← 返回 Skills 市场
Video Recommendation
作者
fischerlam
· GitHub ↗
· v0.1.0
· MIT-0
221
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install video-recommendation
功能描述
Recommend precise, context-aware videos with direct links and curated watchlists based on your current mood, project, or recent chat topics.
安全使用建议
This skill appears coherent and limited in scope: it uses chat context/memory for personalization and includes a tiny browser snippet to extract YouTube watch links (safe for browser-console use). Before installing, decide whether you’re comfortable with the agent using your recent chat history or stored taste memory for personalization, and be cautious about any future edits that add automated browser automation that navigates arbitrary pages — run the provided script only in trusted pages (it simply reads anchors and prints JSON). If you need stronger guarantees, request that the skill refuses to access memory or to perform browser automation without explicit user consent.
功能分析
Type: OpenClaw Skill
Name: video-recommendation
Version: 0.1.0
The video-recommendation skill is a well-documented tool designed to provide curated video suggestions based on user context and chat history. It includes a simple JavaScript utility (scripts/extract_youtube_links.js) for extracting video titles and URLs from the DOM, which is consistent with its stated purpose. The extensive documentation in the references/ directory provides clear, non-malicious guidance for the AI agent to prioritize high-quality content over algorithmic feeds, with no evidence of data exfiltration, unauthorized execution, or harmful prompt injection.
能力评估
Purpose & Capability
Name and description match the actual files and instructions: a contextual video recommender that prefers exact watch links. The included helper script is a small browser DOM extractor for YouTube link collection, which is proportionate to the stated purpose.
Instruction Scope
SKILL.md confines runtime behavior to inferring intent from recent chat/memory, selecting angles, searching public video sources, ranking, and returning direct links with short rationales. It does suggest using browser automation when other tools are blocked; that is a reasonable fallback for harvesting exact URLs but should be limited to the pages the agent legitimately needs to read.
Install Mechanism
No install spec and only one small script (browser DOM snippet) are present. Nothing is downloaded from external URLs or extracted to disk, so installation risk is minimal.
Credentials
The skill requires no environment variables, credentials, or config paths. References to using 'memory' and chat context are expected for personalization and are proportionate to the feature set.
Persistence & Privilege
The skill is not forced-always; it is user-invocable and allows normal autonomous invocation. It does not request persistent system privileges or to modify other skills' configurations.
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 video-recommendation - 安装完成后，直接呼叫该 Skill 的名称或使用
/video-recommendation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
v0.1.0
Initial release: a context-aware, taste-driven video recommendation skill that recommends videos with precision, not addiction. Includes direct-link workflows, source curation, testing, and quality calibration.
元数据
常见问题
Video Recommendation 是什么？
Recommend precise, context-aware videos with direct links and curated watchlists based on your current mood, project, or recent chat topics. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 221 次。
如何安装 Video Recommendation？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install video-recommendation」即可一键安装，无需额外配置。
Video Recommendation 是免费的吗？
是的，Video Recommendation 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Video Recommendation 支持哪些平台？
Video Recommendation 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 Video Recommendation？
由 fischerlam（@fischerlam）开发并维护，当前版本 v0.1.0。
推荐 Skills