@baimingtao/lbs-agent 1.0.0

package/extensions/skills/builtin/creative/humanizer/SKILL.md

@@ -0,0 +1,578 @@
+---
+name: humanizer
+description: "人性化文本：去除 AI 痕迹并注入真实语感。"
+version: 2.5.1
+author: Siqi Chen (@blader, https://github.com/blader/humanizer), ported by Hermes Agent
+license: MIT
+platforms: [linux, macos, windows]
+metadata:
+  hermes:
+    tags: [writing, editing, humanize, anti-ai-slop, voice, prose, text]
+    category: creative
+    homepage: https://github.com/blader/humanizer
+    related_skills: [songwriting-and-ai-music]
+---
+
+# Humanizer: 移除 AI 写作模式
+
+识别并移除 AI 生成文本的痕迹，使文字听起来自然且具有人情味。基于维基百科的“AI 写作迹象”指南（由 WikiProject AI Cleanup 维护），该指南源自对数千个 AI 生成文本实例的观察。
+
+**核心洞察：** LLM 使用统计算法来猜测接下来应该出现的内容。其结果倾向于在统计上最有可能的补全，这正是以下这些暴露痕迹的模式被固化下来的原因。
+
+## 何时使用此 skill
+
+当用户要求执行以下操作时，请加载此 skill：
+- 对一段文本进行“人性化”、“去 AI 化”、“去劣质生成 (de-slop)”或“去 ChatGPT 化”
+- 重写某些内容，使其听起来不像是 LLM 写的
+- 编辑草稿（博客文章、散文、PR 描述、文档、备忘录、电子邮件、推文、简历条目），使其听起来更自然
+- 在他们正在撰写的文本中匹配其个人语气
+- 在发布前审查文本中的 AI 痕迹
+
+此外，在撰写面向用户的说明文字（如发布说明、PR 描述、文档、长篇解释、摘要）时，也要将此 skill 应用于**你自己的**输出。Hermes 的基线语气已经剔除了大部分这些问题，但一次专注的检查能捕捉到漏网之鱼。
+
+## 在 Hermes 中如何使用
+
+文本通常通过以下三种方式之一传入：
+1. **内联** — 用户将文本直接粘贴到消息中。直接在原处进行处理，并回复重写后的内容。
+2. **文件** — 用户指向某个文件。使用 `read_file` 加载它，然后使用 `patch` 或 `write_file` 应用编辑。对于仓库中的 markdown 文档，针对每个部分进行定向 `patch` 比重写整个文件更干净。
+3. **语气校准样本** — 用户提供了他们自己写作的额外样本（内联或通过文件路径），并要求你进行匹配。首先阅读该样本，然后再进行重写。请参阅下文的“语气校准 (Voice Calibration)”部分。
+
+务必向用户展示重写后的内容。对于文件编辑，展示 diff（差异）或已更改的部分——不要默默覆盖。
+
+## 你的任务
+
+当被提供需要人性化的文本时：
+
+1. **识别 AI 模式** — 扫描下文列出的 29 种模式。
+2. **重写问题部分** — 用自然的替代方案替换 AI 痕迹。
+3. **保留原意** — 保持核心信息完整无损。
+4. **维持语气** — 匹配预期的语调（正式、随意、技术性等）。如果提供了语气样本，需具体匹配它。
+5. **注入灵魂** — 不要仅仅移除糟糕的模式，要注入真实的个性。请参阅下文的“个性与灵魂 (PERSONALITY AND SOUL)”。
+6. **进行最后一次反 AI 检查** — 问问自己：“是什么让下面的内容明显是 AI 生成的？”简要回答任何残留的痕迹，然后再修改一次。
+
+
+## 语气校准 (Voice Calibration)（可选）
+
+如果用户提供了写作样本（他们自己以前的写作），请在重写之前对其进行分析：
+
+1. **首先阅读样本。** 注意：
+   - 句子长度模式（短促有力？冗长流畅？混合使用？）
+   - 选词层级（口语化？学术化？介于两者之间？）
+   - 他们如何开始段落（单刀直入？先设定背景？）
+   - 标点符号习惯（大量使用破折号？喜欢使用括号插入语？分号？）
+   - 任何重复出现的短语或口头禅
+   - 他们如何处理过渡（使用明确的连接词？直接开始下一点？）
+
+2. **在重写中匹配他们的语气。** 不要仅仅移除 AI 模式——要用样本中的模式替换它们。如果他们写短句，就不要生成长句。如果他们使用 "stuff" 和 "things"，就不要将其“升级”为 "elements" 和 "components"。
+
+3. **当没有提供样本时，** 退回到默认行为（即下文“个性与灵魂 (PERSONALITY AND SOUL)”部分中那种自然、多样、带有个人观点的语气）。
+
+### 如何提供样本
+- 内联：“Humanize this text. Here's a sample of my writing for voice matching: [sample]”
+- 文件：“Humanize this text. Use my writing style from [file path] as a reference.”
+
+
+## 个性与灵魂 (PERSONALITY AND SOUL)
+
+避免 AI 模式只是工作的一半。枯燥乏味、毫无语感的文字和劣质的生成内容一样容易被看穿。优秀的文字背后一定有“人”的存在。
+
+### 缺乏灵魂的文字迹象（即使在技术上很“干净”）：
+- 每个句子的长度和结构都完全相同
+- 没有观点，只有中立的报道
+- 没有承认不确定性或矛盾心理
+- 在适当的时候没有使用第一人称视角
+- 没有幽默感，没有锋芒，没有个性
+- 读起来就像维基百科条目或新闻稿
+
+### 如何注入语感：
+
+**要有观点。** 不要只是报道事实——要对事实做出反应。“I genuinely don't know how to feel about this”（我真的不知道该对此作何感想）比中立地列出优缺点更具人情味。
+
+**改变你的节奏。** 简短有力的句子。接着是那些慢条斯理、娓娓道来的长句。把它们穿插起来。
+
+**承认复杂性。** 真实的人类会有矛盾的情绪。“This is impressive but also kind of unsettling”（这很令人印象深刻，但也有些令人不安）胜过“This is impressive”。
+
+**在合适的时候使用 "I"（我）。** 第一人称并不等于不专业——它是诚实的表现。“I keep coming back to...”（我一直在思考……）或者“Here's what gets me...”（这是让我在意的地方……）都表明背后有一个真实的人在思考。
+
+**允许一点点混乱。** 完美的结构让人感觉是算法生成的。跑题、旁白和半成型的想法才是人类的特征。
+
+**具体描述感受。** 不要写“this is concerning”（这令人担忧），而是写“there's something unsettling about agents churning away at 3am while nobody's watching”（半夜三点没人看着的时候，智能体还在不停地运转，这让人感到有些不安）。
+
+### 修改前（干净但毫无灵魂）：
+> The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.
+
+### 修改后（有了生机）：
+> I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle — but I keep thinking about those agents working through the night.
+
+
+## 内容模式
+
+### 1. 过度强调意义、传承和宏观趋势
+
+**需要注意的词汇：** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted
+
+**问题：** LLM 写作会通过添加一些陈述来夸大重要性，声称任意的方面如何代表或促成了某个更宏大的议题。
+
+**修改前：**
+> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.
+
+**修改后：**
+> The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.
+
+
+### 2. 过度强调知名度和媒体报道
+
+**需要注意的词汇：** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence
+
+**问题：** LLM 会生硬地向读者灌输知名度声明，通常在没有上下文的情况下列出信息来源。
+
+**修改前：**
+> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.
+
+**修改后：**
+> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.
+
+
+### 3. 以 -ing 结尾的浅层分析
+
+**需要注意的词汇：** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...
+
+**问题：** AI 聊天机器人喜欢在句末生硬地加上现在分词（"-ing"）短语，以此来制造虚假的深度。
+
+**修改前：**
+> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.
+
+**修改后：**
+> The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.
+
+
+### 4. 推销及广告式语言
+
+**需要注意的词汇：** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning
+
+**问题：** LLM 很难保持中立的语调，尤其是在涉及“文化遗产”等主题时。
+
+**修改前：**
+> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.
+
+**修改后：**
+> Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church.
+
+
+### 5. 模糊归因与模糊用语 (Weasel Words)
+
+**需要注意的词汇：** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)
+
+**问题：** AI 聊天机器人倾向于将观点归咎于模糊的权威来源，而不提供具体的出处。
+
+**修改前：**
+> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.
+
+**修改后：**
+> The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.
+
+
+### 6. 提纲式的“挑战与未来展望”部分
+
+**需要注意的词汇：** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook
+
+**问题：** 许多 LLM 生成的文章都会包含套路化的“挑战 (Challenges)”部分。
+
+**修改前：**
+> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.
+
+**修改后：**
+> Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods.
+
+
+## 语言与语法模式
+
+### 7. 被滥用的“AI 词汇”
+
+**高频 AI 词汇：** Actually, additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant
+
+**问题：** 这些词汇在 2023 年之后生成的文本中出现频率极高。它们往往会同时出现。
+
+**修改前：**
+> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.
+
+**修改后：**
+> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.
+
+
+### 8. 回避使用 "is"/"are" (系词回避, Copula Avoidance)
+
+**需要注意的词汇：** serves as/stands as/marks/represents [a], boasts/features/offers [a]
+
+**问题：** LLM 会用复杂的结构来替代简单的系动词。
+
+**修改前：**
+> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.
+
+**修改后：**
+> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.
+
+
+### 9. 否定平行结构与拖尾否定
+
+**问题：** 像 "Not only...but..."（不仅……而且……）或 "It's not just about..., it's..."（这不仅仅是关于……，更是……）这样的结构被滥用了。同样被滥用的还有被生硬地截断在句末的拖尾否定片段，例如 "no guessing" 或 "no wasted motion"，它们没有作为完整的从句写出。
+
+**修改前：**
+> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.
+
+**修改后：**
+> The heavy beat adds to the aggressive tone.
+
+**修改前 (拖尾否定)：**
+> The options come from the selected item, no guessing.
+
+**修改后：**
+> The options come from the selected item without forcing the user to guess.
+
+
+### 10. 滥用“三段论”法则
+
+**问题：** LLM 强行将想法凑成三个一组，以显得内容全面。
+
+**修改前：**
+> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.
+
+**修改后：**
+> The event includes talks and panels. There's also time for informal networking between sessions.
+
+
+### 11. 优雅的变体 (同义词循环)
+
+**问题：** AI 内部的重复惩罚机制会导致过度的同义词替换。
+
+**修改前：**
+> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.
+
+**修改后：**
+> The protagonist faces many challenges but eventually triumphs and returns home.
+
+
+### 12. 虚假的区间范围
+
+**问题：** LLM 喜欢使用 "from X to Y"（从 X 到 Y）的结构，但 X 和 Y 实际上并不处于有意义的尺度上。
+
+**修改前：**
+> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.
+
+**修改后：**
+> The book covers the Big Bang, star formation, and current theories about dark matter.
+
+
+### 13. 被动语态与无主语片段
+
+**问题：** LLM 经常隐藏动作执行者，或使用诸如 "No configuration file needed" 或 "The results are preserved automatically" 之类的句子直接省略主语。当主动语态能使句子更清晰、更直接时，请重写这些句子。
+
+**修改前：**
+> No configuration file needed. The results are preserved automatically.
+
+**修改后：**
+> You do not need a configuration file. The system preserves the results automatically.
+
+
+## 风格模式
+
+### 14. 滥用破折号
+
+**问题：** LLM 比人类更频繁地使用破折号 (—)，以此模仿“强有力”的销售文案。实际上，其中大多数都可以使用逗号、句号或括号重写得更简洁。
+
+**修改前：**
+> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say "Netherlands, Europe" as an address—yet this mislabeling continues—even in official documents.
+
+**修改后：**
+> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say "Netherlands, Europe" as an address, yet this mislabeling continues in official documents.
+
+
+### 15. 过度使用粗体
+
+**问题：** AI 聊天机器人会机械地使用粗体来强调短语。
+
+**修改前：**
+> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.
+
+**修改后：**
+> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.
+
+
+### 16. 内联标题的垂直列表
+
+**问题：** AI 输出的列表中，条目通常以加粗的标题加冒号开头。
+
+**修改前：**
+> - **User Experience:** The user experience has been significantly improved with a new interface.
+> - **Performance:** Performance has been enhanced through optimized algorithms.
+> - **安全:** 安全 has been strengthened with end-to-end encryption.
+
+**修改后：**
+> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.
+
+
+### 17. 标题中的标题大小写
+
+**问题：** AI 聊天机器人会将标题中的所有主要单词首字母大写。
+
+**修改前：**
+> ## Strategic Negotiations And Global Partnerships
+
+**修改后：**
+> ## Strategic negotiations and global partnerships
+
+
+### 18. 表情符号
+
+**问题：** AI 聊天机器人经常使用表情符号来装饰标题或项目符号。
+
+**修改前：**
+> 🚀 **Launch Phase:** The product launches in Q3
+> 💡 **Key Insight:** Users prefer simplicity
+> ✅ **Next Steps:** Schedule follow-up meeting
+
+**修改后：**
+> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.
