summarization by jwynia/agent-skills
npx skills add https://github.com/jwynia/agent-skills --skill summarization通过将摘要类型与目的、受众和上下文相匹配,创建有效的摘要。"总结"可以意味着许多不同的事情——这项技能有助于识别和执行正确的方法。
摘要是翻译,而不仅仅是缩减。 不同的目的需要不同的摘要类型。在浓缩内容之前,先明确需求。
在总结之前,请考虑:
| 类型 | 定义 | 使用场景 |
|---|---|---|
| 关键点提取 | 分离出最重要的主张 | 原文有离散的重要观点 |
| 抽象概括 | 涵盖多个细节的更高级别陈述 | 模式比具体细节更重要 |
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 要点提炼 |
| 捕捉核心意义,丢弃细节 |
| 仅核心信息重要 |
| 压缩 | 缩短篇幅同时保留信息 | 需要在更少空间内全面覆盖 |
| 类型 | 定义 | 使用场景 |
|---|---|---|
| 执行摘要 | 侧重于业务:决策、建议、结果 | 需要采取行动的文档 |
| 摘要/梗概 | 学术性:方法论和发现 | 研究论文、技术文档 |
| TLDR | 超简短的主要要点 | 非正式沟通、极度简洁 |
| 大纲 | 主要/支持点的层次结构 | 逻辑结构重要 |
| 类型 | 定义 | 使用场景 |
|---|---|---|
| 综合摘要 | 连贯地结合多个来源 | 跨文档总结 |
| 批判性摘要 | 在浓缩的同时评估主张 | 需要评估质量 |
| 上下文摘要 | 在更广泛的知识框架内定位 | 理解大局重要 |
| 可操作摘要 | 侧重于影响和后续步骤 | 摘要将驱动行动 |
示例: "作者提出了三个主要论点:(1)..., (2)..., (3)..."
示例: "多项研究一致表明..." 而不是列出 12 项研究
示例: "远程工作提高了大多数知识工作者的生产力。"
示例: "在五份报告中,出现了三个关键趋势..."
示例: "虽然作者声称 X,但证据受到...的限制"
问题: 减少了长度但没有降低复杂性 解决方案: 关注重要内容,而不仅仅是简短的内容
问题: 通过压缩改变了含义 解决方案: 根据原始主张验证摘要
问题: 对所有请求采用相同的方法 解决方案: 使类型与目的和受众相匹配
问题: 丢失了所有有用的具体细节 解决方案: 保留支持理解的具体细节
输入:
输出:
互补技能:
speech-adaptation: 用于口语摘要voice-analysis: 用于在摘要中保持语气每周安装量
298
代码仓库
GitHub 星标
37
首次出现
Jan 20, 2026
安全审计
安装于
opencode256
codex246
gemini-cli240
github-copilot234
cursor232
amp218
Create effective summaries by matching summarization type to purpose, audience, and context. "Summarize" can mean many different things—this skill helps identify and execute the right approach.
Summarization is translation, not just reduction. Different purposes require different summary types. Clarify the need before condensing.
Before summarizing, consider:
Purpose: What will this summary be used for?
Audience: Who will read it?
Scope: How comprehensive?
Emphasis: What aspects are most important?
Format: What structure?
| Type | What It Is | When to Use |
|---|---|---|
| Key Point Extraction | Isolating the most important claims | Original has discrete important points |
| Abstraction | Higher-level statements covering multiple details | Patterns matter more than specifics |
| Gisting | Capturing essential meaning, discarding details | Only core message matters |
| Compression | Shortening while preserving information | Comprehensive coverage needed in less space |
| Type | What It Is | When to Use |
|---|---|---|
| Executive Summary | Business-focused: decisions, recommendations, outcomes | Documents requiring action |
| Abstract/Précis | Academic: methodology and findings | Research papers, technical documents |
| TLDR | Ultra-brief main takeaway | Casual communication, extreme brevity |
| Outline | Hierarchical structure of main/supporting points | Logical structure matters |
| Type | What It Is | When to Use |
|---|---|---|
| Synthesis | Combining multiple sources coherently | Summarizing across documents |
| Critical Summary | Evaluating claims while condensing | Assessment of quality needed |
| Contextual Summary | Framing within broader knowledge | Understanding bigger picture matters |
| Actionable Summary | Focusing on implications and next steps | Summary will drive action |
Example: "The author makes three main arguments: (1)..., (2)..., (3)..."
Example: "Multiple studies consistently show..." instead of listing 12 studies
Example: "Remote work increases productivity for most knowledge workers."
Example: "Across the five reports, three key trends emerge..."
Example: "While the author claims X, the evidence is limited by..."
Problem: Reduces length but not complexity Fix: Focus on what matters, not just what's short
Problem: Changes meaning through compression Fix: Verify summary against original claims
Problem: Same approach for all requests Fix: Match type to purpose and audience
Problem: Loses all useful specifics Fix: Preserve concrete details that support understanding
Inbound:
Outbound:
Complementary:
speech-adaptation: For spoken summariesvoice-analysis: For maintaining voice in summariesWeekly Installs
298
Repository
GitHub Stars
37
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode256
codex246
gemini-cli240
github-copilot234
cursor232
amp218
Python PDF处理教程:合并拆分、提取文本表格、创建PDF文件
55,400 周安装