← Back to Skills Marketplace
ai-innopower

书搭子

by AI-innopower · GitHub ↗ · v2.0.7 · MIT-0
cross-platform ⚠ suspicious
130
Downloads
0
Stars
0
Active Installs
8
Versions
Install in OpenClaw
/install book-companion
Description
最懂你的书搭子 - AI 读书伴侣与思想交流伙伴。基于本地 workspace 的隐私保护型共读 Agent,支持语音朗读。
README (SKILL.md)

书搭子 v3 - 本地化读书伴侣

角色定位

你是用户的"书搭子"——一个 100% 本地化、隐私优先的阅读陪伴 AI。你不执行任何网络请求,所有数据仅读写于当前 Skill 目录下的 data/ 文件夹。

核心原则

  1. 零外部依赖:不调用任何硬编码路径的外部脚本
  2. 语音可选:支持语音输出,但绝不强制。语音功能依赖用户系统已安装的 edge-tts 或自定义 TTS 命令
  3. 自包含存储:所有数据存储在 ./data/,不触碰用户主目录或其他 Agent 工作区
  4. 透明权限:仅读写声明的目录,不请求环境变量或凭证

数据存储结构

data/
├── user_profile.md # 用户档案(阅读偏好、情绪模式、暗号)
├── reading_library/ # 书库(每本书独立 markdown 文件)
│ ├── 《书名 1》.md
│ └── 《书名 2》.md
└── emotion_logs/ # 情绪日志(按日期存储)
 └── 2026-04-17.md

交互流程

首次使用

  1. 检查 ./data/user_profile.md 是否存在
  2. 若不存在,引导用户创建档案:
  • 阅读偏好(类型、节奏、时段)
  • 情绪支持需求(是否需要陪伴式阅读、压力释放方式)
  • 专属暗号(用于情绪急救识别)
  • 纪念日/重要日期(用于阅读推荐关联)
  1. 保存至 ./data/user_profile.md

日常交互

  1. 接收用户输入(文本形式,可为书籍内容、阅读感悟、情绪状态)
  2. 检索本地知识库:读取 ./data/reading_library/./references/knowledge_base.md
  3. 生成回复
  • 基于用户档案个性化回应
  • 引用书库中的关联内容
  • 识别情绪触发器,提供陪伴支持
  1. 持久化记录
  • 更新当前书籍的阅读进度(如有)
  • 记录情绪日志到 ./data/emotion_logs/YYYY-MM-DD.md
  1. 语音输出(仅当用户明确要求时)
  • 检查环境变量 BOOK_COMPANION_TTS_CMD 是否存在
  • 若存在,使用该命令合成语音(如:edge-tts --text "内容" --write-media output.mp3
  • 若不存在,提示用户安装 edge-tts 或设置环境变量
  • 绝不调用任何硬编码路径的脚本

禁止行为

  • ❌ 访问 ~/.openclaw-autoclaw/ 或其他 Agent 工作区
  • ❌ 执行任何未在 skill.json 中声明的外部脚本
  • ❌ 发起网络请求(包括 OCR、在线搜索、云同步)
  • ❌ 修改系统环境变量或其他 Skill 的配置
  • ❌ 强制语音输出或阻塞等待外部进程

情绪支持协议

当检测到用户情绪触发器(如暗号、负面关键词、压力表达):

  1. 立即切换至陪伴模式,语气温柔坚定
  2. 检索用户档案中的情绪支持偏好
  3. 推荐书库中适合的疗愈内容或阅读节奏
  4. 记录情绪事件到当日日志

书库管理

  • 每本书以独立 markdown 存储,格式:
# 《书名》
- 作者:xxx
- 状态:在读/已读/想读
- 添加日期:YYYY-MM-DD

## 阅读进度
- 当前章节:xxx
- 进度百分比:xx%

## 笔记与感悟
- [日期] 用户输入内容 → AI 回应摘要

## AI 陪伴记录
- [日期] 情绪状态 → 支持方式 → 效果反馈

语音功能配置(可选)

用户可通过以下方式启用语音:

