Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".
infinitetalk
infinitetalk is an open-source design skill for Claude Code and compatible agents, published by anbeime. Its author describes it as: “音频驱动的稀疏帧视频配音工具，支持音频驱动的 Video-to-Video 和 Image-to-Video 生成，实现精准的唇形、头部、身体姿态同步，支持无限时长视频生成”. The project has 5.5k stars on GitHub and does not declare a license, so check with the author before reuse. Add it to your setup with `git clone https://github.com/anbeime/skill ~/.claude/skills/infinitetalk`.
What infinitetalk does
- 本 Skill 用于：将音频（语音）转换为同步的说话人视频，支持从单张图片或现有视频生成音频驱动的说话视频 - 能力包含： - Image-to-Video：从单张图片生成音频驱动的说话视频 - Video-to-Video：对现有视频进行音频驱动的重配音 - 多维度同步：唇形、头部运动、身体姿态、面部表情与音频精准对齐 - 无限时长：支持无限制时长的视频生成 - 低显存适配：支持量化、模型卸载等显存优化方案 - 触发条件：当需要生成音频驱动的数字人视频、视频配音、虚拟主播内容时使用
Installation
Add infinitetalk to your agent with:
git clone https://github.com/anbeime/skill ~/.claude/skills/infinitetalkAlways review a skill's source before installing it. This command comes from the skill's public repository; the linked repo is the source of truth for exact setup steps.
What's inside
The SKILL.md for infinitetalk is organised into these sections:
- 任务目标
- 前置准备
- 操作步骤
- 模式一：Image-to-Video（图片生成视频）
- 模式二：Video-to-Video（视频重配音）
- 模式三：使用 TTS 生成音频
- 资源索引
- 注意事项
- 使用示例
When to use it
Reach for infinitetalk when you want design help from your agent without writing the same instructions every session. Load the skill and the agent picks it up automatically for relevant tasks.
Strengths
- Ships in anbeime/skill, an established project with 5,476 GitHub stars
- Actively maintained (recent commits)
Things to check
- No license declared — confirm terms with the author before reuse
Topics
Frequently asked questions
- What does infinitetalk do?
- 音频驱动的稀疏帧视频配音工具，支持音频驱动的 Video-to-Video 和 Image-to-Video 生成，实现精准的唇形、头部、身体姿态同步，支持无限时长视频生成
- How do I install infinitetalk?
- Run git clone https://github.com/anbeime/skill ~/.claude/skills/infinitetalk in your agent, then reload your skills. Review the source at https://github.com/anbeime/skill before installing.
- Is infinitetalk free to use?
- infinitetalk is publicly available on GitHub, but anbeime has not declared a standard open-source license (No license). Confirm the terms with the author before reusing it.
- Where does infinitetalk come from?
- infinitetalk ships inside anbeime/skill, a repository that contains 37 catalogued skills in total. The repository's 5,476 GitHub stars apply to that whole collection, not to this skill on its own.
Related skills
More Design →小省导购员多智能体数字人口播带货视频生成系统，以"小省导购员"为核心人设，打造专业购物助手+数字人口播带货视频一体化服务。涵盖五大智能体（小省导购员、带货脚本师、数字人口播生成师、带货画面设计师、音画合成师），产出"数字人口播+带货画面+字幕音效"的成品视频，适配抖音、快手等短视频平台，支持淘宝、京东、拼多多、唯品会等全平台商品信息，具备知识库自动存取能力。
小省导购员数字人带货版即梦视频提示词生成系统，基于四大智能体协同（提示词生成师、质量管控师、知识库运维师、跨环节适配师），按照"主体+运动+场景+（镜头语言+光影+氛围）"公式输出中英文双版提示词，适配5s短视频。确保人物一致性、视觉连贯性、情绪连贯性，支持知识库智能复用和跨工具适配（Suno音乐、AI绘画），为数字人带货视频提供高质量提示词生成服务。
电商视频营销创作技能，支持多品类商品的营销视频脚本生成，包含6阶段创作流程、智能体提示词框架、8种商品类型模板，适用于电商平台、社交媒体、品牌推广
自动化生成历史科学类3分钟科普短视频的全流程素材包，包含口播文案、分镜脚本、Veo2提示词、人物形象规范等，适配即梦平台视频生成。