@superzhang21/weibo-like-someone
AWeibo Like Someone (微博模仿者):深度克隆博主文风。支持抓取、分析、模仿生成全流程,支持 Agent 协作模式。
Install
agr install @superzhang21/weibo-like-someone --target claudeWrites 5 files into .claude/skills/, pinned to git-a5a1fa26.
- .claude/skills/weibo-like-someone/CHANGELOG.md
- .claude/skills/weibo-like-someone/LICENSE
- .claude/skills/weibo-like-someone/README.md
- .claude/skills/weibo-like-someone/SKILL.md
- .claude/skills/weibo-like-someone/cli.py
Document
name: weibo-like-someone description: "Weibo Like Someone (微博模仿者):深度克隆博主文风。支持抓取、分析、模仿生成全流程,支持 Agent 协作模式。" version: "6.5.0" author: "superzhang21"
Weibo Analyzer v6.5 — 微博博主克隆引擎
这是由 superzhang21 与赛博哈雷(Cyber Harley)共同开发的微博博主深度解构工具。它不仅能全自动完成“抓取-分析-生成”,还支持在无 API 环境下通过智能 Agent 协作完成创作。
🌟 核心特性
- 双模引擎:支持自动化(LLM 驱动)和 Agent 协作(人工智能力量)两种模式。
- 高性能抓取:基于微博桌面版 AJAX 接口,原生支持全文抓取,无需二次加载。
- 智能缓存:内置 SQLite 数据库,特征分析结果 7 天内自动缓存。
- 数据闭环:自动过滤转发,仅聚焦博主原创语料,确保文风克隆的纯净度。
🚀 快速开始
1. 配置 Cookie (燃料注入)
登录 weibo.com,在控制台执行 document.cookie,将结果保存到 assets/cookies.json (或通过脚本加密)。
2. 命令行操作
# 全流程:抓取 -> 分析 -> 模仿 (默认使用 OPENAI_API_KEY)
python3 cli.py --uid 1989660417 --action all --topic "评价人工智能"
# 纯抓取模式:仅获取语料并存入本地库
python3 cli.py --uid 1989660417 --action analyze --count 20
# Agent 协作模式:无 API Key 时,工具会自动输出语料供 Agent 参考
python3 cli.py --uid 1111681197 --action generate --topic "评价王思聪"
📂 目录结构
cli.py: 统一入口assets/weibo_scraper.py: 桌面版 API 爬虫assets/data_manager.py: SQLite 存储管理assets/feature_extractor.py: 语言特征提取 (LLM)assets/content_generator.py: 文风模仿生成 (LLM)
“技术应当服务于表达。把博主的灵魂代码化,就是对信息时代最好的致敬。”
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-a5a1fa26c8302026-07-31