promptschat
Gives Claude Code access to the prompts.chat library, letting you search, retrieve and improve AI prompt templates, and find and install Agent Skills from its registry.
Turns a rough topic into a confirmed brief, then writes platform-specific copy and short-video scripts for YouTube, Douyin, Xiaohongshu and WeChat. It also analyses post performance and saves each finished draft, with you approving direction, titles and final versions first.
Auto-invoked ships a router so the right skill fires automatically as you prompt. No remembering which skill to call.
Normal is the plain upstream plugin, installed as-is. You invoke its skills yourself.
Claude Code
The plugin> /plugin marketplace add yanhua1010/self-media-content-workflow> /plugin install self-media-suite@self-mediaAuto-invocation> /plugin marketplace add flowy-sh/flowy-core> /plugin install flowy-core> /plugin install flowy-self-media-suite
Codex
$ npx skills add yanhua1010/self-media-content-workflow -a codex
Cursor
$ npx skills add yanhua1010/self-media-content-workflow -a cursor
Gemini CLI
$ npx skills add yanhua1010/self-media-content-workflow -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add yanhua1010/self-media-content-workflow$ copilot plugin install self-media-suite@self-media
OpenCode
$ npx skills add yanhua1010/self-media-content-workflow -a opencode
Windsurf
$ npx skills add yanhua1010/self-media-content-workflow -a windsurf
简体中文 | English
一套通用、模块化的自媒体内容生产与经营 Agent Skills:从模糊需求到创作简报、账号策略、热点与竞品研究、平台原生文案、短视频方案、数字人与动画解说视频制片、YouTube 与抖音视频号小红书多平台视频发布、公众号排版发布、数据复盘和交付归档,覆盖内容生产的完整闭环。
数字人制片中,头像与声音素材由用户在了解所选服务商当前数据处理条款后,亲自在该平台上传、创建并选定。任务文件、注册表和仓库不保存原始头像或录音、其本机路径、临时链接及平台私有标识,只索引数字人生成片段、最终视频、字幕文件等交付物的路径。
graph TD
W["self-media-content-workflow<br/>总控:路由 · 状态 · 确认点"]
W --> B["content-brief<br/>创作简报"]
W --> S["content-strategy<br/>内容策略"]
W --> R["trend-radar<br/>热点与竞品"]
W --> C["platform-copywriting<br/>平台文案"]
W --> V["short-video<br/>短视频"]
W --> A["content-analytics<br/>数据复盘"]
W --> D["content-delivery<br/>交付归档"]
W --> P["wechat-publisher<br/>公众号发布"]
W --> U["video-publisher<br/>视频发布"]
| Skill | 职责 |
|---|---|
self-media-content-workflow | 请求路由、状态管理、确认点和端到端编排 |
self-media-content-brief | 澄清目标、受众、证据、角度和约束 |
self-media-content-strategy | 账号定位、内容配比、栏目、选题池和内容日历 |
self-media-trend-radar | 热点追踪、关键词研究、竞品拆解和原创选题 |
self-media-platform-copywriting | X、小红书、公众号、短视频平台和 YouTube 原生文案,含配图风格库 |
self-media-short-video | 钩子、口播、分镜、字幕、拍摄方案,可选数字人制片和动画解说制片,横竖屏多平台版本 |
self-media-content-analytics | 数据质量、基线比较、归因、决策和实验 |
self-media-content-delivery | 里程碑保存、版本、路径核验和完整发布包 |
self-media-wechat-publisher | 公众号排版、图片上传、草稿箱写入和小绿书图片消息 |
self-media-video-publisher | 视频逐平台发布包,经逐平台授权后上传 YouTube、抖音、视频号、小红书为私密、草稿或定时 |
视频发布可选用 SAU 适配器和无依赖的 publish.mjs 先预览逐平台上传计划。
Claude Code 用户(推荐,无需 Node.js)
在 Claude Code 中依次执行两条命令,一次装齐全部 10 个 Skill:
/plugin marketplace add yanhua1010/self-media-content-workflow
/plugin install self-media-suite@self-media
其他 Agent(Codex、Cursor 等)
使用官方 skills CLI(需要 Node.js):
# 安装全部 10 个 Skill 到当前项目
npx skills add yanhua1010/self-media-content-workflow
# 安装到用户全局目录
npx skills add yanhua1010/self-media-content-workflow -g
按需选装模块,或用 -a 指定目标 Agent:
npx skills add yanhua1010/self-media-content-workflow --skill self-media-content-workflow -a claude-code
从总控 Skill 开始,它会自动路由到需要的模块:
使用 $self-media-content-workflow,把这段产品失败经历做成小红书和公众号内容。
也可以直接调用单个模块:
使用 $self-media-content-strategy,为一个新账号建立选题池和一个月内容日历。
使用 $self-media-trend-radar,研究最近一个月 AI 编程内容的高频问题。
使用 $self-media-content-analytics,分析这 10 篇内容并找出下一轮唯一实验。
Skill 的具体引用语法以所用 Agent 为准。
需求澄清 → 方向确认* → 研究与证据 → 平台确认* → 发布预检
→ 平台原生初稿 → 标题确认* → 素材生成(真人/数字人) → 质量审校
→ 终稿确认* → 发布授权* → 草稿或发布包 → 数据复盘
* 为强制人工确认点。终稿确认不等于发布授权:Skill 默认只创建草稿或手动发布包,不直接群发。
素材生成前,工作流从配图风格库按内容类型和平台推荐 2 到 3 套风格供选择,账号已有稳定偏好时直接沿用。
完整安全策略见 SECURITY.md。
python3 scripts/validate.py
校验器检查 Skill frontmatter、目录一致性、核心文件行数、UI 元数据、相对链接和未处理的 TODO,无第三方依赖。CI 在每次提交时运行结构校验,并用官方 skills CLI 执行一次真实安装测试。
skills/ # 10 个可独立安装的 Skill
├── <skill>/SKILL.md # 核心流程(≤ 500 行)
├── <skill>/references/ # 平台细则与详细规范
└── <skill>/assets/ # 可复制的输出模板
scripts/validate.py # 仓库结构校验
.claude-plugin/ # Claude Code plugin 与 marketplace 清单
.github/workflows/ # 结构校验 + 安装测试
欢迎 Issue 和 Pull Request。提交前请阅读 CONTRIBUTING.md,并运行 python3 scripts/validate.py。版本记录见 CHANGELOG.md。
本项目是一套内容创作辅助 Skills,按「现状」提供,不附带任何明示或默示的担保。使用前请注意:
WECHAT_APP_ID、WECHAT_APP_SECRET 等敏感信息仅通过你本地的环境变量提供,请勿写入任何会被提交或分享的文件。Gives Claude Code access to the prompts.chat library, letting you search, retrieve and improve AI prompt templates, and find and install Agent Skills from its registry.
A Claude Code skill for generating editable PPTX presentations and slides from a workflow, with reusable brand, style, layout, and deck workspaces, native charts, speaker notes, and template filling.
Gives AI agents control over Word, Excel and PowerPoint files, with skills for building .docx reports, academic papers, Excel dashboards and Morph-style animated slides.
A skill that builds animation-rich HTML presentations from scratch or converts PowerPoint files to web slides. Useful for anyone turning a deck into a web presentation.
Turns a rough topic into a confirmed brief, then writes platform-specific copy and short-video scripts for YouTube, Douyin, Xiaohongshu and WeChat. It also analyses post performance and saves each finished draft, with you approving direction, titles and final versions first. Install it once and the right skill fires as you prompt, with no slash command to remember. It is listed on Flowy in the Content category. It includes self-media-content-analytics, self-media-content-brief, self-media-content-delivery. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it