Adapt one piece of content for multiple Chinese social platforms, checking text length, tags, media type, and aspect ratio. The skill prepares platform-specific versions and delegates actual posting to each platform’s publishing skill.
中文简介正在准备中。当前显示英语简介。
跨平台一键发布：一份内容适配并发布到多个平台（小红书/抖音/B站/公众号/快手/视频号/知乎）。按各平台格式约束（字数/比例/标签/内容类型）适配内容，再逐个委派对应平台发布 SKILL。当用户说"一键发布""同时发到多个平台""多平台发布""一稿多发""全平台发""发到抖音+小红书+B站" "分发到各平台"时使用。
适配由 LLM 做，路由与约束检查由 scripts/publish_dispatch.py。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
一稿多发：按各平台规范适配同一份内容，再逐平台委派发布 SKILL。走
scripts/publish_dispatch.py（约束检查 + 平台→publisher 路由 + 派发计划）。 内容适配由你（LLM）完成，实际发布委派各平台 publisher SKILL。
| 平台 | publisher SKILL |
|---|---|
| xiaohongshu | skill-xhs-publisher ✅ |
| douyin | skill-douyin-upload ✅ |
| wechat（公众号） | skill-wechat-publisher ✅ |
| bilibili | skill-bilibili-upload ✅ |
| kuaishou | skill-kuaishou-upload ✅ |
| weixin-channels（视频号） | skill-channels-upload ✅ |
| zhihu | skill-zhihu-publisher ✅ |
python <skill>/scripts/publish_dispatch.py platforms 看全部平台及约束。
内容清单 manifest（JSON）：
{
"content": {"title": "...", "body": "...", "tags": ["...", "..."], "media_type": "video"},
"platforms": ["xiaohongshu", "douyin", "bilibili"]
}
脚本路径：skills/builtin/skill-cross-platform-publish/scripts/publish_dispatch.py。
# 1) 生成派发计划（校验各平台越限 + 路由到 publisher）
python skills/builtin/skill-cross-platform-publish/scripts/publish_dispatch.py plan --manifest content.json
constraints_note 与 warnings 精简标题/正文、删减标签、调整话题格式。recommend_aspect 决定是否用 video-reframe 转比例（如竖版转横版发 B站）。python skills/shared/scripts/persona_gate.py check --score 85——
低于 80 分时告知分数、偏离点和修改建议，但不阻断发布；用户已明确要发布就继续执行。dispatch[i].publisher 对应的发布 SKILL 执行。python skills/shared/scripts/manifest.py record --topic 露营攻略 \
--layer publish --skill skill-cross-platform-publish --profile 户外达人 \
--upstream outputs/露营攻略/article.md --summary "已发 小红书/抖音/B站"
发布记录已由 publisher 脚本在
--exec成功时自动落「内容日历（_schedule.json）+ skill-publish-log」，无需手动补记（重复会双记）。仅当要补--persona-score/--persona-verdict等元数据时，再单独调 skill-publish-log 追加。
platforms.md 已开通的账号；各平台语气/话题贴合 style.md；
合规底线遵守 preferences.md。plan 检查越限，逐条消除 warnings 再发。一稿多发的关键不是"复制粘贴"而是"按平台重适配"。本 SKILL 用约束注册表把各平台的字数/比例/ 标签/类型规则固化，路由到对应 publisher，适配交给 LLM，发布交给平台 SKILL。
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Generate images from written descriptions, transform existing images with editing instructions, or create several variations. Choose image dimensions and quantity, then save the results using an OpenAI-compatible service or apimart with your own API key.
中文简介正在准备中。当前显示英语简介。
Generate background music for short videos, vlogs, and social posts from descriptions of mood, style, and instruments. Download MP3 audio, optionally include sung lyrics, and use shared scripts to trim tracks, adjust loudness, or add music to videos.
中文简介正在准备中。当前显示英语简介。
Create new videos from written scene descriptions or still images using external AI services. Set the aspect ratio and duration, animate a character image, and request generated audio when the selected model supports it.
中文简介正在准备中。当前显示英语简介。
Organize generated images, videos, and text in outputs/ by date, platform, and type. Add tags, search filenames and content, produce asset lists and reports, and preview archive moves before applying them to make past work easier to reuse.
中文简介正在准备中。当前显示英语简介。
Reduce background noise in audio recordings or video soundtracks with three processing levels. Keep the original file, create a cleaned version, and receive a report of the settings used and file details before and after processing.
中文简介正在准备中。当前显示英语简介。
Edit audio files by trimming sections, converting formats, matching loudness, or extracting sound from videos. You can also join recordings, add fades, and change playback speed while keeping the original pitch.
中文简介正在准备中。当前显示英语简介。