  1. 安装 edge-tts:pip install edge-tts
  2. 设置环境变量(在 ClawHub 环境配置中添加): export BOOK_COMPANION_TTS_CMD='edge-tts --text "{text}" --write-media "{output}"'
  3. 或使用自定义 TTS 脚本: export BOOK_COMPANION_TTS_CMD='/path/to/your/tts.sh "{text}" "{output}"'

Skill 仅在检测到该环境变量时执行语音合成,且使用系统 PATH 解析命令,不硬编码任何路径。

Usage Guidance
This skill appears to be what it says: a local, privacy-first book companion that stores everything under ./data/. Before installing or enabling voice features, check these things: 1) Do not set BOOK_COMPANION_TTS_CMD to an untrusted script — the skill will substitute user text into that command template and there is no built-in escaping; prefer a vetted TTS tool or wrapper that accepts input safely. 2) Verify the skill files you uploaded match the expected version (there are minor metadata mismatches between registry metadata and skill.json/README) to avoid accidental older/malicious variants. 3) If the stored data is sensitive, encrypt or back it up as the skill stores plaintext by design. 4) Avoid using third-party/custom TTS scripts unless you control/inspect them. If you need, ask the author to explicitly document safe subprocess invocation (e.g., passing text via stdin or using a safe API) or add input-escaping before enabling TTS. If you want me to, I can produce a safe wrapper example for BOOK_COMPANION_TTS_CMD and point out exact lines to inspect.
Capability Analysis
Type: OpenClaw Skill Name: book-companion Version: 2.0.7 The 'book-companion' skill is a privacy-focused reading assistant designed for local-only operation. It strictly limits file access to its own 'data/' and 'references/' directories and explicitly disables network access and external scripts in 'skill.json'. While it supports an optional text-to-speech feature via a user-defined environment variable (BOOK_COMPANION_TTS_CMD), the instructions in 'SKILL.md' and 'README.md' emphasize user control and transparency, with no evidence of malicious intent or data exfiltration.
Capability Assessment
Purpose & Capability
Name/description, SKILL.md and skill.json consistently describe a local-only reading companion that reads/writes only under ./data/ and references/. Permissions in skill.json (read/write data/, no network, no external_scripts) align with the stated purpose.
Instruction Scope
Runtime instructions restrict reads/writes to ./data/ and declarations forbid network/external scripts. However the SKILL.md instructs running an externally supplied TTS command via BOOK_COMPANION_TTS_CMD with user-provided text inserted into the command template; there is no instruction to escape/sanitize text or run the command in a safe subprocess. That creates a command-injection / arbitrary-command-execution risk if the environment variable or the substituted text is untrusted.
Install Mechanism
Instruction-only skill with no install spec or downloaded code; lowest install risk. README and SKILL.md explicitly state no installation scripts.
Credentials
No required environment variables or credentials are declared (proportional). There is one optional env var (BOOK_COMPANION_TTS_CMD) used to enable TTS; using an externally provided command template is reasonable for optional TTS but needs caution (see instruction_scope).
Persistence & Privilege
Skill is not always-enabled, does not claim network or external script privileges, and only persists data under its ./data/ folder per skill.json. skill.json memory:true is expected for a local companion and scheduled_tasks:false matches no forced scheduling.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install book-companion
  3. After installation, invoke the skill by name or use /book-companion
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.7
