← 返回 Skills 市场
199
总下载
1
收藏
0
当前安装
8
版本数
在 OpenClaw 中安装
/install wechat-favorites
功能描述
微信收藏夹导出、智能分类与知识库管理。支持从解析后的 favorite.db 导出收藏记录、三级分类体系（一级9类 + 二级57标签 + 跨领域6类）、LLM 智能增强（可选）、批量导入 IMA 知识库（可选）。核心功能支持离线使用，网络功能默认关闭。
安全使用建议
This skill appears to do what it says: local decryption/export/classification of WeChat favorites, with optional LLM classification and optional bulk import to Tencent IMA. Before installing/running, consider: 1) Data sensitivity — decrypt_db will attempt to decrypt local WeChat DB files if you supply a keys file (all_keys.json); ensure that all_keys.json was created by you with a trusted tool and that you are comfortable decrypting the files on this machine. 2) Auto-detection — config.py may auto-detect WeChat data directories and will write config.json to the script directory; if you prefer manual control, create config.json yourself. 3) Network/credentials are optional — set SAFE_MODE=1 to force offline operation; if you enable LLM or IMA, provide LLM_API_KEY / IMA credentials only in trusted environments and understand which fields are sent (LLM code builds prompts containing title/source/url; import_ima sends URL lists to ima.qq.com). 4) Code quality notes: import_ima.py contains a bug (uses undefined variable batch_count) which may raise an exception; llm and incremental scripts expect LLM_API_KEY for network usage. 5) Least privilege: run in an isolated/trusted environment and review/verify config and credential files (~/.config/ima, environment variables) before use. If you want greater assurance, run the scripts on a copy of your data or inspect the few omitted helper files (e.g., find_all_keys.py if you plan to extract keys) so you understand how keys are produced.
能力标签
能力评估
Purpose & Capability
Name/description (WeChat favorites export, classification, optional LLM/IMA import) matches the included scripts: decrypt_db.py, export_favorites.py, classify_favorites.py, llm_*.py and import_ima.py. Required operations (reading favorite.db, classifying, optionally calling LLM or IMA) align with the stated capability. The skill does expect an all_keys.json to decrypt SQLCipher DBs (decrypt_db.py prints '请先运行 find_all_keys.py'), and SKILL.md explicitly suggests pre-parsing favorite.db using other tools — together these are consistent with the described workflow.
Instruction Scope
SKILL.md and scripts limit actions to local file parsing/processing and optional network calls for LLM and IMA. Sensitive actions are limited: decrypt_db requires a local all_keys.json and reads files under the detected db_storage path; llm_classify only sends title/source/url (not full content) per the prompt build. The skill will auto-detect and write a local config.json and may scan user directories (APPDATA, ~/Documents/xwechat_files, etc.) to find WeChat db paths — this is expected but worth noting.
Install Mechanism
No install spec; code is instruction-only and runs locally. No remote download/extract behavior observed. This minimizes supply-chain risks compared with arbitrary installers.
Credentials
The skill declares no required env vars but the code optionally reads SAFE_MODE, LLM_API_KEY/LLM_API_URL/LLM_MODEL and IMA_CLIENT_ID/IMA_API_KEY/IMA_KB_ID (or files under ~/.config/ima). These are proportionate to the optional LLM and IMA features and are documented in SKILL.md. Users should verify and control any API keys placed in environment or ~/.config/ima before use.
Persistence & Privilege
always:false and normal model invocation. The skill writes/updates its own config.json (scripts/config.py auto-saves detected db_dir) and creates output directories (decrypted/, exported_favorites/, exported state/log files) — expected for a local data processing tool. It does not modify other skills or system-wide agent settings.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install wechat-favorites - 安装完成后，直接呼叫该 Skill 的名称或使用
/wechat-favorites触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.1.4
• Expanded category system: now supports a three-level taxonomy—9 primary classes, 57 sub-tags, and 6 cross-domain labels for more precise and multi-faceted classification.
• Improved documentation: updated SKILL.md with more details on classification logic, LLM usage, real-world stats, and file formats.
• Simplified and modernized quick start instructions and sample config/commands. Enhanced onboarding guidance and common trigger keywords for easier discovery and usage
• Added optional LLM-assisted classification: low-confidence or ambiguous items can now be re-classified using large language models via new scripts (llm_classify.py, llm_incremental.py, merge_llm_results.py, normalize_categories.py).
• Streamlined and optimized documentation, added “Security Notes” section highlighting localization, privacy, and data security
• Added SAFE_MODE offline mode — set SAFE_MODE=1 to completely disable all network calls (LLM classification, IMA import), ensuring sensitive data stays local.
• Version bump to 1.1 with a new display name (微信收藏知识库).
• 分类体系升级：新增三级分类体系——9大主类、57个二级标签、6个跨领域标签，分类更精细多元
• 文档全面优化：完善 SKILL.md，补充分类逻辑说明、LLM 使用指南、实测数据、文件格式说明
• 快速上手简化：精简配置示例、优化命令说明、增强引导提示、补充常用触发词，方便快速上手
• LLM 智能增强（可选）：新增 LLM 辅助分类脚本（llm_classify.py、llm_incremental.py、merge_llm_results.py、normalize_categories.py），低置信度或模糊条目可交由大模型重新分类
• 安全说明强化：新增## 安全说明章节，强调本地化、隐私保护与数据安全
• 新增 SAFE_MODE 离线模式，设置环境变量 SAFE_MODE=1 即可完全禁用所有网络调用（LLM 分类、IMA 导入），确保敏感数据不出本地。
• 版本升级：1.0 → 1.1，新显示名（微信收藏知识库）
v1.1.3
• Expanded category system: now supports a three-level taxonomy—9 primary classes, 57 sub-tags, and 6 cross-domain labels for more precise and multi-faceted classification.
• Improved documentation: updated SKILL.md with more details on classification logic, LLM usage, real-world stats, and file formats.
• Simplified and modernized quick start instructions and sample config/commands. Enhanced onboarding guidance and common trigger keywords for easier discovery and usage
• Added optional LLM-assisted classification: low-confidence or ambiguous items can now be re-classified using large language models via new scripts (llm_classify.py, llm_incremental.py, merge_llm_results.py, normalize_categories.py).
• Streamlined and optimized documentation, added “Security Notes” section highlighting localization, privacy, and data security
• Version bump to 1.1 with a new display name (微信收藏知识库).
• 分类体系升级：新增三级分类体系——9大主类、57个二级标签、6个跨领域标签，分类更精细多元
• 文档全面优化：完善 SKILL.md，补充分类逻辑说明、LLM 使用指南、实测数据、文件格式说明
• 快速上手简化：精简配置示例、优化命令说明、增强引导提示、补充常用触发词，方便快速上手
• LLM 智能增强（可选）：新增 LLM 辅助分类脚本（llm_classify.py、llm_incremental.py、merge_llm_results.py、normalize_categories.py），低置信度或模糊条目可交由大模型重新分类
• 安全说明强化：新增## 安全说明章节，强调本地化、隐私保护与数据安全
• 版本升级：1.1.0 → 1.1，新显示名（微信收藏知识库）
v1.1.2
- Added LLM-assisted classification: low-confidence or ambiguous items can now be re-classified using large language models via new scripts (llm_classify.py, llm_incremental.py, merge_llm_results.py, normalize_categories.py).
- Expanded category system: now supports a three-level taxonomy—9 primary classes, 57 sub-tags, and 6 cross-domain labels for more precise and multi-faceted classification.
- Improved documentation: updated SKILL.md with more details on classification logic, LLM usage, real-world stats, and file formats.
- Simplified and modernized quick start instructions and sample config/commands. Enhanced onboarding guidance and common trigger keywords for easier discovery and usage
- Streamlined and optimized documentation, added “Security Notes” section highlighting localization, privacy, and data security
- Version bump to 1.1 with a new display name (微信收藏知识库).
v1.1.1
wechat-favorites 1.1.0
**Summary: This update introduces LLM (large language model) enhanced classification and refines the tagging system for WeChat Favorites export and organization.**
- Added LLM-assisted classification: low-confidence or ambiguous items can now be re-classified using large language models via new scripts (llm_classify.py, llm_incremental.py, merge_llm_results.py, normalize_categories.py).
- Expanded category system: now supports a three-level taxonomy—9 primary classes, 57 sub-tags, and 6 cross-domain labels for more precise and multi-faceted classification.
- Improved documentation: updated SKILL.md with more details on classification logic, LLM usage, real-world stats, and file formats.
- Simplified and modernized quick start instructions and sample config/commands. Enhanced onboarding guidance and common trigger keywords for easier discovery and usage
- Streamlined and optimized documentation, added “Security Notes” section highlighting localization, privacy, and data security
- Version bump to 1.1.1 with a new display name (微信收藏知识库).
v1.1.0
**Summary: This update introduces LLM (large language model) enhanced classification and refines the tagging system for WeChat Favorites export and organization.**
- Added LLM-assisted classification: low-confidence or ambiguous items can now be re-classified using large language models via new scripts (llm_classify.py, llm_incremental.py, merge_llm_results.py, normalize_categories.py).
- Expanded category system: now supports a three-level taxonomy—9 primary classes, 57 sub-tags, and 6 cross-domain labels for more precise and multi-faceted classification.
- Improved documentation: updated SKILL.md with more details on classification logic, LLM usage, real-world stats, and file formats.
- Simplified and modernized quick start instructions and sample config/commands.
- Discontinued quick_validate.py (removed).
- Version bump to 1.1.0 with a new display name (微信收藏知识库).
v1.0.2
- Major structure update: the skill is now fully script modularized, and workflows are clarified.
- Nine new files added, including database decryption, export, classification, IMA import, and utility scripts.
- Central user configuration moved to a single `config.json` for clear setup.
- IMA import process streamlined with flexible credential sources.
- Documentation updated: simplified user guide, clarified prerequisites, and split workflows by function.
- Removed legacy batch import script; replaced with more modular and configurable alternatives.
v1.0.1
Version 1.0.1
- Added more flexible configuration for IMA knowledge base import (supporting config file, environment variables, and command-line arguments).
- Updated dependencies: now requires zstandard and pycryptodome.
- Clarified that IMA import is optional and provided detailed configuration instructions.
- Improved guidance on decompressing content with zstd when necessary.
- Minor workflow clarifications and documentation improvements.
v1.0.0
WeChat Favorites Skill 1.0.0 — Initial Release
- 支持将微信收藏夹（favorite.db）导出为 CSV 文件。
- 提供多标签智能分类（如生物医药、AI、投资等）。
- 支持批量导入收藏到 IMA 知识库，含断点续传与详尽日志。
- 自动生成分类报告，包括统计、趋势、热门话题与主流来源分析。
- 提供详细的操作流程、数据结构说明与常见问题解答。
元数据
常见问题
微信收藏知识库 是什么？
微信收藏夹导出、智能分类与知识库管理。支持从解析后的 favorite.db 导出收藏记录、三级分类体系（一级9类 + 二级57标签 + 跨领域6类）、LLM 智能增强（可选）、批量导入 IMA 知识库（可选）。核心功能支持离线使用，网络功能默认关闭。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 199 次。
如何安装 微信收藏知识库？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wechat-favorites」即可一键安装，无需额外配置。
微信收藏知识库 是免费的吗？
是的，微信收藏知识库 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
微信收藏知识库 支持哪些平台？
微信收藏知识库 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 微信收藏知识库？
由 BrainClaw（@geosun）开发并维护，当前版本 v1.1.4。
推荐 Skills