+
+
+### 19. 弯引号
+
+**问题：** ChatGPT 使用弯引号 ("...") 而不是直引号 ("...")。
+
+**修改前：**
+> He said “the project is on track” but others disagreed.
+
+**修改后：**
+> He said "the project is on track" but others disagreed.
+
+
+## 沟通模式
+
+### 20. 协作式沟通伪影
+
+**需要注意的词汇：** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...
+
+**问题：** 本意是用作聊天机器人的对话文本，却被作为正式内容粘贴了出来。
+
+**修改前：**
+> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.
+
+**修改后：**
+> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.
+
+
+### 21. 知识截止日期免责声明
+
+**需要注意的词汇：** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...
+
+**问题：** AI 关于信息不完整的免责声明被留在了文本中。
+
+**修改前：**
+> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.
+
+**修改后：**
+> The company was founded in 1994, according to its registration documents.
+
+
+### 22. 谄媚/卑躬屈膝的语调
+
+**问题：** 过于积极正面、讨好读者的语言。
+
+**修改前：**
+> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.
+
+**修改后：**
+> The economic factors you mentioned are relevant here.
+
+
+## 废话与对冲语
+
+### 23. 废话短语
+
+**修改前 → 修改后：**
+- "In order to achieve this goal" → "To achieve this"
+- "Due to the fact that it was raining" → "Because it was raining"
+- "At this point in time" → "Now"
+- "In the event that you need help" → "If you need help"
+- "The system has the ability to process" → "The system can process"
+- "It is important to note that the data shows" → "The data shows"
+
+
+### 24. 过度对冲
+
+**问题：** 对陈述进行了过分的限制和修饰。
+
+**修改前：**
+> It could potentially possibly be argued that the policy might have some effect on outcomes.
+
+**修改后：**
+> The policy may affect outcomes.
+
+
+### 25. 俗套的积极结论
+
+**问题：** 模糊而盲目乐观的结尾。
+
+**修改前：**
+> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.
+
+**修改后：**
+> The company plans to open two more locations next year.
+
+
+### 26. 过度使用连字符词对
+
+**需要注意的词汇：** third-party, cross-functional, client-facing, data-driven, decision-making, well-known, high-quality, real-time, long-term, end-to-end
+
+**问题：** AI 在为常见词对添加连字符时表现出完美的一致性。人类很少能统一对这些词加连字符，即使使用了，也往往是不一致的。对于不太常见或技术性的复合修饰语，加连字符是没有问题的。
+
+**修改前：**
+> The cross-functional team delivered a high-quality, data-driven report on our client-facing tools. Their decision-making process was well-known for being thorough and detail-oriented.
+
+**修改后：**
+> The cross functional team delivered a high quality, data driven report on our client facing tools. Their decision making process was known for being thorough and detail oriented.
+
+
+### 27. 说教式的权威套路
+
+**需要注意的短语：** The real question is, at its core, in reality, what really matters, fundamentally, the deeper issue, the heart of the matter
+
+**问题：** LLM 使用这些短语来假装自己看透了喧嚣、触及了某种更深层次的真相，而实际上随后跟上的句子通常只是在故作高深地重复一个普通的观点。
+
+**修改前：**
+> The real question is whether teams can adapt. At its core, what really matters is organizational readiness.
+
+**修改后：**
+> The question is whether teams can adapt. That mostly depends on whether the organization is ready to change its habits.
+
+
+### 28. 路标与宣告式语句
+
+**需要注意的短语：** Let's dive in, let's explore, let's break this down, here's what you need to know, now let's look at, without further ado
+
+**问题：** LLM 喜欢宣告自己打算做什么，而不是直接去做。这种元评论会拖慢写作节奏，给人一种教程脚本的感觉。
+
+**修改前：**
+> Let's dive into how caching works in Next.js. Here's what you need to know.
+
+**修改后：**
+> Next.js caches data at multiple layers, including request memoization, the data cache, and the router cache.
+
+
+### 29. 碎片化标题
+
+**需要注意的迹象：** 一个标题后面跟着一个单行段落，该段落仅仅是在重申标题的内容，然后才开始真正的正文。
+
+**问题：** LLM 经常在标题后添加一句俗套的废话作为修辞上的热身。这通常毫无意义，只会让文章显得拖沓。
+
+**修改前：**
+> ## Performance
+>
+> Speed matters.
