Media Publish Check

All-platform pre-publish audit and adaptation for creators publishing to 抖音/Douyin、小红书/Xiaohongshu、微信视频号/Weixin Video Accounts、快手/Kuaishou. Review videos, images, graphic posts, audio, articles, transcripts, subtitles, covers, livestream scripts, product claims, reposted material, and overseas content. Use when users need one Skill to check visible content, spoken claims, AI disclosure, sources, rights, commercial context, platform mentions, livestream commerce, or platform-specific release versions. Trigger on requests such as “能不能发”“发布前审核”“查违禁词/敏感词”“会不会限流”“检查口播/字幕/封面/导流/带货”“标注 AI/转载/演绎/广告/个人

71 stars 14 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add XshuiAi/media-publish-check --skill media-publish-check

Manual install

git clone --depth 1 https://github.com/XshuiAi/media-publish-check.git /tmp/media-publish-check
mkdir -p ~/.claude/skills
cp -r /tmp/media-publish-check/. ~/.claude/skills/media-publish-check

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Media Publish Check｜自媒体发布审核

审核用户已经完成或正在制作的内容，给出可执行的发布判断、精确问题位置和修改稿。把法律风险、平台规则、权利/事实待证、平台发布策略和分发优化分开；不把民间词表、单个词命中或所谓“限流经验”伪装成官方规则。

## 个人账号记忆与复盘（可选、本地）

仅在用户明确说“开启个人账号记忆 / 按我的经验库审核 / 保存这次审核 / 复盘这条内容 / 查看我的账号规则”时，读取 [personal-account-memory.md](references/personal-account-memory.md)。遵守：

- 资料默认只写入当前用户电脑的 `~/.codex/data/media-publish-check/`；不上传、不共享、不写入本 Skill 文件夹或公开仓库，也不读取其他账号目录。
- 未经用户明确要求，不创建档案、不保存内容、不追问反馈；普通审核流程保持不变。
- 首次开启时，只询问一个本地账号代号；用 `scripts/account_memory.py init` 创建空档案。不要索要姓名、手机号、账号密码、完整原片、订单或聊天记录。
- 用户说“保存这次”时，只记录平台、内容形式、风险标签、审核结论和用户同意保存的简短摘要；默认不保存原始视频、图片、全文、联系方式或未脱敏通知。
- 用户说“复盘这条”时，使用简短复盘卡记录：`已发布/未发布`、`正常/收到通知/驳回/未知`、以及可选的已脱敏通知摘要。不能把低播放当作违规反馈。
- 每次复盘后运行 `scripts/account_memory.py rebuild-candidates`。它只能生成“候选账号提醒”；只有用户明确说“启用候选规则”后，才可写入本地生效规则。
- “按我的经验库审核”时，先运行 `scripts/account_memory.py context`，最多带入 3 条与目标平台和风险标签匹配的已启用提醒。它们仅是账号经验，不得覆盖法律、平台官方规则、授权事实或当前证据。
- 独立 Skill 不能在用户离开后主动发消息或后台追踪发布结果。用户下次回来时，可在不打断当前审核的前提下，用一行询问未回收案例的结果；用户不反馈就保持 `未知`，绝不自行推断。

## 直接开始

- 用户可直接上传视频、图片、图文、音频、文章、字幕、口播稿、封面或链接；不要先发长问卷。
- 用户已指定平台时直接审核；未指定时只问：`准备发抖音、小红书、视频号还是快手？`，同时先做四平台共用安全检查。
- 只问会改变结论的信息；最多集中追问 4 项：原创/授权、AI 使用、商业关系、事实来源或专业资质。
- 跟随用户语言解释；中国平台发布稿使用自然中文。

## 1. 确认证据范围

先写清已检查和未检查的模态。读取 [media-inspection.md](references/media-inspection.md) 执行：

- 文本：标题、正文、标签、字幕、简介、评论话术；
- 视觉：封面、首尾帧、关键帧、花字、Logo、水印、二维码、人物、产品和隐私；
- 音频：口播、音乐、采样、AI 配音和可能的版权素材；
- 权利与来源：原创、转载、翻译、授权、拍摄时间地点和原始链接；
- 商业与制作：赞助、返佣、赠品、带货、AI、数字人、换脸、拟声和演绎。

只看到字幕或文案时必须写“文本层面初审”，不得声称完整作品可直接发布。无法访问链接或某个模态时说明缺口，请用户补原文、截图、逐字稿或文件，不能假装看过。

Read the full skill on GitHub

Details

Skill name: media-publish-check
Repository: XshuiAi/media-publish-check
License: MIT
Repo updated: 22 July 2026

FAQ

What does the Media Publish Check skill do?

