install Yao Weread Skill

skills CLI
$ npx skills add yaojingang/yao-open-skills --skill yao-weread-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install yaojingang/yao-open-skills yao-weread-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/yaojingang/yao-open-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/yao-weread-skill .claude/skills/yao-weread-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
yao-weread-skill
GitHub stars
1.3k
Token cost
~532 tokens
SKILL.md length
99 words
Files
13 (incl. scripts, references)
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

当用户需要分析微信读书阅读历史、生成读书报告、可视化阅读统计、笔记、书架、词云、热力图、雷达图,或导出精排 HTML 报告时使用。也适用于创建 AI 创业者示例阅读报告。不用于通用图书推荐,或不生成报告的原始微信读书 API 查询。

  • Works in 6 steps: 调用 API 前先阅读微信读书 skill 文档 → 运行 scripts/generate_weread_report.py。 → 检查生成的 HTML 至少包含 20 个图表面板,没有 TODO、占位文本或内嵌… → …
  • SKILL.md covers 输入, 输出, 工作流 and 命令, plus 2 more sections
  • Runs Python scripts from its folder; calls python3; needs WEREAD_API_KEY

What it does

Yao Weread Skill is an agent skill from yaojingang/yao-open-skills. 当用户需要分析微信读书阅读历史、生成读书报告、可视化阅读统计、笔记、书架、词云、热力图、雷达图,或导出精排 HTML 报告时使用。也适用于创建 AI 创业者示例阅读报告。不用于通用图书推荐,或不生成报告的原始微信读书 API 查询。

Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts and reference files (for example `README.md`, `agents/interface.yaml` and `examples/ai-founder-report/README.md`).

The repository describes itself as: OpenYao public skills collection: reusable AI assets for decision-making, business analysis, tutorials, research evidence gathering, and document generation. The licence is MIT.

Example prompts

  • “/yao-weread-skill”

Requirements

  • Python 3
  • A credential in WEREAD_API_KEY

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. 调用 API 前先阅读微信读书 skill 文档
  2. 运行 scripts/generate_weread_report.py。
  3. 检查生成的 HTML 至少包含 20 个图表面板,没有 TODO、占位文本或内嵌 API key。
  4. 检查矩形树图、热力图、横向条形图等高密度图表没有被默认边距压缩,没有右侧空白导致标签截断。
  5. 检查读者画像模块:金句必须来自画像划线清单第一条;真实账号模式不得编造划线,划线不足 20 条时如实少展示。
  6. 如果用户要求视觉验证,或报告排版有实质变化,使用浏览器打开生成的 HTML,并检查桌面、平板宽度和窄屏宽度。

What it can do on your machine

Read from SKILL.md and the folder at commit 093996e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • x.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • WEREAD_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Yao Weread Skill loads about 532 tokens when it runs, and up to ~2.7k if it reads all its reference files. Until then it costs about 33 tokens; SKILL.md has 99 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~532
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from yaojingang/yao-open-skills at commit 093996e, republished under its MIT licence (© yaojingang). 99 words, ~532 tokens.

Download SKILL.mdSave it as .claude/skills/yao-weread-skill/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
yao-weread-skill
description
当用户需要分析微信读书阅读历史、生成读书报告、可视化阅读统计、笔记、书架、词云、热力图、雷达图,或导出精排 HTML 报告时使用。也适用于创建 AI 创业者示例阅读报告。不用于通用图书推荐,或不生成报告的原始微信读书 API 查询。
<!--
Copyright © 2026 姚金刚. All rights reserved.
Project: yao-weread-skill
Created by: 姚金刚
Date: 2026-05-16
X: https://x.com/yaojingang
-->

Yao WeRead Skill

从微信读书账号数据生成精排中文 HTML 报告。默认范围为截至今天的最近 24 个月。

输入

  • 环境变量 WEREAD_API_KEY,格式遵循微信读书 skill 的要求。
  • 可选报告范围:--years、--start 或 --end。
  • 可选笔记深度:--max-note-books;省略或传 0 时处理微信读书返回的全部笔记书籍。
  • 可选输出目录。
  • 可选示例模式:--sample-ai-founder --sample-scale 5,不需要 WEREAD_API_KEY。

输出

流程会生成:

  • weread-report.html:参考 kami 排版风格的交互式 HTML 报告。
  • weread-report-data.json:聚合后的图表数据。
  • weread-raw-summary.json:不含密钥的 API 结构和计数摘要,便于复核。

