← 返回 Skills 市场
91
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install silas-wechat-article-search
功能描述
微信公众号文章搜索与解析。搜狗微信+新榜双源搜索,Python脚本解析全文(零Node依赖),Serper转载兜底。
安全使用建议
Before installing: 1) Ask the author to declare required environment variables (at minimum SERPER_API_KEY) and any credentials for Feishu or other services the skill will call. 2) Confirm where web-keywords.json and memory/collect-log.json come from and whether the skill will read any other local files. 3) Understand that the skill will write scraped output and images to /tmp/openclaw/images/ and may upload media to Feishu — make sure those actions are acceptable and that Feishu credentials are handled securely by the agent. 4) Note legal/terms-of-service risks when scraping WeChat/Sogou; consider rate limits and captcha workarounds. 5) If you need tighter assurance, request the author remove undeclared external dependencies or explicitly list required secrets and file paths; otherwise treat this skill as having broader access than the metadata indicates.
功能分析
Type: OpenClaw Skill
Name: silas-wechat-article-search
Version: 2.0.0
The skill bundle is a legitimate tool designed to search for WeChat articles via Sogou/Serper and parse them into a Feishu knowledge base. The Python script `scripts/parse_article.py` uses standard libraries (requests, BeautifulSoup) to extract content and includes a common scraping technique (iPhone User-Agent) to bypass WeChat's anti-crawling measures. There is no evidence of data exfiltration, malicious command execution, or harmful prompt injection.
能力标签
能力评估
Purpose & Capability
Name/description (WeChat article search & parse) matches the included parser script and curl-based search steps. However, the SKILL.md uses a SERPER API key ($SERPER_API_KEY) and references other system artifacts (web-keywords.json, memory/collect-log.json) and Feishu integration steps without declaring any required environment variables, credentials, or config paths in the skill metadata. Those externally referenced items are not explained or requested in the registry metadata, which is disproportionate.
Instruction Scope
Instructions tell the agent to: curl sogou/webrank/Serper, run the included Python parser, search for reposts, write and save JSON, save images to /tmp/openclaw/images/, and call other agent-native tools (feishu_create_doc, feishu_doc_media, feishu_search_doc_wiki, wiki-directory-manager, web_fetch). The SKILL.md also expects local files (web-keywords.json, memory/collect-log.json). The skill instructs reading/writing files and calling external services beyond the single parse operation; many of these inputs/outputs are not declared, granting the agent broad scope that isn't captured in metadata.
Install Mechanism
No formal install spec (instruction-only) — lower install risk. SKILL.md suggests 'pip3 install requests beautifulsoup4' which is a normal, minimal Python dependency list and aligns with the included script. Nothing is downloaded from unknown URLs or extracted to disk by an installer.
Credentials
Metadata lists no required env vars, but the SKILL.md uses $SERPER_API_KEY in curl commands. The skill also expects Feishu insertion (which usually requires credentials) and references local state files; none of these credentials or config paths are declared. Requesting or using undeclared secrets/configs is disproportionate and should be explicit.
Persistence & Privilege
always:false and the skill is user-invocable; it does not request forced/permanent inclusion. It does instruct writing output and images to /tmp/openclaw/images/ (its own local path) which is reasonable for a scraper/collector and not an escalation of platform privileges.
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 silas-wechat-article-search - 安装完成后,直接呼叫该 Skill 的名称或使用
/silas-wechat-article-search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
v2.0.0
v2.0: 合并parser+search双技能,Python解析全文(iPhone UA绕验证),段落去重,零Node依赖,Serper转载兜底
v1.1.0
去掉Node脚本和cheerio依赖,纯agent工具实现,零依赖
v1.0.0
Initial release: 微信公众号文章搜索,搜狗+新榜双源
元数据
常见问题
Silas WeChat Article Search 是什么?
微信公众号文章搜索与解析。搜狗微信+新榜双源搜索,Python脚本解析全文(零Node依赖),Serper转载兜底。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 91 次。
如何安装 Silas WeChat Article Search?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install silas-wechat-article-search」即可一键安装,无需额外配置。
Silas WeChat Article Search 是免费的吗?
是的,Silas WeChat Article Search 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Silas WeChat Article Search 支持哪些平台?
Silas WeChat Article Search 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(linux)。
谁开发了 Silas WeChat Article Search?
由 silas(@aohoyo)开发并维护,当前版本 v2.0.0。
推荐 Skills