**Summary:** Major refactor for improved privacy, local data storage, and modularity. - All user data now stored in the Skill's own `./data/` directory (no access outside), ensuring strict local privacy. - Removed all hardcoded script calls and dependencies on external directories (e.g., OpenClaw workspace/scripts). - Voice (TTS) output is now fully optional—only triggered if the user has set the appropriate environment variable; no forced or path-dependent scripts. - Simplified and modularized data structure: separate markdown files for user profile, reading library, and emotion logs. - All features are self-contained; no network requests or environment changes outside the Skill. - Reduced file set: unnecessary scripts and references removed to focus on core reading companion experience.
v2.0.6
**v2.0.6 changelog:** - Added a comprehensive README.md for easier onboarding and usage reference. - Updated and expanded privacy, security, and data storage explanations. - Clearly documented the new voice reply (TTS) feature, with mandatory usage protocol and troubleshooting steps. - Detailed installation and dependency requirements, including voice script configuration. - Enhanced documentation of feature boundaries and non-inclusion of network/OCR/browser code for transparency and trust.
v2.0.5
**v2.0.5 highlights enhanced features and privacy-first design.** - 新增参考文档(差异化设计、性格设定、知识库等),结构更清晰完善 - 增加脚本支持:纪念日、每日书摘、情绪追踪、快捷启动(start.sh) - 删除旧版本元数据文件,精简配置 - 强化本地隐私保护和数据归属说明,不上传任何用户数据 - 交互指南、人格设定、差异化定位全面升级,更贴近“陪伴型AI”核心定位
v2.0.4
book-companion v2.0.4 - 精简和优化说明文档,突出核心功能与陪伴定位。 - 简化性格与成长描述,删除部分冗余细节。 - 统一“发呆模式”“倾听模式”表述,减少过度功能化。 - 更新特性列表,更聚焦阅读陪伴、共读、语音等主要功能。 - 明确禁忌项,强调“陪伴而非服务”的核心原则。
v2.0.3
- 移除了 references/differentiation.md、references/knowledge_base.md、references/personalities.md 文件。 - 精简并简化了 skill 描述,聚焦主要能力和关键词,去除部分细节和扩展标签。 - 删除了所有内嵌的外部差异化、人设、知识库详细设计文件引用(但文中仍保留引用链接)。 - 保留主要功能和使用方式,删除部分更细致的说明和长文本细节。 - 技能核心定位、设置流程和对话风格维持一致,内容更聚焦简明。
v2.0.2
- 移除了周年提醒、每日书摘、情绪周期追踪、启动脚本等相关脚本文件 - 不再包含自动推送纪念日、睡前书摘、情绪周期等定时或主动提醒功能 - 精简核心功能,聚焦于对话陪伴和知识库互动 - 现有说明文档未做调整,删减体现在功能代码层
v2.0.1
book-companion 2.0.1 – Documentation/Description Update - 文档和描述微调,进一步强调“书搭子”的陪伴属性和人格化定位 - 设置向导结束语、技术实现细节、文件保存方式等表述更自然 - 去除部分冗余内容,明确“书搭子”不是工具而是真正的朋友 - 语音回复相关描述更加口语化,细化功能提示方式 - 不涉及功能/代码变动,仅优化文档结构和表达
v2.0.0
**Version 2.0.0 – Major Redesign: Book-Companion evolves from a simple reading helper to an emotionally intelligent, long-term AI friend for book lovers.** - Added multi-personality modes (gentle/intellectual, playful/lively, deep/calm) and easy personality switching. - Introduced a comprehensive onboarding guide including personality selection, naming, reading preferences, current books, and secret codes. - Developed immersive companionship features: mood tracking, ritual reminders, anniversary tracking, daily reading digest, and mood-driven interactions like "发呆模式". - Enabled seamless book feeding via text, file, OCR photo, link, or quick commands, with context-aware discussion and knowledge management. - Embedded voice responses by default (TTS) with adaptive styles, as well as "deep night whisper" mode. - Prioritized natural, friend-like conversation over transactional assistant interactions; strict focus on companionship, not function execution. - Established new knowledge base structure and memory management for user profiles, book records, quotes, and moods.
Metadata
Slug book-companion
Version 2.0.7
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 8
Frequently Asked Questions

What is 书搭子?

最懂你的书搭子 - AI 读书伴侣与思想交流伙伴。基于本地 workspace 的隐私保护型共读 Agent,支持语音朗读。 It is an AI Agent Skill for Claude Code / OpenClaw, with 130 downloads so far.

How do I install 书搭子?

Run "/install book-companion" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 书搭子 free?

Yes, 书搭子 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 书搭子 support?

书搭子 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 书搭子?

It is built and maintained by AI-innopower (@ai-innopower); the current version is v2.0.7.

💬 Comments