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.
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。
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
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。
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
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.
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.
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.
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.
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.
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.