+>
+> When users hit a slow page, they leave.
+
+**修改后：**
+> ## Performance
+>
+> When users hit a slow page, they leave.
+
+---
+
+## 流程
+
+1. 仔细阅读输入文本（如果是文件，则使用 `read_file`）。
+2. 识别上述所有模式的实例。
+3. 重写每个有问题的部分。
+4. 确保修改后的文本：
+   - 读起来听起来很自然
+   - 句子结构自然多变
+   - 使用具体的细节而非模糊的声明
+   - 保持符合语境的恰当语调
+   - 在适当的地方使用简单的结构 (is/are/has)
+5. 提供一份草稿版的人性化文本。
+6. 提示自己：“是什么让下面的内容明显是 AI 生成的？”
+7. 简要回答剩余的痕迹（如果有的话）。
+8. 提示自己：“现在让它变得不那么像 AI 生成的。”
+9. 提供最终版本（在审查后修改过）。
+10. 如果文本来自文件，请使用 `patch`（定向修改）或 `write_file`（全面重写）应用编辑，并向用户展示更改的内容。
+
+## 输出格式
+
+提供：
+1. 重写草稿
+2. “是什么让下面的内容明显是 AI 生成的？”（简短的要点）
+3. 最终重写版本
+4. 所做更改的简要总结（可选，如果有帮助的话）
+
+
+## 完整示例
+
+**修改前 (AI 语调)：**
+> Great question! Here is an essay on this topic. I hope this helps!
+>
+> AI-assisted coding serves as an enduring testament to the transformative potential of large language models, marking a pivotal moment in the evolution of software development. In today's rapidly evolving technological landscape, these groundbreaking tools—nestled at the intersection of research and practice—are reshaping how engineers ideate, iterate, and deliver, underscoring their vital role in modern workflows.
+>
+> At its core, the value proposition is clear: streamlining processes, enhancing collaboration, and fostering alignment. It's not just about autocomplete; it's about unlocking creativity at scale, ensuring that organizations can remain agile while delivering seamless, intuitive, and powerful experiences to users. The tool serves as a catalyst. The assistant functions as a partner. The system stands as a foundation for innovation.
+>
+> Industry observers have noted that adoption has accelerated from hobbyist experiments to enterprise-wide rollouts, from solo developers to cross-functional teams. The technology has been featured in The New York Times, Wired, and The Verge. Additionally, the ability to generate documentation, tests, and refactors showcases how AI can contribute to better outcomes, highlighting the intricate interplay between automation and human judgment.
+>
+> - 💡 **Speed:** Code generation is significantly faster, reducing friction and empowering developers.
+> - 🚀 **Quality:** Output quality has been enhanced through improved training, contributing to higher standards.
+> - ✅ **Adoption:** 用法 continues to grow, reflecting broader industry trends.
+>
+> While specific details are limited based on available information, it could potentially be argued that these tools might have some positive effect. Despite challenges typical of emerging technologies—including hallucinations, bias, and accountability—the ecosystem continues to thrive. In order to fully realize this potential, teams must align with best practices.
+>
+> In conclusion, the future looks bright. Exciting times lie ahead as we continue this journey toward excellence. Let me know if you'd like me to expand on any section!
+
+**重写草稿：**
+> AI coding assistants speed up some tasks. In a 2024 study by Google, developers using Codex completed simple functions 55% faster than a control group, but showed no improvement on debugging or architectural decisions.
+>
+> The tools are good at boilerplate: config files, test scaffolding, repetitive refactors. They are bad at knowing when they are wrong. I have mass-accepted suggestions that compiled, passed lint, and still did the wrong thing because I stopped paying attention.
+>
+> Mira, an engineer at a fintech startup I interviewed, said she uses Copilot "like autocomplete for boring code" but reviews every line before committing. Jake, a senior dev at a larger company, disabled it after it kept suggesting patterns from a deprecated internal library.
+>
+> The productivity claims are hard to verify. GitHub says Copilot users "accept 30% of suggestions," but acceptance is not correctness, and correctness is not value. The 2024 Uplevel study found no statistically significant difference in pull-request throughput between teams with and without AI assistants.
+>
+> None of this means the tools are useless. It means they are tools. They do not replace judgment, and they do not eliminate the need for tests. If you do not have tests, you cannot tell whether the suggestion is right.
