Skill Kuaishou Upload logo

Skill Kuaishou Upload

OrganizationPopular
ZJU-REAL
skill-kuaishou-upload

快手视频发布:把竖版短视频发布到快手创作者中心。当用户说"发快手""上传快手""快手投稿" "发布到快手""快手视频发布"时使用。基于通用浏览器发布框架(Playwright + 登录态持久化)。

Overview

PublisherZJU-REAL
RepositoryEasel
Skill nameskill-kuaishou-upload
Stars
3.5K
Forks
535
Bundled files
1
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ZJU-REAL on GitHub. Read the source before you install it.

Installation

Install the Skill Kuaishou Upload AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/skill-kuaishou-upload
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ZJU-REAL/Easel.git /tmp/Easel
mkdir -p .claude/skills
cp -r /tmp/Easel/skills/openclaw/skill-kuaishou-upload .claude/skills/skill-kuaishou-upload
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Kuaishou Upload in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Kuaishou Upload on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Kuaishou Upload is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

快手视频发布

基于通用浏览器发布框架 ../../shared/scripts/web_publisher.py(--platform kuaishou)。 网页自动化发布——需真实浏览器 + 已登录快手创作者中心。

⚠️ 环境依赖(同 skill-xhs-publisher 定位)

  • pip install playwright + playwright install chromium
  • 首次 login 扫码/登录快手创作者中心,登录态持久化到 ~/.easel-browser-profiles/KuaishouProfile 后复用
    • 远程/headless 环境用 login-qr --platform kuaishou(抠二维码成图轮询),或走 Web「账号」页扫码
  • 选择器时效:快手网页改版频繁,内置选择器为最佳努力,首次发布务必先 plan 预览 + --headed 目视校验,失效时更新 web_publisher.py 中 kuaishou 配置。

无浏览器环境可用 platforms / plan / check。

发布成功输出形如 ✅ 快手发布成功(读回核验:作品 <id>,<状态>;账号:<昵称>)—— 该判定来自平台作品列表对账(不是「点完就算」);未核实的档位会在输出里明确写出原因与「先别重发」提示。

执行

脚本:../../shared/scripts/web_publisher.py(各子命令 -h)。

bash
python <ROOT>/skills/shared/scripts/web_publisher.py check
python <ROOT>/skills/shared/scripts/web_publisher.py login   --platform kuaishou
python <ROOT>/skills/shared/scripts/web_publisher.py plan    --platform kuaishou \
  --media out.mp4 --title "标题" --tags "#恐怖故事 #都市怪谈 #灵异事件"
# 有头执行,便于首次核对选择器:
python <ROOT>/skills/shared/scripts/web_publisher.py publish --platform kuaishou \
  --media out.mp4 --title "标题" --tags "#话题1 #话题2 #话题3 #话题4" --exec --headed

登录态:确认「真能发」而不只是「已登录」

快手创作者中心的「外壳」登录态比发布/上传子系统的授权活得久——外壳显示已登录、昵称头像都在,却可能已经发不出去(上传 token 过期)。为此 whoami 已内置发布子系统鉴权探针(login_probe),真校验能否发布而不只看页面外壳,账号页据此自愈假阳性。

  • 仍出现「显示已登录、发布却失败」= 发布态过期:去 Web「账号」页重新扫码,或清空 ~/.easel-browser-profiles/KuaishouProfile 后重跑 login-qr。
  • 快手发布 token 偏短命,需要比别的平台更勤地重新扫码,属正常现象。

Profile 感知

  • 有 Profile:标题/话题贴合 style.md 与快手生态(生活化、接地气);竖版 9:16。
  • 无 Profile:按快手通用规范(竖版、话题#、口语化描述)。

规则(含 2026-08 真机校准)

  1. 快手以竖版 9:16 为主,横版素材先用 video-reframe 转竖版;发布走视频流程,只收视频。
  2. 话题标签最多 4 个:超过报「话题标签数量超过上限:4」,--tags 控制在 4 个以内。
  3. 发布前先 plan 预览、--headed 目视确认;确认无误再无头批量。
  4. 发布按钮靠 JS 派发点击(脚本已用 js_click):底部提交按钮 class 带哈希后缀(如 _button-primary_xxx)、每次改版都变,纯 CSS :has-text('发布') 在 headless 下命中不稳; 脚本改为定位「可见 + innerText=='发布' + class 含 button-primary」的元素派发点击。 注意别误点右上角下拉菜单里的「发布作品」(那不是提交按钮)。
  5. 成功判定 = 读回对账(权威):点击「发布」后的界面信号(URL 离开 publish/video)只作旁证—— 脚本随后回到作品管理页读本人作品列表对账(标题前缀 + 时间窗,发前快照排除旧作品), 输出 ✅ 快手发布成功(读回核验:作品 <id>…) 才算真成功。另外三档绝不冒报成功,也不许盲目重发: unverified(多轮未见新作品,可能索引延迟——先人工确认再决定)、 login_required(读回时登录态失效——重登后核对,先别重发)、 readback_error(读回通道失败——人工核对,先别重发)。 读回未核实 ≠ 没发出去;视频初始「审核中」,稍后过审公开。
  6. 选择器/流程失效不要硬跑——先看截图定位阶段,再更新配置或提示用户平台已改版。
  7. 登录态与 Cookie 属敏感信息,妥善保存、不外泄。

发布失败排错顺序

① 先看报错档位与读回证据(发布输出/outputs/_publish.log):unverified/login_required/readback_error 先到创作者中心人工核对是否已发出(先别重发)→ ② 看 outputs/_login/kuaishou-publish-fail.png 截图确认停在哪一步 → ③ whoami + 实际打开发布页看 input[type=file] 在不在(不在=没真正登录、 停在营销介绍页)→ ④ 截图核对标题/话题填写、有无标签超限提示 → ⑤ dump innerText=='发布' 的元素 确认 class 仍含 button-primary → ⑥ 确认 JS 点击后 URL 跳转离开 publish/video。据此更新 web_publisher.py 配置。

参考来源

网页发布思路同 social-auto-upload 的快手模块;本 SKILL 复用统一 Playwright 框架,配置驱动、 登录态持久化。选择器需按平台现状维护;2026-08-19 真机调试校准(登录态发布子系统探针、JS 派发 发布按钮、话题上限 4);2026-09 起成功判定升级为读回对账(作品列表比对,界面 URL 信号仅作旁证)。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Skill Kuaishou Upload AI skill do?

快手视频发布:把竖版短视频发布到快手创作者中心。当用户说"发快手""上传快手""快手投稿" "发布到快手""快手视频发布"时使用。基于通用浏览器发布框架(Playwright + 登录态持久化)。

Why use Skill Kuaishou Upload on TypingMind?

Because you install it once and use it with any model. Skill Kuaishou Upload is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Kuaishou Upload in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZJU-REAL/Easel/tree/main/skills/openclaw/skill-kuaishou-upload. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Skill Kuaishou Upload?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Kuaishou Upload?

As many as you like. As long as a model supports skills, you can use Skill Kuaishou Upload with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Kuaishou Upload AI skill free?

Yes. It is published on GitHub by ZJU-REAL under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