报告还会生成一个读者画像模块:顶部诗性总结、1 条画像金句,以及从近两年划线中筛选出的最多 20 条高价值句子。原始划线和想法仅用于聚合分析与画像筛选。除非用户明确要求分享或发布,否则报告产物应视为私有内容。

工作流

  1. 调用 API 前先阅读微信读书 skill 文档:
    • shelf.md:书架计数、公开/私密规则。
    • readdata.md:阅读时长单位、周期规则、年度/月度字段。
    • notes.md:笔记分页、笔记数计算、划线/想法文本。
    • book.md:仅在需要书籍详情或阅读进度时使用。
  2. 运行 scripts/generate_weread_report.py。
  3. 检查生成的 HTML 至少包含 20 个图表面板,没有 TODO、占位文本或内嵌 API key。
  4. 检查矩形树图、热力图、横向条形图等高密度图表没有被默认边距压缩,没有右侧空白导致标签截断。
  5. 检查读者画像模块:金句必须来自画像划线清单第一条;真实账号模式不得编造划线,划线不足 20 条时如实少展示。
  6. 如果用户要求视觉验证,或报告排版有实质变化,使用浏览器打开生成的 HTML,并检查桌面、平板宽度和窄屏宽度。

命令

bash
python3 scripts/generate_weread_report.py --output reports/generated

常用选项:

bash
python3 scripts/generate_weread_report.py \
  --years 2 \
  --max-note-books 0 \
  --output reports/generated

AI 创业者示例报告:

bash
python3 scripts/generate_weread_report.py \
  --years 2 \
  --sample-ai-founder \
  --sample-scale 5 \
  --output reports/generated/ai-founder-sample

报告设计

  • 视觉系统遵循 references/report-design.md。
  • 图表模块遵循 references/chart-catalog.md。
  • API 字段语义和降级规则遵循 references/data-contract.md。
  • 高密度图表必须显式设置容器占满、标签换行/隐藏策略和 resize 监听,避免 ECharts 默认布局留下空白。
  • 内容画像必须基于真实划线文本生成,顶部总结可以使用统计口径生成温暖、诗性但不冒充用户原文的描述。

边界

  • 真实账号模式下,不编造微信读书响应中不存在的阅读事件、笔记文本、评分或分类。
  • AI 创业者示例模式用于在不接入真实账号时生成可复用示例报告。
  • 不导出书籍全文;只使用用户自己的划线/想法,以及微信读书 skill 可访问的元数据。
  • 不存储或打印 WEREAD_API_KEY。
  • 无法获得精确滚动日期边界时,必须清楚标注月度或年度近似口径。

© yaojingang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (scripts, references) in skills/yao-weread-skill of yaojingang/yao-open-skills.

  • SKILL.md
  • README.md
  • agents/interface.yaml
  • examples/ai-founder-report/README.md
  • examples/ai-founder-report/weread-report.html
  • manifest.json
  • references/chart-catalog.md
  • references/data-contract.md
  • references/report-design.md
  • reports/artifact-design-profile.md
  • reports/output-risk-profile.md
  • requirements.txt
  • scripts/generate_weread_report.py

Open the folder on GitHubat commit 093996e

Compare with similar skills

Yao Weread Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Yao Weread Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Yao Weread Skill this skillyaojingang/yao-open-skills1.3k—~532Automated safety check: PassMIT
Weread Year In Review Video Templatenexu-io/open-design100k—~784Automated safety check: PassApache-2.0
Yao Daemon ManagerYaoApp/yao8.1k—~1.1kAutomated safety check: PassCustom licence
Yao Agent Management ToolsYaoApp/yao8.1k—~873Automated safety check: PassCustom licence
WeRead Bookshelf and Notesteng-lin/weread-omni660—~3.3kAutomated safety check: PassMIT
Yao Audio TranscriptionYaoApp/yao8.1k—~416Automated safety check: PassCustom licence

Similar skills

  • WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories.

    100k GitHub stars~784 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Starts, lists, checks, restarts and stops long-running background services through Yao daemon tools, reporting the verified port and URL of each.

    8.1k GitHub stars~1.1k tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Lists, downloads, references and deploys agents on a Yao host through five bash-invoked tools, keeping edits to the smith namespace while allowing read-only study of any agent.

    8.1k GitHub stars~873 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • WeRead Bookshelf and Notes

    teng-lin/weread-omni

    Searches books, manages the shelf, reads public-account articles and reads or writes highlights and notes in WeRead through the weread-omni CLI.

    660 GitHub stars~3.3k tokensUpdated 27 days ago
    Knowledge ManagementAuto-check passed
  • Transcribes audio files such as mp3, m4a, wav and webm to text with the tai audio_transcribe tool, and lists the available speech-to-text providers.

    8.1k GitHub stars~416 tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Yao Image Tools

    YaoApp/yao

    Lets an agent read and describe images through a vision model and generate or edit images from text prompts, using the tai command-line tool.

    8.1k GitHub stars~2k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed

More from yaojingang/yao-open-skills

All 16 skills in this repo
  • Yao Copyright Skill

    yaojingang/yao-open-skills

    A skill your agent uses when adding or auditing Yao copyright comment headers for an agent skill package, especially SKILL.md, README.md, references, prompts, templates, examples, scripts, YAML, or…

    1.3k GitHub stars~551 tokensUpdated 1 mo ago
    Auto-check passed
  • Yao Crux Skill

    yaojingang/yao-open-skills

    A skill your agent uses when a user is stuck in a complex real-world situation with many conflicts, limited resources, unclear priorities, or asks to identify the principal contradiction, secondary…

    1.3k GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Yao Interpreter Skill

    yaojingang/yao-open-skills

    Analyze local Agent Skill folders, SKILL.md files, or safe zip archives as untrusted input; explain purpose, trigger contract, structure, usage readiness, safety risks, evidence-backed 100-point…

    1.3k GitHub stars~545 tokensUpdated 1 mo ago
    Auto-check passed
  • Yao Positioning Skill

    yaojingang/yao-open-skills

    Generate evidence-aware positioning reports for personal IPs, courses, products, services, brands, or companies by combining positioning theory, course-marketing analysis, user intent, competitor…

    1.3k GitHub stars~805 tokensUpdated 1 mo ago
    Auto-check passed
  • Yao Bayesian Skill

    yaojingang/yao-open-skills

    Convert uncertain real-world choices into an auditable Bayesian evidence-to-action report with priors, evidence grading, posterior update, action thresholds, sensitivity checks, multi-turn decision…

    1.3k GitHub stars~956 tokensUpdated 1 mo ago
    Auto-check passed
  • Yao Business Skill

    yaojingang/yao-open-skills

    Design, diagnose, and study business models from ideas, product websites, or company names.

    1.3k GitHub stars~821 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Yao Weread Skill

What does Yao Weread Skill do?

当用户需要分析微信读书阅读历史、生成读书报告、可视化阅读统计、笔记、书架、词云、热力图、雷达图,或导出精排 HTML 报告时使用。也适用于创建 AI 创业者示例阅读报告。不用于通用图书推荐,或不生成报告的原始微信读书 API 查询。. Yao Weread Skill is an agent skill from yaojingang/yao-open-skills.

How do I install Yao Weread Skill in Claude Code?

Run `npx skills add yaojingang/yao-open-skills --skill yao-weread-skill -a claude-code`. Or copy the skill folder (skills/yao-weread-skill in yaojingang/yao-open-skills) into .claude/skills/yao-weread-skill in your project. Claude Code loads it when a task matches its description.

How do I install Yao Weread Skill in Codex?

Run `npx skills add yaojingang/yao-open-skills --skill yao-weread-skill -a codex`. Or copy the skill folder (skills/yao-weread-skill in yaojingang/yao-open-skills) into .agents/skills/yao-weread-skill in your project. Codex loads it when a task matches its description.

Can I use Yao Weread Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add yaojingang/yao-open-skills --skill yao-weread-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/yao-weread-skill, .gemini/skills/yao-weread-skill, .github/skills/yao-weread-skill and .opencode/skills/yao-weread-skill in your project.

What does Yao Weread Skill need to run?

Going by SKILL.md and its folder, Yao Weread Skill needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named WEREAD_API_KEY. Our summary lists: Python 3; A credential in WEREAD_API_KEY.

Does Yao Weread Skill access the network?

SKILL.md names 1 domain. As links in the text: x.com. This is read from the text; nothing was executed.

Is Yao Weread Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Yao Weread Skill use?

Yao Weread Skill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Yao Weread Skill use?

About 532 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.1k tokens, read only when the agent opens those files.

What are the alternatives to Yao Weread Skill?

Skills that share tags, products or a category with Yao Weread Skill: Weread Year In Review Video Template (nexu-io/open-design, 100k stars), Yao Daemon Manager (YaoApp/yao, 8.1k stars), Yao Agent Management Tools (YaoApp/yao, 8.1k stars) and WeRead Bookshelf and Notes (teng-lin/weread-omni, 660 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Yao Weread Skill?

yaojingang (a GitHub user) maintains it in yaojingang/yao-open-skills, which has 1,323 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on August 28, 2026.

Source: yaojingang/yao-open-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.