Community비디오 & 애니메이션github.com

TeamWiseFlow/tiktok-post

Upload and publish a video (or image carousel) to TikTok using the browser.

지원 대상~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/TeamWiseFlow/wiseflow/tree/master/addons/officials/crew/selfmedia-operator/skills/tiktok-post

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

문서

TikTok 发布技能

Use this skill when:

  • The user wants to publish a video to TikTok (国际版)
  • You need to cross-post a short video generated by video-producer
  • You need to set caption, hashtags, and cover for a TikTok post

Prerequisites: Browser session must be logged in to tiktok.com.


通用约束

  • 文件上传前必须先复制到 /tmp/openclaw/uploads/(browser 工具沙箱限制)
  • browser upload 工具可能返回「超时错误」,但这不代表上传失败!上传后用 snapshot 检查页面状态(进度条、处理状态文字)
  • 不要通过检查 input.files.length 是否为 0 判定上传是否失败! input.files.length == 0 不代表上传失败。
  • 遇到 browser failed: timed out. Restart the OpenClaw gateway ... 错误时,不需要重启、不需要报错!等待 30 秒后在原页面继续操作即可。若仍无法操作,再等 30 秒;若还不行,尝试关闭浏览器后重开;只有关闭重开后仍报错才是真的出错,需停止并反馈用户。
  • Caption 输入使用 type + slowly: true,不要用 fill()

Cookie Warmup

Navigate to https://www.tiktok.com first. If it redirects to login, the session has expired — inform the user.


Workflow: Upload Video

1. Navigate to https://www.tiktok.com/creator-center/upload
   (fallback: https://www.tiktok.com/upload)
2. Wait for the upload page to load
3. Click "Select video" or drag-and-drop the video file into the upload zone
   - Supported: MP4, MOV, WebM
   - Recommended: 9:16 vertical, 1080×1920, under 500MB
   - Duration: 15s – 10 minutes
4. Wait for upload and processing to finish (progress bar reaches 100%)
5. Click into the caption area and type the caption:
   - Plain text + hashtags (use #tag format)
   - Max 2200 characters
   - Include 3–5 relevant hashtags for discoverability
6. Set cover image:
   - Click "Cover" and select a frame from the video
   - Or upload a custom cover image
7.  Click "Post" button
8. Wait for confirmation — TikTok shows "Your video has been posted" or similar
9. Copy and report the post URL

Workflow: Schedule Post (if available)

After step 6 above:
1. Toggle "Schedule" instead of posting immediately
2. Select date and time (timezone auto-detected from account settings)
3. Click "Schedule"

Caption Best Practices

  • Lead with a hook in the first line (shown in feed before "more" truncation)
  • Add hashtags at the end, not inline
  • Use a mix of broad tags (#ai #technology) and niche tags (#aitools #wiseflow)
  • Keep core message under 100 characters before hashtags

Error Handling

SituationAction
Login pageSession expired — inform user to re-login
Video rejected (policy violation)Report reason to user; do not retry automatically
Upload stuck at %Wait up to 3 minutes; refresh page if still stuck
Caption too longTrim hashtags first, then caption
Cover selection failsSkip cover customization and use auto-generated cover

Notes

  • TikTok's upload UI changes frequently — if a button/element is not found, look for equivalent UI based on intent
  • Always confirm post URL after completion
  • Do NOT post content that violates TikTok Community Guidelines

관련 스킬

heygen-com/three

Three.js and WebGL adapter patterns for HyperFrames. Use when creating deterministic Three.js scenes, WebGL canvas layers, AnimationMixer timelines, camera motion, shader-driven visuals, or canvas renders that respond to HyperFrames hf-seek events.

community

conardli/web-video-presentation

把一篇文章或口播稿,做成"看起来像视频"的点击驱动 16:9 网页演示,可选合成口播音频。流程:原始文章 → **一次产出**口播稿 + outline 开发计划 → 用户**一次对齐** 5 件事(稿子 / outline / 主题 / 素材 / 开发模式)→ 网页开发(逐章 / 顺序 / 并行)→ 可选音频合成(provider-agnostic:内置 MiniMax mmx-cli + OpenAI TTS,可换 ElevenLabs / edge-tts / Azure / 自带 TTS)。**outline 只规划节奏与信息密度,不规划动画** —— 动画由章节开发时按 PRINCIPLES + ANTI-AI 法则即时设计。每次点击推进口播稿的一个节拍,每一步独占整屏,进度条平时隐藏只在悬浮时出现。适用场景:用网页做视频(动态 PPT 但不像 PPT)、把口播稿 / 文章变成可交互的解说、为 B 站 / YouTube / 视频号录屏教程、做有电影感的产品 / talk demo。本 Skill 沉淀的是设计方法论 + 协作流程 —— 不绑定任何特定样式 / 字体 / 颜色 —— 因此能复用到任意主题与美学。

community

jiyangnan/lecturecast

One prompt → finished 5-minute course video for both Bilibili (16:9) and Xiaohongshu (9:16). An agent skill that handles script → TTS → animated visuals → subtitles → covers, end-to-end.

community

zc277584121/video-to-gif

Convert a video to multiple GIF variants with different quality/size tradeoffs. Generates a comparison set so the user can visually pick the best result.

community

delphinereverse794/remotion-transitions

Build custom scene transitions in Remotion using a plugin with animation math, timing patterns, and ready-to-use examples.

community

JarvixGaby/motion-guide

AI-agent skill for product-safe UI motion decisions.

community