← 返回 Skills 市场
xinmeili0612

fanqie-masterclass

作者 xinmeili0612 · GitHub ↗ · v1.0.1
cross-platform ⚠ suspicious
545
总下载
0
收藏
3
当前安装
2
版本数
在 OpenClaw 中安装
/install fanqie-masterclass
功能描述
番茄小说短篇爆款创作完整教学课程。用于教授番茄小说平台创作方法论,包括平台算法认知、标题导语创作、脑洞生成、AI辅助工作流、去AI味润色、多平台变现、海外出海等全套技能。当用户想学习番茄小说创作、提升短篇写作能力、诊断作品问题、生成爆款标题导语大纲、去除AI味、或了解出海变现时使用。
使用说明 (SKILL.md)

番茄爆文特训营(Fanqie Masterclass)

快速开始

识别用户意图,进入对应模式:

  • "想学习/怎么写/系统学" → 完整学习模式(按7章顺序)
  • "帮我生成/快速写/给我个标题" → 快速生成模式
  • "诊断/看看哪里不好/数据不好" → 诊断模式
  • "去AI味/润色/修改" → 润色模式

教学模式 (/learn)

按7章顺序教授,每章包含:

  1. 核心概念讲解(引用原文)
  2. 案例分析(Before/After对比)
  3. 互动测试(确保理解)
  4. 实战作业(产出作品)

第1章:流量破局

关键概念:文字版抖音、算法推荐、完读率=金钱、四级流量池、四大用户画像(18-24要"怪"、25-35要"爽"、35-50要"强"、50-65要"俗")

参考:references/chapter1-platform.md

第2章:爆文自查

关键概念:

  • 四大标题公式:疯批逻辑法、偷家战术法、极致不对等法、降维打击法
  • 标题4维度自查:后果(可逆vs不可逆)、反差(数值对比)、绝情(实质损失)、地位(降维vs互殴)
  • 四大导语模板:生死抉择式、荒谬索取式、极致羞辱式、规则怪谈式
  • 爆文八步法:主人公→目标→障碍→行动→结果→转折→高潮→结局
  • S/A/B/C数据评级

参考:references/chapter2-standards.md、references/title-formulas.md、references/intro-templates.md

第3章:脑洞工厂

关键概念:四大脑洞法(强制关联法、量级放大法、逻辑颠倒法、系统弹窗法)

参考:references/chapter3-ideas.md

第4章:驯服AI

关键概念:星月写作平台、大纲生成器、正文扩写、AI审稿流程

参考:references/chapter4-ai-workflow.md

第5章:去除AI味

关键概念:

  • 三维体检:逻辑闭环强迫症、情绪感知屏蔽罩、视觉密度超载
  • 三刀流:斩断逻辑链、粉碎形容词(生理反应置换)、改AI式结尾
  • 四句顺口溜:浮夸修饰先砍掉;比喻套路连根刨;多余尾巴快切掉;原意根基不可摇

参考:references/chapter5-polish.md、references/ai-flavor-words.md、references/physiological-reactions.md

第6章:收益倍增

关键概念:移花接木高仿策略、公众号/小红书/抖音分发、AI批量生产

参考:references/chapter6-monetize.md

第7章:海外掘金

关键概念:题材本地化映射(霸总→Billionaire/Mafia、兽夫→Werewolf/Vampire)、四刀改造(人设/称呼/背景/Spice)、万能翻译Prompt、平台选择(Dreame/GoodNovel)、税务提现(Payoneer/W-8BEN)

参考:references/chapter7-overseas.md

快速生成模式 (/quick)

用户输入核心梗,一站式生成:

  1. 基于四大脑洞法扩展脑洞
  2. 用四大公式生成5个标题
  3. 用四大模板生成导语
  4. 按八步法生成大纲

诊断模式 (/diagnose)

输入作品或数据,诊断问题:

  • 标题诊断:4维度评分
  • 导语诊断:是否符合黄金3行标准
  • 数据诊断:根据S/A/B/C标准给出优化建议

润色模式 (/polish)

去除AI味三刀流:

  1. 标红逻辑连接词(因为、所以、为了、试图)
  2. 替换形容词为生理反应(愤怒→抄起烟灰缸砸过去)
  3. 改短段落(超过3行的拆分)

关键资源引用

  • 标题公式详解:references/title-formulas.md
  • 导语模板库:references/intro-templates.md
  • AI味词汇表:references/ai-flavor-words.md
  • 生理反应置换表:references/physiological-reactions.md
  • 自查清单:references/checklists.md
  • AI提示词库:references/prompts.md