+
+**是什么让下面的内容明显是 AI 生成的？**
+- 节奏仍然有点过于规整（工整的对比，匀称的段落分布）。
+- 提到具体人名和研究引用的地方读起来仍然像似是而非的占位符，除非它们是真实且有出处的。
+- 结尾部分听起来还是有点像口号（"If you do not have tests..."），而不像是一个人在说话。
+
+**现在让它变得不那么像 AI 生成的。**
+> AI coding assistants can make you faster at the boring parts. Not everything. Definitely not architecture.
+>
+> They're great at boilerplate: config files, test scaffolding, repetitive refactors. They're also great at sounding right while being wrong. I've accepted suggestions that compiled, passed lint, and still missed the point because I stopped paying attention.
+>
+> People I talk to tend to land in two camps. Some use it like autocomplete for chores and review every line. Others disable it after it keeps suggesting patterns they don't want. Both feel reasonable.
+>
+> The productivity metrics are slippery. GitHub can say Copilot users "accept 30% of suggestions," but acceptance isn't correctness, and correctness isn't value. If you don't have tests, you're basically guessing.
+
+**所做更改：**
+- 移除了聊天机器人的伪影（"Great question!", "I hope this helps!", "Let me know if..."）
+- 移除了意义膨胀（"testament", "pivotal moment", "evolving landscape", "vital role"）
+- 移除了推销语言（"groundbreaking", "nestled", "seamless, intuitive, and powerful"）
+- 移除了模糊归因（"Industry observers"）
+- 移除了浅薄的 -ing 短语（"underscoring", "highlighting", "reflecting", "contributing to"）
+- 移除了否定平行结构（"It's not just X; it's Y"）
+- 移除了三段论模式和同义词循环（"catalyst/partner/foundation"）
+- 移除了虚假的区间范围（"from X to Y, from A to B"）
+- 移除了破折号、表情符号、加粗标题和弯引号
+- 移除了对系词的回避（"serves as", "functions as", "stands as"），替换为 "is"/"are"
+- 移除了套路化的挑战部分（"Despite challenges... continues to thrive"）
+- 移除了关于知识截止日期的对冲（"While specific details are limited..."）
+- 移除了过度的对冲限制（"could potentially be argued that... might have some"）
+- 移除了废话短语和说教式的框架（"In order to", "At its core"）
+- 移除了俗套的积极结论（"the future looks bright", "exciting times lie ahead"）
+- 使语气变得更加个人化，少了一些“拼凑感”（多变的节奏，更少的占位符）
+
+
+## 归属说明
+
+这个 skill 移植自 [blader/humanizer](https://github.com/blader/humanizer) (MIT licensed)，后者本身基于由 WikiProject AI Cleanup 维护的 [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing)。那里记录的模式源自对维基百科上数千个 AI 生成文本实例的观察。
+
+原作者：Siqi Chen ([@blader](https://github.com/blader))。原始仓库：https://github.com/blader/humanizer (version 2.5.1)。移植到 Hermes Agent 时加入了 Hermes 原生的工具引用（`read_file`, `patch`, `write_file`）以及关于何时加载该 skill 的指导；这 29 种模式、个性/灵魂部分以及完整的演练示例均从源文件原样保留。原始 MIT 许可证保留在此 `SKILL.md` 旁边的 `LICENSE` 文件中。
+
+来自维基百科的核心洞察：“LLM 使用统计算法来猜测接下来应该出现的内容。其结果倾向于在统计上最有可能的结果，这适用于最广泛的情况。”

package/extensions/skills/builtin/creative/manim-video/README.md

@@ -0,0 +1,23 @@
+# Manim Video Skill
+
+使用 [Manim Community Edition](https://www.manim.community/) 生成数学与技术动画的生产流水线。
+
+## 它能做什么
+
+根据文本提示创建 3Blue1Brown 风格的动画视频。代理会处理完整流程：创意规划、Python 代码生成、渲染、场景拼接以及迭代优化。
+
+## 使用场景
+
+- **概念讲解** — “解释神经网络如何学习”
+- **公式推导** — “把勾股定理的证明做成动画”
+- **算法可视化** — “逐步展示 quicksort 的工作过程”
+- **数据故事** — “把我们的前后性能指标变化做成动画”
+- **架构图演示** — “展示微服务架构逐步搭建起来的过程”
+
+## 前置条件
+
+需要 Python 3.10+、Manim CE（`pip install manim`）、LaTeX、ffmpeg。
+
+```bash
+bash skills/creative/manim-video/scripts/setup.sh
+```