← 返回 Skills 市场
tujinsama

流量重组洗稿虾

作者 Ricky · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
183
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install content-rewriter-claw
功能描述
流量重组洗稿虾 — 基于爆款逻辑的深度内容改写专家。保留爆款基因,规避重复风险,快速产出高质量原创内容。 **当以下情况时使用此 Skill**: (1) 需要将爆款内容改写为符合自己账号风格的原创版本 (2) 需要跨平台内容迁移(长文→短视频脚本、视频→图文) (3) 需要基于同一核心观点生成多个不同角度的内容...
使用说明 (SKILL.md)

流量重组洗稿虾 (content-rewriter-claw)

工作流程

步骤 1:解构原始内容

分析原文的核心要素:

  • 核心观点/论点
  • 论证逻辑(因果/对比/递进)
  • 情绪共鸣点
  • 金句/亮点
  • 数据/案例
  • 结构框架

步骤 2:提炼爆款基因

识别内容为什么会爆的关键因素,参考 references/viral-gene-model.md

  • 标题钩子类型(悬念/痛点/反常识/数字/共鸣)
  • 情绪触发器(焦虑/好奇/愤怒/感动/共鸣)
  • 传播结构(起承转合节奏)
  • 价值密度

步骤 3:选择改写深度

根据用户需求或内容风险选择改写深度,详见 references/rewrite-rules.md

  • shallow:浅层改写(快速产出,重复率30-50%)
  • medium:中层改写(大多数场景,重复率10-30%)
  • deep:深度重构(高风险内容,重复率\x3C10%)
  • full:完全原创(仅保留核心观点,重复率\x3C5%)

用户未指定时,默认使用 deep(安全优先)。

步骤 4:执行改写

按选定深度改写内容,同时:

  • 保留爆款基因(钩子类型、情绪触发点、传播结构不变,内容全换)
  • 适配目标账号风格(语言风格、句式、人称、特色表达)
  • 适配目标平台规范(如有指定)

步骤 5:合规检查

改写完成后,对照 references/compliance-rules.md 检查:

  • 估算重复率是否达标
  • 检查绝对化用语和平台敏感词
  • 评估版权风险

步骤 6:输出结果

输出格式:

  1. 改写后的内容(完整版)
  2. 改写说明:简述做了哪些改动(改写深度、角度转换、案例替换等)
  3. 合规评估:预估重复率区间、风险等级

辅助脚本

scripts/rewrite-content.py:生成结构化改写 prompt,适合批量处理场景。

python3 scripts/rewrite-content.py --input "原文内容" --depth deep --style "轻松幽默" --platform xiaohongshu
python3 scripts/rewrite-content.py --input-file content.txt --depth medium --output result.json

参数:

  • --depth:shallow / medium / deep / full
  • --style:目标风格描述(如"专业严谨"、"轻松幽默")
  • --platform:目标平台(douyin / xiaohongshu / wechat / bilibili)
  • --keep:必须保留的要素(逗号分隔)
  • --avoid:需要规避的要素(逗号分隔)

参考资料

  • references/rewrite-rules.md:改写深度层级定义和操作清单
  • references/viral-gene-model.md:爆款基因提炼模型(钩子公式、情绪触发器、传播结构)
  • references/compliance-rules.md:查重阈值、平台敏感词、版权风险评估

注意事项

  • 改写不等于可以随意使用他人内容,注意版权边界
  • 深度改写需要较长时间,告知用户预期等待
  • 改写质量依赖原文质量
  • 不支持视频内容直接改写(仅支持文字)
安全使用建议
This skill appears coherent and implements a local prompt-builder plus clear rewrite rules, but consider the following before installing or using it: - Copyright and platform rules: Rewriting/"洗稿" can still infringe copyright if unique expressions, large verbatim blocks, or exclusive data are reused. Do not feed confidential or copyrighted material unless you have rights; verify outputs with a plagiarism tool or legal review for high-risk content. - Compliance is partly heuristic: The SKILL.md and references define thresholds and sensitive-word checks, but the package provides no automated duplication checker. If you need legal certainty, run a dedicated duplication/plagiarism scan on outputs. - Model invocation: The script only generates prompts; actual rewriting will occur when your agent/LLM processes those prompts. Ensure the model you use and any downstream services comply with privacy and content policies and that you don't inadvertently send secrets in prompts. - Ethical/platform risk: The skill intentionally preserves "viral hooks" (钩子/传播结构). This is expected for the stated purpose but may encourage tactics that skirt platform policies—review final outputs for policy compliance and avoid using it to evade takedowns or platform enforcement. Overall: technically coherent and low-risk from a packaging/permissions perspective, but treat legal/copyright risk as a separate operational concern and verify outputs before publishing.
功能分析
Type: OpenClaw Skill Name: content-rewriter-claw Version: 1.0.0 The skill is a content rewriting tool designed to adapt viral content for different platforms while minimizing plagiarism detection. The Python script `scripts/rewrite-content.py` is a safe utility that generates structured prompts for the AI agent, and the documentation in `SKILL.md` and the `references/` directory provides clear, non-malicious instructions for content analysis and transformation. No evidence of data exfiltration, unauthorized execution, or prompt injection attacks was found.
能力评估
Purpose & Capability
Name/description (content rewrite, cross-platform adaptation, compliance) match the included materials: SKILL.md, rewrite rules, viral-gene model, compliance checklist, and a small prompt-generator script. Nothing requested (no env vars, binaries, or installs) is out of scope for a content-rewriter.
Instruction Scope
Runtime instructions focus on analyzing and rewriting text, selecting rewrite depth, and running a local script to build structured prompts. They also require estimating duplication and checking platform-sensitive words. Note: the skill instructs aiming for low duplication (<10%) but provides no automated plagiarism-checking tool—that step is a manual/heuristic compliance check, so outputs should still be verified with a dedicated plagiarism tool if legal certainty is needed.
Install Mechanism
No install spec; the skill is instruction-only plus a small Python script. There are no external downloads or installers, and the script performs only local prompt generation and I/O.
Credentials
The skill requests no environment variables, credentials, or config paths. All required inputs are provided by the user at runtime (text, file paths, depth/style/platform flags).
Persistence & Privilege
always is false and the skill does not attempt to modify other skills or system-wide settings. It requires no persistent presence or elevated privileges.
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 content-rewriter-claw
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /content-rewriter-claw 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
v1.0.0
Initial release: 基于爆款逻辑的深度内容改写专家,支持4种改写深度,含爆款基因提炼模型和合规检查规则
元数据
Slug content-rewriter-claw
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

流量重组洗稿虾 是什么?

流量重组洗稿虾 — 基于爆款逻辑的深度内容改写专家。保留爆款基因,规避重复风险,快速产出高质量原创内容。 **当以下情况时使用此 Skill**: (1) 需要将爆款内容改写为符合自己账号风格的原创版本 (2) 需要跨平台内容迁移(长文→短视频脚本、视频→图文) (3) 需要基于同一核心观点生成多个不同角度的内容... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 183 次。

如何安装 流量重组洗稿虾?

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

流量重组洗稿虾 是免费的吗?

是的,流量重组洗稿虾 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

流量重组洗稿虾 支持哪些平台?

流量重组洗稿虾 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 流量重组洗稿虾?

由 Ricky(@tujinsama)开发并维护,当前版本 v1.0.0。

💬 留言讨论