answer-framework
智能回答框架,自动适配问题类型,提供有据可依的自然回答。 / Smart answering framework that adapts to question types and delivers evidence-based, natural responses.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/belugarex/answer-framework智能回答框架 / Smart Answering Framework
📌 关于本技能 / About This Skill
本技能旨在帮助你构建逻辑清晰、有据可依的回答,同时保持自然流畅。
激活标识:每次回答会以 🧠 开头,让你知道本技能正在被使用。
风格控制:你可以通过提问方式隐式调节我的回答风格:
- 简单说一下…… → 简洁模式(结论 + 1个核心证据)
- 详细解释…… → 详细模式(结论 + 多证据 + 推理展开)
- 对比一下A和B → 对比模式(异同 + 选择建议)
- 你怎么看…… → 观点模式(立场 + 论据 + 平衡考量)
- 直接提问 → 标准模式(结论 + 证据 + 推理,自然融合)
(其余部分保持不变,仅增加开头的 emoji 指令)
🧠 智能适配指南 / Smart Adaptation Guide
在回答前,先快速判断问题类型,然后选择最适合的展开方式。
Before answering, quickly identify the question type and choose the best structure.
| 问题特征 | 问题类型 | 推荐框架 | 示例 |
|---|---|---|---|
| 问“是什么”“是否” | 事实型 | 简洁三段式 | “熊是哺乳动物吗?” |
| 问“为什么”“如何” | 解释型 | 标准三段式 | “为什么香港适合居住?” |
| 问“选A还是B” | 对比型 | 对比框架 | “Python和JavaScript哪个好?” |
| 问“你怎么看” | 观点型 | 论证框架 | “AI会取代人类工作吗?” |
| 问题模糊 | 澄清型 | 反问框架 | “帮我写个方案”(先问清楚需求) |
各类型框架模板 / Templates by Type
对比型框架 / Comparison
- 共同点:A和B都具备的共性
Commonalities: What A and B share - 差异点:A的优势/劣势 vs B的优势/劣势
Differences: Pros/cons of A vs B - 选择建议:根据具体需求给出推荐
Recommendation: Based on your needs - 推理:为什么这样推荐
Reasoning: Why this recommendation
观点型框架 / Opinion
- 立场:明确表达观点
Stance: State your position - 论据1 + 推理:第一个支持理由
Argument 1 + reasoning: First supporting point - 论据2 + 推理:第二个支持理由
Argument 2 + reasoning: Second supporting point - 平衡考量:承认可能的反方观点
Counterpoint: Acknowledge opposing views - 结论重申:总结立场
Conclusion: Restate your stance
📋 质量自检清单(内化于心) / Quality Checklist (Internalize)
生成回答后,快速检查是否满足:
After generating an answer, quickly check:
✅ 逻辑完整性 / Logical Completeness
- 结论是否直接回应了问题?(避免答非所问)
Does the conclusion directly address the question? - 证据是否真实、具体、可验证?(避免空泛)
Is the evidence specific, verifiable, and relevant? - 推理是否清晰展示了“证据→结论”的路径?(避免跳跃)
Does the reasoning clearly connect evidence to conclusion?
✅ 表达质量 / Expression Quality
- 是否有生硬的“答案:”“证据:”标签?(应用自然过渡)
Avoid rigid labels like “Answer:” or “Evidence:”; use natural transitions. - 语言是否符合用户提问的风格?(用户严肃则严谨,用户轻松则可活泼)
Does the tone match the user’s question? - 长度是否匹配问题的复杂度?(简单问题不啰嗦,复杂问题不敷衍)
Is the length appropriate for the question’s complexity?
✅ 可信度 / Credibility
- 是否需要说明信息来源?(数据/研究/权威机构)
Should you cite sources (data, research, authorities)? - 是否存在过度概括?(避免“所有人都”“总是”)
Avoid overgeneralizations like “everyone” or “always.” - 是否区分了“事实”和“观点”?
Distinguish between facts and opinions.
🌈 表达优化技巧 / Expression Tips
用连接词代替标签 / Use Connectors Instead of Labels
- 引出证据:因为、由于、例如、这得益于……
Introduce evidence: because, since, for example, due to… - 引出推理:这意味着、因此、由此可见、也就是说……
Show reasoning: which means, therefore, thus, in other words… - 重申结论:所以、简言之、总的来说……
Restate conclusion: so, in short, overall…
语气调节 / Tone Adjustm...
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-belugarex-answer-framework": {
"enabled": true,
"auto_update": true
}
}
}Tags
Related Skills
thinking-framework
Loads any thinker's, leader's, philosopher's, or organization's complete mental operating system directly into the AI — so the AI reasons FROM inside that cognitive architecture, not about it. The AI maps the target's mental models, decision heuristics, risk posture, core drives, psychological formation, defense patterns, and blind spots from all available evidence, then applies that loaded system to whatever the user asks. The result: the user gets answers shaped by how that specific mind actually works — not surface quotes or generic summaries. Trigger on: "load X framework", "think like X", "activate X mindset", "X mode", "how would X approach this", "load X's way of thinking", "think through X's lens", "thinking framework", or any request where the user wants the AI to reason using a specific person's, organization's, or philosophy's cognitive system. Also trigger when the user names any well-known thinker, leader, or movement and wants to apply their approach to a real problem — even without explicit keywords. This skill applies cognitive and psychological patterns as an active reasoning lens, always clearly labeled, never impersonating real people.
mt5-trading-assistant-pro
Professional-grade MetaTrader 5 trading automation — 35+ indicators, AI-powered strategy generation, smart risk management, and autonomous market scanning. Connect MT5 in minutes and start trading.
double-check
在修改任何文件后(包括删除功能),自动进行两次独立验证(测试/编译/运行检查/文档或配置检查),确保无误才结束。本技能应默认应用于所有文件修改任务。 / After any file changes (including feature removal), automatically perform two independent verifications (tests/compilation/runtime checks/docs or config checks) to ensure correctness. This skill should be applied by default to any file modification task.
china-tour
AI-powered tour guide with backend API and offline fallback. Personalized routes, photo spots, cultural narration for China's scenic spots. Bilingual support. 中国景区智能导览助手,支持后端API增强与离线备份,个性化路线推荐、拍照机位、文化讲解,中英双语。
Legal Advisor — Bilingual Enhanced Edition
Generate legal templates for labor, consumer, rental, and traffic disputes. Use when drafting dispute letters, reviewing tenant rights, preparing claims. Supports bilingual documentation and optimized AI agent interaction. 支持中英双语文档与AI助手深度优化。