← 返回 Skills 市场
1221
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install wrynai-skill
功能描述
Perform advanced web crawling and content extraction with multi-page crawling, search result parsing, pattern filtering, and screenshot capture using the Wry...
安全使用建议
This skill appears to be a client wrapper for the WrynAI web-crawling service and legitimately needs an API key and the WrynAI Python package. Before installing or providing an API key: 1) Verify the WrynAI service (https://wryn.ai) and the identity of the 'wrynai' PyPI package or repository (confirm package author, homepage, and release history on PyPI or GitHub). 2) Note the registry metadata omission: the skill metadata does not declare the WRYNAI_API_KEY requirement — treat that as a potential oversight and ask the publisher to correct it. 3) Remember that pip installs run code at install time; only install packages from trusted sources. 4) Consider the data-flow risk: crawled content will be sent to the WrynAI service (the API key will authenticate those requests). If you will crawl sites with sensitive content, verify the service's privacy and retention policies. 5) If you need stronger assurance, request the skill publisher add a homepage, explicit required env vars/primary credential in metadata, and a formal install spec (or provide the SDK code) so you can audit the exact behavior.
功能分析
Type: OpenClaw Skill
Name: wrynai-skill
Version: 1.0.0
The skill bundle is designed for web crawling and content extraction using the WrynAI SDK. All observed behaviors, including network requests to `wryn.ai` and local file writing for screenshots (`screenshot.png`), are clearly aligned with its stated purpose. The `SKILL.md` instructions guide the AI agent to use the skill's functions for their intended web scraping tasks, without any evidence of prompt injection attempts to subvert the agent's behavior, exfiltrate unrelated sensitive data, or execute arbitrary malicious commands. API keys are handled securely via environment variables.
能力评估
Purpose & Capability
The SKILL.md clearly describes a WrynAI web-crawling skill (crawl, search, screenshots, content extraction) which is coherent with the skill name, but the package metadata gives no description or homepage and lists no required environment variables or primary credential. That mismatch (no declared env vars vs SKILL.md requiring WRYNAI_API_KEY) is unexpected and reduces trust in the metadata.
Instruction Scope
The instructions are focused on crawling/searching tasks and do not instruct the agent to access unrelated files or credentials. They do, however, tell the agent to read an environment variable (WRYNAI_API_KEY) and to pip install the 'wrynai' package — both are within the expected scope for a third-party SDK but the env var is not declared in the registry metadata.
Install Mechanism
There is no formal install spec in the registry; the SKILL.md instructs users to run 'pip install wrynai'. Instruction-only skills are lower risk, but pip-installing an external package can execute arbitrary code at install time. There is no link to a PyPI package or authoritative repo in the metadata to verify the package identity.
Credentials
The SKILL.md requires a single API key (WRYNAI_API_KEY), which is proportionate for a hosted SDK. However the declared requirements list in the registry is empty (no required env vars, no primary credential). That inconsistency is a red flag — the skill will need an API key to function, but the registry does not advertise that requirement.
Persistence & Privilege
The skill is instruction-only, does not request 'always: true', and does not ask to modify system or other skill configurations. It does not request elevated persistence or platform-wide 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 wrynai-skill - 安装完成后，直接呼叫该 Skill 的名称或使用
/wrynai-skill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
v1.0.0
WrynAI Skill 1.0.0 – Initial Release
- Introduces advanced web crawling and content extraction using the WrynAI SDK.
- Supports multi-page site crawling, documentation crawling with pattern filtering, and search engine result crawling.
- Enables extraction of text, markdown, structured data, links, and page screenshots.
- Includes sample code snippets for basic crawling, documentation gathering, combined search/crawl workflows, and single-page content extraction.
- Requires a WrynAI API key set as an environment variable.
元数据
常见问题
WrynAI Skill 是什么？
Perform advanced web crawling and content extraction with multi-page crawling, search result parsing, pattern filtering, and screenshot capture using the Wry... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1221 次。
如何安装 WrynAI Skill？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wrynai-skill」即可一键安装，无需额外配置。
WrynAI Skill 是免费的吗？
是的，WrynAI Skill 完全免费（开源免费），可自由下载、安装和使用。
WrynAI Skill 支持哪些平台？
WrynAI Skill 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 WrynAI Skill？
由 wrynai（@wrynai）开发并维护，当前版本 v1.0.0。
推荐 Skills