share-reading
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseShare Reading
分享读物
Help draft social media posts for sharing valuable readings, articles, tools, or resources. Generates multiple candidate posts with appropriate tone and style, ready for publishing on X, Substack, or 知识星球.
帮助撰写用于分享优质读物、文章、工具或资源的社交媒体帖子。生成多篇符合平台语气风格的候选帖子,可直接发布在X、Substack或知识星球上。
Workflow
工作流程
Step 1: Process Input
步骤1:处理输入
Determine the input type and extract content accordingly:
If input is a URL:
- Use WebFetch to retrieve the page content
- Extract: title, author, key points, publication date
- Preserve the original URL for inclusion in the post
If input is a file path:
- Use Read to load the file
- Extract the same metadata from frontmatter or content
If input is direct text/notes:
- Use the provided content as-is
- Ask for the source URL if not included
判断输入类型并据此提取内容:
若输入为URL:
- 使用WebFetch获取页面内容
- 提取:标题、作者、核心要点、发布日期
- 保留原始URL以纳入帖子中
若输入为文件路径:
- 使用Read工具加载文件
- 从文件前置信息或内容中提取上述相同元数据
若输入为直接文本/笔记:
- 直接使用提供的内容
- 若未包含来源URL,向用户询问
Step 2: Understand Context
步骤2:理解上下文
Before writing, consider:
- What makes this worth sharing? (insight, practical value, novelty, controversy)
- Who would care about this? (developers, AI enthusiasts, general tech audience)
- What's the user's likely angle? (recommendation, commentary, discussion)
If the intent is unclear, ask briefly:
这篇内容你想从什么角度分享?比如:
- 推荐给大家(觉得很有价值)
- 分享某个观点/发现
- 提出讨论/问题
- 其他想法?撰写前需考虑:
- 内容值得分享的点是什么?(见解、实用价值、新颖性、争议性)
- 目标受众是谁?(开发者、AI爱好者、普通科技受众)
- 用户可能的分享角度是什么?(推荐、评论、讨论)
若意图不明确,可简要询问:
这篇内容你想从什么角度分享?比如:
- 推荐给大家(觉得很有价值)
- 分享某个观点/发现
- 提出讨论/问题
- 其他想法?Step 3: Generate Candidates
步骤3:生成候选帖子
Produce 2-3 candidate posts with varying approaches. Each candidate should:
- Include the source link — always present, naturally placed
- Be self-contained — readers should understand the value without clicking
- Match the platform tone — see Platform Guidelines below
生成2-3篇采用不同风格的候选帖子。每篇候选帖子需满足:
- 包含来源链接 — 必须存在,且自然融入帖子
- 内容独立完整 — 读者无需点击链接即可理解内容价值
- 契合平台语气 — 详见下方平台指南
Candidate Approaches (pick 2-3 that fit)
候选帖子风格(选择2-3种合适的)
- Summary + takeaway: Concise summary with a personal takeaway or opinion
- Key highlight: Pull out the most striking point or quote, add brief context
- Question/discussion: Frame a question around the content to spark engagement
- Practical angle: Focus on actionable value — "if you're doing X, read this because Y"
- Contrarian/fresh take: Offer a perspective the article didn't cover
- 总结+感悟型:简洁总结内容,并加入个人感悟或观点
- 核心亮点型:提炼最具冲击力的要点或引用,补充简要背景
- 提问/讨论型:围绕内容提出问题,激发互动
- 实用导向型:聚焦可落地的价值——“如果你正在做X,一定要读这篇,因为Y”
- 逆向/新颖视角型:提出文章未涉及的观点
Step 4: Present to User
步骤4:呈现给用户
Present candidates clearly labeled, e.g.:
undefined将候选帖子清晰标注后呈现,例如:
undefined候选 1:总结推荐型
候选 1:总结推荐型
{content}
{content}
候选 2:观点提炼型
候选 2:观点提炼型
{content}
{content}
候选 3:讨论引导型
候选 3:讨论引导型
{content}
Ask user to pick one, or mix elements from multiple candidates.{content}
请用户选择其中一篇,或结合多篇的元素进行调整。Platform Guidelines
平台指南
X (Twitter)
X(Twitter)
- Keep main post concise (under 280 chars for single tweet, or use thread format)
- Front-load the hook — first line matters most
- Use line breaks for readability
- Hashtags: 1-3 relevant ones, placed at the end or naturally inline
- Link can be in the main tweet or a reply
- 主帖保持简洁(单条推文控制在280字符以内,或使用推文串格式)
- 开头设置钩子——第一句话至关重要
- 使用换行提升可读性
- 话题标签:1-3个相关标签,置于末尾或自然融入内容
- 链接可放在主帖或回复中
Substack Notes / 知识星球
Substack Notes / 知识星球
- Can be longer and more conversational
- Add more personal commentary and context
- Structure with short paragraphs
- OK to include bullet points for key takeaways
- 内容可更长,风格更口语化
- 加入更多个人评论和背景信息
- 用短段落组织内容
- 可使用项目符号列出核心要点
General Style
通用风格
- Write in the same language as the source content (Chinese article → Chinese post, English → English)
- If the user has a personal-writing-style skill, follow those preferences
- Avoid hype words ("revolutionary", "game-changing") — be genuine
- Be specific rather than vague ("reduces build time by 40%" > "makes things faster")
- 使用与源内容相同的语言撰写(中文文章→中文帖子,英文→英文)
- 若用户有个人写作风格相关技能,遵循其偏好
- 避免使用夸张词汇(如“革命性的”“改变游戏规则的”)——保持真诚
- 表述具体而非模糊(例如“将构建时间缩短40%”优于“让事情更快”)
Examples
示例
Example 1: User shares a link
示例1:用户分享链接
User: 分享一下这个 https://example.com/article-about-rust-in-linux
Claude: Fetches the page, reads the content, generates candidates:
候选 1:总结推荐型
Rust 正式进入 Linux 6.12 内核的网络子系统。这意味着内核中最关键、也最容易出内存安全问题的模块,开始用 Rust 重写了。
文章详细讲了迁移策略:不是一刀切,而是新模块用 Rust 写,老代码逐步替换。最实际的一点 - 已经在生产环境跑了 3 个月,零内存安全 bug。
候选 2:观点提炼型
"我们不是要用 Rust 重写 Linux,而是让新代码不再产生旧问题。"
Linux 网络子系统开始引入 Rust,最值得关注的不是语言之争,而是他们的渐进式迁移策略 - 这对所有大型 C 项目都有参考价值。
候选 3:讨论引导型
Linux 内核的网络子系统开始用 Rust 了。跑了 3 个月,零内存安全 bug。
但评论区有个好问题:Rust 的编译时间和学习曲线,对内核贡献者社区的影响会有多大?快速迭代和安全保障之间,怎么平衡?