How do I install the Media Publish Check skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add XshuiAi/media-publish-check --skill media-publish-check. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Media Publish Check popular?

It lives in XshuiAi/media-publish-check, which has 71 GitHub stars and 14 forks.

Related skills

Watch Video

Newuxtreme/watch-video-skill

SLASH-COMMAND-ONLY. Invoke ONLY when the user explicitly types the literal `/watch-video` slash command. Never auto-trigger on phrases like "watch this video," "summarize this video," "take notes on this video," or on a bare YouTube URL. For ad-hoc YouTube questions, fetch the transcript directly (YouTube page or yt-dlp) and skim — do not run this heavyweight pipeline.

Images, Video & Audio

Take One

talsiach/take-one

Turn a short request into a finished short film rendered from code, working like a studio team of twelve jobs (strategist, creative director, writer, voice director, art director, storyboard artist, cinematographer, composer, sound designer, editor, reviewer, social copywriter). For launch and product videos, explainers, music videos, brand and story films. It learns the brand from its site, pitches the best route first (code, real-looking pictures, moving shots from a video model) with prices, asks whether to run to a finished first take or work in stages, always asks before spending money, c

Images, Video & Audio15

Regional Culture Poster

dacnay816y62-hub/regional-culture-poster

Convert Chinese provinces, municipalities, autonomous regions, cities, counties, ancient cities, and cultural regions into restrained contemporary posters led by one culturally transformed Chinese character. Supports direct one-shot final image generation and layered production. Use when the user asks for a 中国省域文化海报、城市文化海报、地域文化视觉、极简大字海报、地区系列海报、展览主视觉、出版或社交封面，requests 直接生成、一次成图、不合成、不要后期、direct generation, or wants cultural analysis, art direction, image prompts, rendered poster images, or a coherent batch series for places such as 北京、广东、福建、江南、岭南、巴蜀 or 关中.

Images, Video & Audio13

Notebooklm Video Research

BayramAnnakov/notebooklm-youtube-skill

Automate NotebookLM notebook creation from YouTube videos. Given a YouTube video URL, extract information about people featured in the video, research them online, create a new NotebookLM notebook with the video and research as sources, and generate an audio overview. Uses screenshot-first automation to reliably target UI elements.

Images, Video & Audio

Video Storyboard Generator

OYYH-Apple/video-storyboard-generator

视频分镜脚本生成器，支持头脑风暴、用户偏好记忆、15秒镜头规则、角色提示词生成、音效/BGM建议。用于生成带运镜指导、画面设计、旁白、角色描述的完整分镜脚本。支持极简版（内容描述）和专业版（详细运镜）。适用：教程、书籍介绍、评论、剧情、产品介绍、数据报告。当用户说"做分镜"、"分镜脚本"、"视频分镜"时使用。

Images, Video & Audio

Whiteboard Book Video Skill

nutllwhy/whiteboard-book-video-skill

白板火柴人拆书短视频工作流。用于把一本书或一段长内容做成 60-90 秒竖屏(9:16)白板手绘信息图风格的拆书口播短视频，并用 HyperFrames 在本地渲染无平台水印的最终成片。覆盖：拆书脚本与分镜表生成、白板火柴人信息图分镜图生成、口播配音生成(可选男声/女声)、背景音乐生成(可选活泼/沉稳/其他风格)、每个阶段与用户确认、HyperFrames 动效渲染+字幕卡点+音乐混音装配、成片交付。当用户提到"拆书视频""拆解一本书""白板风/火柴人信息图短视频""口播短视频""书评视频""把这本书做成视频"等需求时使用。

Images, Video & Audio15

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.