Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zJay26/douyin-skills --skill douyin-publishgit clone --depth 1 https://github.com/zJay26/douyin-skillsWrote 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/zjay26/douyin-skills/douyin-publish)<a href="https://agentmods.dev/skills/zjay26/douyin-skills/douyin-publish"><img src="https://agentmods.dev/badge/skills/zjay26/douyin-skills/douyin-publish/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/zjay26/douyin-skills/douyin-publish"><img src="https://agentmods.dev/badge/skills/zjay26/douyin-skills/douyin-publish.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 | $0.00072 | $0.01265 |
| Opus 5.5 | $0.00029 | $0.00506 |
| Sonnet 5.5 | $0.00014 | $0.00253 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
douyin-publish 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 2mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
发布抖音图文或视频
只使用 python "{baseDir}/../../scripts/cli.py" <子命令> 完成抖音页面操作。可以使用普通图片、视频工具准备和肉眼检查素材,但不要换用其他发布实现。
共同强制流程
- 确认目标账号并运行
check-login。 - 检查全部素材、标题和文案,并确定本次发布类型是图文还是视频。
- 使用对应的填表命令,人工查看页面,再使用对应的只读校验命令。
- 用户没有预先明确授权发布时,展示最终内容并取得授权。
- 只有校验返回
success: true、state: ready后,才执行对应的click-publish* --confirm。 - 根据
published与status判断结果;点击后未确认时绝不自动重试。
不要把图文校验器用于视频页,也不要把视频校验器用于图文页。任何 wrong_page、验证码/风控、字段不一致、上传未完成或封面缺失都必须先解决。
图文发布
图片必须是存在的绝对路径,格式为 JPG、JPEG、PNG 或 WebP。标题、正文和至少一张图片都不能为空;正文先写入 UTF-8 文本文件。
python "{baseDir}/../../scripts/cli.py" fill-publish-image \
--title "作品标题" \
--desc-file "/absolute/path/desc.txt" \
--images "/absolute/path/01.jpg" "/absolute/path/02.jpg"
只有 success: true、status: filled 且页面中的标题/正文与请求值完全一致时才继续。然后选择音乐:
python "{baseDir}/../../scripts/cli.py" select-music --names "目标音乐1" "目标音乐2"
检查图片数量、裁切、标题、正文和音乐后运行:
python "{baseDir}/../../scripts/cli.py" validate-publish
用户明确要求热点时才加入 --require-topic。最终发布命令为:
python "{baseDir}/../../scripts/cli.py" click-publish --confirm
视频发布
- 视频必须是存在的绝对路径。支持 AVI、FLV、M4V、MKV、MOV、MP4、MPEG4、MPG、TS、WEBM、WMV。
- 标题和作品简介不能为空;作品简介先写入 UTF-8 文本文件。
- 推荐提供 JPG、JPEG、PNG 或 WebP 自定义封面。发布前必须看到至少一个已设置封面,不能把“AI 封面生成中”当成封面已完成。
- 页面常驻提示里可能出现“上传中”;只有远端视频预览或明确的“重新上传”控件,且没有真实进度条/“上传失败”,才算视频上传完成。
一次上传、填写并设置封面:
python "{baseDir}/../../scripts/cli.py" fill-publish-video \
--video "/absolute/path/video.mp4" \
--cover "/absolute/path/cover.jpg" \
--title "作品标题" \
--desc-file "/absolute/path/desc.txt"
如果没有在填表时传 --cover,命令可能返回 status: filled_needs_cover。准备好封面后,在当前视频发布页执行:
python "{baseDir}/../../scripts/cli.py" set-video-cover \
--cover "/absolute/path/cover.jpg"
人工检查视频预览、标题、作品简介、竖/横封面和可见性设置,再运行:
python "{baseDir}/../../scripts/cli.py" validate-publish-video
用户明确要求热点时才加入 --require-topic。任何 errors 都必须先解决。最终发布命令为:
python "{baseDir}/../../scripts/cli.py" click-publish-video --confirm
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.
- 2mo ago Changed · +3 lines 2cc74c6f9043
- 2mo ago First seen · 97 lines · 72 tokens per session scan A 2e0f8671fb0c
douyin-publish is a skill published in the GitHub repository zJay26/douyin-skills (60 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 1,265 once invoked, about $0.0003 per session on Opus 5.5. 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.
douyin-publish compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| douyin-publishzJay26/douyin-skills | Skill | 60 | yesterday | MIT | A | 72 | Claude Code, Codex |
| skillredf0x1/camofox-mcp | Skill | 124 | 12d ago | MIT | A | 38 | Claude Code, Codex |
| chrome-agentsderosiaux/chrome-agent | Skill | 96 | 26d ago | MIT | A | 44 | Claude Code, Codex |
| revergreekr4/rever-browser | Skill | 51 | yesterday | MIT | A | 82 | Claude Code, Codex |
| browser-bridgekoltyakov/browser-bridge | Skill | 29 | yesterday | MIT | A | 49 | Codex |
| scrape-structured-datasderosiaux/chrome-agent | Skill | 96 | 26d ago | MIT | A | 111 | Claude Code, Codex |
| fanqie-publisheramm10090/fanqie-publisher-skill | Skill | 24 | 12d ago | MIT | A | 59 | Claude Code, Codex |