Claude:获取页面内容,读取后生成候选帖子:
候选1:总结推荐型
Rust 正式进入 Linux 6.12 内核的网络子系统。这意味着内核中最关键、也最容易出现内存安全问题的模块,开始用 Rust 重写了。
文章详细介绍了迁移策略:并非一刀切,而是新模块用 Rust 编写,旧代码逐步替换。最值得关注的实际成果是——该模块已在生产环境运行3个月,未出现任何内存安全漏洞。
候选2:观点提炼型
“我们不是要用 Rust 重写 Linux,而是让新代码不再引发旧问题。”
Linux 网络子系统开始引入 Rust,最值得关注的并非语言之争,而是其渐进式迁移策略——这对所有大型C语言项目都具有参考价值。
候选3:讨论引导型
Linux 内核的网络子系统开始采用 Rust 编写。已运行3个月,未出现任何内存安全漏洞。
但评论区有个值得探讨的问题:Rust 的编译时间和学习曲线,会对内核贡献者社区产生多大影响?如何平衡快速迭代与安全保障?
Example 2: User shares with a specific angle
示例2:用户指定分享角度
User: share this, really interesting approach to prompt engineering https://example.com/prompt-patterns
Claude: Fetches the page, generates candidates focused on the user's angle (interesting approach):
Candidate 1: Highlight
This is the clearest framework I've seen for systematic prompt engineering. Instead of trial-and-error, the author breaks it down into 5 composable patterns you can mix and match.
The "constraint layering" pattern alone is worth the read — it's how they got GPT-4 to consistently output valid JSON without schema enforcement.
Candidate 2: Practical
If you're writing prompts for production (not just ChatGPT conversations), this is worth 10 minutes of your time.
Key insight: treat prompts like function signatures — define inputs, expected output shape, and edge case handling upfront. The author shares 5 patterns with before/after examples.
用户:分享这个,这篇关于提示词工程的方法真的很有意思 https://example.com/prompt-patterns
Claude:获取页面内容,围绕用户指定的角度(有趣的方法)生成候选帖子:
候选1:亮点提炼型
这是我见过的最清晰的系统化提示词工程框架。作者摒弃了试错法,将其拆解为5种可组合的模式,你可以灵活搭配使用。
单是“约束分层”模式就值得一读——这正是他们让GPT-4在无需模式强制的情况下持续输出有效JSON的方法。
候选2:实用导向型
如果你正在为生产环境编写提示词(而非仅用于ChatGPT对话),这篇文章值得你花10分钟阅读。
核心见解:将提示词视为函数签名——预先定义输入、预期输出格式和边缘情况处理方式。作者分享了5种模式,并配有前后对比示例。
Example 3: User provides notes directly
示例3:用户直接提供笔记
User: 帮我写个分享帖,关于我今天试用了 Cursor 的新 Background Agent 功能,感觉很惊艳,可以后台自动完成任务
Claude: No URL to fetch, works with the provided notes, asks:
要附上 Cursor 官方的介绍链接吗?或者你有截图/录屏想一起分享?Then generates candidates based on the user's first-hand experience.
用户:帮我写个分享帖,关于我今天试用了 Cursor 的新 Background Agent 功能,感觉很惊艳,它可以在后台自动完成任务
Claude:无需获取URL,直接使用提供的笔记,并询问:
要附上 Cursor 官方的介绍链接吗?或者你有截图/录屏想一起分享?随后根据用户的一手体验生成候选帖子。
Critical Rules
核心规则
- Always include the source link — never omit it
- Don't fabricate content — only reference what's actually in the article
- Match source language — Chinese content gets Chinese posts, English gets English
- Multiple candidates — always offer 2-3 options, not just one
- No auto-publishing — only generate text, don't execute any publishing
- Genuine tone — avoid marketing speak and excessive superlatives
- 必须包含来源链接 — 绝不可省略
- 不可编造内容 — 仅引用文章中实际存在的信息
- 匹配源内容语言 — 中文内容生成中文帖子,英文内容生成英文帖子
- 提供多个候选 — 始终提供2-3个选项,而非仅一个
- 禁止自动发布 — 仅生成文本,不执行任何发布操作
- 语气真诚 — 避免营销话术和过度夸张的形容词