cs

Automatically extract key points from long texts in Chinese or English using keywords or length triggers, outputting clear, concise bullet-point summaries.

Security Scan

The skill's code and instructions match its stated purpose (summarizing long text) and request no credentials or installs; it appears internally consistent.

Purpose & Capability

The skill's name/description, SKILL.md, and code all describe a summarizer and the required behavior (keyword and length triggers). Minor naming inconsistencies exist: registry slug is 'cs', SKILL.md shows an install command for 'smart-summarizer', and the code defines id 'summarizer' — likely harmless but worth noting for clarity.

Instruction Scope

SKILL.md and summarizer.ts limit behavior to reading the incoming message text, applying a simple trigger (keyword regex or length), and forwarding the text to the platform-provided LLM. There are no instructions to read files, environment variables, or external endpoints beyond the LLM API.

Install Mechanism

No install specification is provided (instruction-only with a single code file). Nothing is downloaded or written to disk by the skill itself, which is the lowest-risk install profile.

Credentials

The skill declares no required environment variables, credentials, or config paths. The runtime uses the platform's llm.chat API (expected for an LLM-based summarizer).

Persistence & Privilege

always is false and the skill does not request persistent presence or modify other skills/config. It uses normal autonomous invocation (disable-model-invocation is false), which is expected.

Assessment

This skill appears to do exactly what it says: it watches incoming messages and, when triggered by keywords or length, sends the message text to the configured LLM and returns a bullet-point summary. There are no requested secrets or external downloads. Before installing, consider: (1) privacy — summaries require sending full message text to your LLM provider, so avoid using it with highly sensitive data unless your provider/policy permits; (2) triggers — it will auto-activate on messages containing the listed keywords or >100 characters, so it may run in some conversations you didn't intend; (3) naming mismatch — the registry slug, README install command, and code id differ (cosmetic but check you are installing the intended skill). If those points are acceptable, the skill is coherent and low-risk.

📝 智能摘要助手 (Smart Summarizer)

🔍 一键提取长文本核心要点，告别信息过载

---

🌟 核心能力

✅ 智能触发机制

• 🔑 关键词触发：消息包含 总结、摘要、summarize、brief 时自动激活
• 📏 长度触发：纯文本超过 100 字符时，即使无关键词也会尝试摘要
• 🎯 精准匹配：正则表达式 /总结|摘要|summarize|brief/i，不误触日常聊天

✅ 专业摘要输出

• 📋 结构化列表：自动使用 bullet points 格式，层次清晰
• 🌐 语言自适应：输入中文输出中文，输入英文输出英文，混合内容智能处理
• ✂️ 去噪精简：自动过滤寒暄、重复、无关内容，只保留干货
• ⚡ 快速响应：温度参数 0.3，确保输出稳定一致

✅ 场景全覆盖

场景	示例输入	输出效果
📧 邮件摘要	长邮件正文	3-5 条核心事项 + 行动点
🗣️ 会议记录	讨论纪要文本	议题列表 + 决策结论 + 待办
📰 文章提炼	新闻/博客全文	核心观点 + 关键数据 + 结论
💬 聊天记录	群聊长篇讨论	争议点 + 共识 + 下一步

---

🚀 快速开始

1️⃣ 安装技能

openclaw skills install smart-summarizer