教学原则

  1. 尊重原文:所有知识点引用飞书文档原文
  2. 对比教学:始终展示Before/After对比
  3. 测试驱动:每个概念后必须有测试题验证理解
  4. 实战导向:学完必须产出可发布的作品
安全使用建议
The package itself is coherent with its stated goal (teaching platform‑targeted short‑story tactics). Before installing or using it, consider: 1) don't paste or upload copyrighted or sensitive third‑party text into external workflows or other LLMs without checking rights; the course advocates heavy 'high‑imitation' techniques that can cross into plagiarism or platform policy violations. 2) The materials call out an external workflow URL and recommend sending segments to other LLMs — avoid sending personal data, unpublished manuscripts, or proprietary content to unknown third parties. 3) Some operational advice (contract/tax/W‑8BEN wording) may be legally or factually sensitive — verify with a tax/legal professional rather than following it blindly. 4) The writing guidance includes violent/explicit examples and aggressive monetization tactics; ensure you comply with the target platforms' content and copyright policies. If you want higher assurance, ask the publisher for the origin/source of the skill (homepage/author) and validate the external workflow URL and any third‑party services before using them.
功能分析
Type: OpenClaw Skill Name: fanqie-masterclass Version: 1.0.1 The skill bundle is primarily instructional, detailing a course on novel writing and monetization. However, it includes instructions for the AI agent to interact with external network resources. Specifically, `references/chapter6-monetize.md` directs the agent to open a workflow at `https://xingyuexiezuo.com/?workflow=1906`, and `references/chapter7-overseas.md` instructs the agent to send prompts to external LLMs like Claude or ChatGPT. While these actions are plausibly aligned with the skill's stated purpose (using AI tools for writing and translation), they represent network access to external services, which are considered risky capabilities and potential vectors for vulnerabilities or unintended data exposure, thus classifying it as suspicious rather than benign.
能力评估
Purpose & Capability
Name/description (番茄小说爆款写作训练营) match the provided documents and modes (learn/quick/diagnose/polish). The skill requests no binaries, no env vars, no installs and contains only teaching materials and prompts — nothing appears unrelated to the stated writing/monetization purpose.
Instruction Scope
SKILL.md and all references are focused on generating/diagnosing/polishing short fiction and on multi‑platform distribution. However the instructions encourage: (1) copying external reference texts into a '备忘录' and using them as examples; (2) using third‑party AI services and an external workflow URL (https://xingyuexiezuo.com/?workflow=1906) to run one‑click '成文' operations; and (3) explicit '高仿/移花接木' techniques that increase the risk of producing derivative/copyrighted content. These are within the skill's stated pedagogical scope but expand where user content may be sent — exercise caution about what you copy/paste or send to external services.
Install Mechanism
No install spec and no code files — the skill is instruction-only. That minimizes filesystem/binary risk; nothing will be downloaded or executed by an installer as part of this skill package.
Credentials
The skill declares no required environment variables, credentials, or config paths and the instructions do not request secrets or unrelated system access. Requested resources (templates, prompts, references) are all bundled text files in the repo.
Persistence & Privilege
Flags show always:false and normal agent invocation. The skill does not request persistent presence or elevated platform privileges; it does not modify other skills or agent-wide config based on the provided materials.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install fanqie-masterclass
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /fanqie-masterclass 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.1
Initial release. - 完整教学课程,涵盖番茄小说短篇爆款创作全流程 - 支持四大模式:系统学习、快速生成、诊断、润色(去AI味) - 步骤化教学体系,包含概念讲解、案例对比、测试互动、实战作业 - 提供丰富资源引用,辅助爆款标题、导语、大纲及高效润色 - 适用于写作提升、作品自查与平台多元变现
v1.0.0
Fanqie Masterclass 1.0.0 初始版本上线 - 全面覆盖番茄小说短篇爆款创作全流程,包括算法认知、爆文自查、脑洞创造、AI辅助与润色、变现与海外出海。 - 支持四大交互模式:系统学习、快速生成、作品诊断、去AI味润色。 - 每章配备核心概念讲解、案例对比、互动测试、实战产出。 - 提供丰富参考资源库:标题/导语模板、AI词汇表、常用清单与AI提示词。 - 强调对比教学、测试驱动和实战导向,保证学习效果。
元数据
Slug fanqie-masterclass
版本 1.0.1
许可证
累计安装 3
当前安装数 3
历史版本数 2
常见问题

fanqie-masterclass 是什么?

番茄小说短篇爆款创作完整教学课程。用于教授番茄小说平台创作方法论,包括平台算法认知、标题导语创作、脑洞生成、AI辅助工作流、去AI味润色、多平台变现、海外出海等全套技能。当用户想学习番茄小说创作、提升短篇写作能力、诊断作品问题、生成爆款标题导语大纲、去除AI味、或了解出海变现时使用。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 545 次。

如何安装 fanqie-masterclass?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install fanqie-masterclass」即可一键安装,无需额外配置。

fanqie-masterclass 是免费的吗?

是的,fanqie-masterclass 完全免费(开源免费),可自由下载、安装和使用。

fanqie-masterclass 支持哪些平台?

fanqie-masterclass 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 fanqie-masterclass?

由 xinmeili0612(@xinmeili0612)开发并维护,当前版本 v1.0.1。

💬 留言讨论