← 返回 Skills 市场
266
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install web-llm-chat
功能描述
Chat with web-based LLMs through the Chrome Relay extension. Supports Qwen (chat.qwen.ai) and Kimi (kimi.com) via scripts; more sites may be added. Use for w...
安全使用建议
Key things to consider before installing/running this skill:
- It will read your local OpenClaw configuration file (openclaw.json) to obtain gateway.auth.token and derive a relay token. This token is sensitive; the skill metadata does not declare this file/credential requirement — treat that as a privacy gap.
- The script connects to localhost (127.0.0.1) ports used by your OpenClaw gateway/relay and to the browser tab via CDP; it does not contact remote servers according to the provided code, but you should still review the source (scripts/qwen_chat.js) yourself before running.
- If you trust the skill: run it on a machine/account that contains only the necessary credentials, inspect outgoing network traffic (to ensure nothing is exfiltrating), and install npm dependencies from official registries.
- If you do not want the skill to access your gateway token, do not run it, or modify the script to accept the token via an explicit user-supplied environment variable or prompt and update the skill metadata to declare that requirement.
If you want higher confidence, ask the publisher to: (1) declare required config paths/credentials in the registry metadata, (2) add an option to pass the gateway token explicitly (instead of reading from disk), and (3) document exactly what files are read and why.
功能分析
Type: OpenClaw Skill
Name: web-llm-chat
Version: 1.0.0
The skill bundle is a legitimate tool for automating interactions with the Qwen web-based LLM (chat.qwen.ai) using a Chrome Relay extension. The primary script, `scripts/qwen_chat.js`, uses WebSockets and Chrome DevTools Protocol (CDP) to simulate user input and extract responses from the browser. While it reads the local `openclaw.json` file, it does so only to derive an HMAC-SHA256 token required to authenticate with the local OpenClaw gateway (127.0.0.1). There is no evidence of data exfiltration, unauthorized remote access, or malicious instructions in the SKILL.md file.
能力评估
Purpose & Capability
The skill's name/description (web-based LLM chat via Chrome Relay) matches the included code and docs: it connects to a local OpenClaw gateway/relay and a Qwen chat tab. However the registry metadata claims no required config paths or credentials, while the code expects an OpenClaw config file (openclaw.json) containing gateway.auth.token. That undeclared requirement is an inconsistency.
Instruction Scope
SKILL.md tells the agent to run the included Node script which connects to a local gateway and Relay, reads page content, and extracts responses. The runtime instructions and the script only target localhost (gateway/relay and local CDP via WebSocket) and the browser tab; there are no external network endpoints in the docs. The script does, however, instruct/require reading local OpenClaw config files to derive a relay token — this file access is outside what the metadata advertised and should be explicitly declared.
Install Mechanism
No install spec is provided (instruction-only with code files). The package.json only depends on the widely used 'ws' npm package; SKILL.md tells users to 'npm install ws'. There are no remote downloads or extraction of arbitrary archives in the skill bundle.
Credentials
The manifest lists no required environment variables or config paths, but the script reads openclaw.json from multiple filesystem locations (including E:\.openclaw\... and ~/.openclaw/...), extracts gateway.auth.token, and derives an HMAC relay token. Accessing that local token is sensitive and should have been declared as a required config/credential. The script also optionally reads an env flag for debug output (QWEN_CHAT_DEBUG_EXTRACT). Requiring access to a gateway auth token is proportionate for the stated operation, but the omission from declared requirements is a privacy/visibility concern.
Persistence & Privilege
The skill is not forced-always, does not request elevated platform-wide privileges, and does not modify other skills or system-wide config. It runs as a user-level Node script and communicates with local gateway/extension endpoints only.
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 web-llm-chat - 安装完成后，直接呼叫该 Skill 的名称或使用
/web-llm-chat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
v1.0.2
**v1.0.2 changelog**
- Expanded skill to support both Qwen (chat.qwen.ai) and Kimi (kimi.com) web LLMs via dedicated scripts.
- Updated triggers and description to reflect multi-site capability.
- Documentation improved for clarity, including separate command samples and status outputs for Qwen and Kimi.
- Instructions now clarify how to extend for other web LLMs using script templates.
- No code or file changes detected in this release; documentation only.
v1.0.1
**Kimi web LLM support added.**
- Added `scripts/kimi_chat.js` to enable chat automation with Kimi (kimi.moonshot.cn) via Chrome Relay.
- Skill wording, triggers, and documentation updated to reflect support for both Qwen and Kimi web LLM chat tabs.
- Command reference and usage examples expanded to cover Kimi, including dedicated `send`, `status`, `read`, and new `diag` command for DOM diagnostics.
- Improved documentation on completion detection, output formats, and research workflow for multiple web LLMs.
v1.0.0
web-llm-chat 1.0.0 – Initial Release
- Enables chat with web-based LLMs via the Chrome Relay extension.
- Supports Qwen AI (chat.qwen.ai) for web search, RAG, and deep research workflows.
- Offers plain text, Markdown, and HTML response formats.
- Includes multi-turn research mode for agent-orchestrated investigations.
- Requires a running Chrome Relay extension and Node.js setup.
- Provides command-line utilities for status checking, messaging, and research operations.
元数据
常见问题
web-llm-chat 是什么？
Chat with web-based LLMs through the Chrome Relay extension. Supports Qwen (chat.qwen.ai) and Kimi (kimi.com) via scripts; more sites may be added. Use for w... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 266 次。
如何安装 web-llm-chat？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install web-llm-chat」即可一键安装，无需额外配置。
web-llm-chat 是免费的吗？
是的，web-llm-chat 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
web-llm-chat 支持哪些平台？
web-llm-chat 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 web-llm-chat？
由 GoDiao（@godiao）开发并维护，当前版本 v1.0.0。
推荐 Skills