移除多厂商AI溯源标记：不可见Unicode（A层）、通过重写消除统计文本水印（B层，始终提供）以及对PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD/TEX格式文件中的C2PA/EXIF/XMP/容器元数据进行清理。适用于Claude、Gemini/SynthID类、OpenAI溯源及开源LLM采样标记。
该技能（ToddModica/remove-ai-marks）旨在帮助用户从AI生成的输出中移除各类溯源标记，包括不可见Unicode字符（A层）、统计文本水印（B层，通过重写实现）以及C2PA/EXIF/XMP/容器元数据。它支持多种文件格式（如PNG、JPEG、WebP、SVG、PDF、DOCX、ODT、HTML、MD和TEX），并覆盖了主流AI平台（如Claude、Gemini/SynthID类、OpenAI及开源LLM）的标记。用户可以通过自然语言请求（如“去除水印”、“移除C2PA/Content Credentials”、“清理AI元数据”、“去除不可见Unicode”、“反检测清理AI输出”）或使用斜杠命令（/remove-ai-marks，别名/remove-claude-marks）来触发该操作。该技能通过解析文件内容、识别并擦除隐藏标记，在必要时对文本进行重写以消除统计水印，从而帮助用户实现“反检测”或“清洁AI输出”的目的。
npx skills add https://github.com/ToddModica/codex-upstream-skills-marketplace/tree/main/plugins/watermarks-remover/skills/remove-ai-marksInstalled? Explore more 写作与编辑 skills: steipete/notion, langchain-ai/langchain, bytedance/podcast-generation · View all 6 →
移除多厂商AI溯源标记：不可见Unicode（A层）、通过重写消除统计文本水印（B层，始终提供）以及对PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD/TEX格式文件中的C2PA/EXIF/XMP/容器元数据进行清理。适用于Claude、Gemini/SynthID类、OpenAI溯源及开源LLM采样标记。当用户要求去除水印、移除C2PA/内容凭证、清理AI元数据、去除不可见Unicode、反检测清理AI输出，或运行/remove-ai-marks（别名：/remove-claude-marks）时使用。
Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.
The agent engineering platform.
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
Analyze and optimize tweets for maximum reach using Twitter's open-source algorithm insights. Rewrite and edit user tweets to improve engagement and visibility based on how the recommendation system ranks content.
Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors