Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/skill-douyin-uploadWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zju-real/easel/skill-douyin-upload)<a href="https://agentmods.dev/skills/zju-real/easel/skill-douyin-upload"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-douyin-upload/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zju-real/easel/skill-douyin-upload"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-douyin-upload.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.01673 |
| Opus 5 | $0.00055 | $0.00837 |
| Sonnet 5 | $0.00022 | $0.00335 |
| Haiku 4.5 | $0.00011 | $0.00167 |
Grade A, and why
skill-douyin-upload scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
抖音发布助手（douyin-upload）
在用户确认后，调用 douyin_publish.py 完成视频/图文发布。
运行方式（Playwright，headless 可用）
统一走 ../../shared/scripts/douyin_publish.py（CWD=项目根）。Playwright + 持久化登录态驱动
抖音创作者后台，headless 即可发布——替代了旧的 CDP/puppeteer/MCP Node 死栈（需真实 Chrome，
本环境跑不了，已删除）。
| 依赖 | 说明 |
|---|---|
| playwright + chromium | 本环境已装（douyin_publish.py check 验证） |
| 已扫码登录 | login 抠二维码成 PNG（默认 outputs/_login/douyin.png，Web「账号」页可扫）→ cookie 持久化到 ~/.easel-browser-profiles/DouyinProfile |
| 干净网络 IP | 抖音对机房/代理 IP 更易触发风控短信墙（登录与发布都可能弹）。短信墙可过——脚本支持验证码回填（见「短信验证码处理」），无需家宽 IP；仍建议尽量用干净 IP 降低触发频率 |
能力范围
- 现做：视频发布、图文发布、扫码登录、发布前预检（plan）。
- 话题：写进作品简介的
#话题（抖音自动联想成话题）。 - 视频发布含：上传等转码（≤5min）+ 选 AI 推荐封面。
风险提示
抖音自动化发布存在被平台风控/限流风险。默认提醒用测试号、小流量、人工复核。脚本已内置反检测
（--disable-blink-features=AutomationControlled + 逐字符输入 + zh-CN）；风险不可完全消除。
执行流程
check（环境就绪？）
→ 未登录 → login（抠二维码，Web 账号页扫 或 CLI 扫）
→ plan（dry-run 预检：标题长度/媒体路径/步骤）— 给用户确认最终标题、简介、媒体
→ 发布前人设检查（见下）
→ publish / publish-video --exec（首次建议 --headed 校验选择器，OK 后 headless 复跑）
→ 【若弹短信墙】问用户验证码 → 回填 → 脚本自动过墙（见「短信验证码处理」）
→ 成功校验（脚本内置：发布后 toast「发布成功」）
→ 发布后留痕（见下）
短信验证码处理（对话页发布必读）
抖音发布点「发布」后可能弹风控短信墙（提示『接收短信验证码』）。脚本已内置完整过墙能力（_handle_publish_sms：下发验证码 → 轮询码文件 → 填码提交，最多等 300s，可多次重输），但对话页里 agent 必须主动把验证码递进去——否则脚本会空等 300s 超时失败。
对话页正确姿势（后台跑 + 轮询状态 + 问用户 + 写码文件）：
- 后台启动发布（务必带
--status-file和--sms-code-file，路径用outputs/_login/下）：python skills/shared/scripts/douyin_publish.py publish-video --exec \ --title "标题" --content "简介" --video /abs/v.mp4 --tags "旅行,攻略" \ --status-file outputs/_login/douyin.publish.json \ --sms-code-file outputs/_login/douyin.code - 轮询
outputs/_login/douyin.publish.json（JSON，字段state：starting→可能sms_required→verifying→success/error）。 - 读到
state=="sms_required"：把该文件里的message（含发码手机尾号）转达用户，在对话里向用户要验证码。 - 拿到验证码后，把纯数字写进码文件（一次性消费，脚本读走即删）：
printf '%s' "123456" > outputs/_login/douyin.code - 继续轮询直到
success/error。码错会退回sms_required，可再要一次重写。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 106 lines · 110 tokens per session scan A 559a486f41e2
skill-douyin-upload is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 110 tokens to every session and 1,673 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
website-to-video
Capture a general website/URL and turn it into a HyperFrames video (site tour, showcase, or social clip from the site's own visuals). Uses headless Chrome screenshots + brand assets. Use when intent is general — portfolio/blog/landing-page showcase or social clip from the site. NOT for: product/SaaS launch or promo (→…
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol.