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 yanhua1010/self-media-content-workflow --skill self-media-video-publishergit clone --depth 1 https://github.com/yanhua1010/self-media-content-workflowWrote 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/yanhua1010/self-media-content-workflow/self-media-video-publisher)<a href="https://agentmods.dev/skills/yanhua1010/self-media-content-workflow/self-media-video-publisher"><img src="https://agentmods.dev/badge/skills/yanhua1010/self-media-content-workflow/self-media-video-publisher/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/yanhua1010/self-media-content-workflow/self-media-video-publisher"><img src="https://agentmods.dev/badge/skills/yanhua1010/self-media-content-workflow/self-media-video-publisher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00140 | $0.01427 |
| Opus 5.5 | $0.00056 | $0.00571 |
| Sonnet 5.5 | $0.00028 | $0.00285 |
| Haiku 4.5 | $0.00014 | $0.00143 |
Grade A, and why
self-media-video-publisher 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 16d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频发布
目标
把确认过的视频成片和平台文案，准确、完整地送到用户选择的平台，并把结果记回任务卡。默认交付手动发布包；外部上传只在逐平台授权后进行，优先上传为私密或草稿，由用户自己点公开。
前置条件
- 终稿已确认：用户完整看过、听过成片。
- 各平台版本和发布字段已就绪，见
self-media-short-video的 video-platform-versions.md 和平台文案模块的各平台规范。 - 有配乐或素材署名要求时，署名文本已写进各平台描述。
缺少任一项时，报告缺口并停在 AWAITING_USER，不带着缺口上传。
发布方式分级
从低到高，每升一级都需要用户对该平台、该条视频单独授权：
| 级别 | 方式 | 谁点“发布” | 适用 |
|---|---|---|---|
| L0 手动发布包 | 交付文件、封面、字幕和逐字段文案，用户自己上传 | 用户 | 默认；任何平台 |
| L1 填表助手 | 浏览器扩展或已登录浏览器自动打开发布页并填好字段 | 用户检查后亲自点 | 想省去重复填表，又要逐个把关 |
| L2 私密上传或草稿 | 官方 API 或上传工具上传为私密、不公开或草稿 | 用户在后台检查后公开 | YouTube 官方 API；支持草稿的平台 |
| L3 定时发布 | 上传并设定公开时间 | 到点自动公开 | 只在用户明确给出平台、视频和时间后使用 |
“全部发了吧”这类笼统指令不等于 L3 授权。逐平台列出将要执行的动作（平台、文件、标题、公开范围、时间），用户确认后再执行。
适配器发现
先发现当前环境已有的能力，不要求用户为本 Skill 安装特定工具。常见选项和各自边界见 upload-adapters.md：
- YouTube：优先使用官方 YouTube Data API（用户本人完成 OAuth 授权），或已登录的 YouTube Studio。
- 抖音、视频号、小红书：通常没有面向个人创作者的公开上传 API。可选的有填表类浏览器扩展、基于浏览器自动化的开源上传工具，或用户手动上传。
- 已安装
sau时，可选 SAU 适配器：先用node scripts/publish.mjs --episode <期目录> --platforms douyin,weixin,xhs,youtube --dry-run预览，再逐平台确认。视频号传草稿、YouTube 传私密（L2）；抖音、小红书只有--mode schedule --at的 L3 定时发布，到点自动公开，脚本逐平台要求人工确认且--yes对它们无效。--sau指定可执行文件，--yes只用于已经逐平台授权的 L2 平台。 - 非官方自动化可能违反平台条款或触发风控，新账号尤其敏感。向用户说明风险，由用户选择。
没有可用适配器，或用户不想安装时，直接交付 L0 手动发布包。
发布流程
- 核对发布包：逐平台检查视频文件、画幅、时长、封面、字幕、标题、描述、话题、署名和 AI 标识字段，缺什么报什么。
- 列出执行计划：每个平台一行，写清发布级别、文件、标题和公开范围或时间。
- 取得逐平台授权：用户确认哪些平台、按哪一级执行。 使用 SAU 脚本时，每个平台都要单独确认；默认草稿路径不支持抖音和小红书，不能用即时上传代替草稿。
- 执行：一次处理一个平台。登录失效、验证码、短信验证、风控提示或界面异常时立即停止，交给用户接管，不重试绕过。
- 回读核对：上传后打开后台或草稿，核对标题、封面、描述前两行、字幕、公开范围和定时时间。
- 记录结果：把发布级别、执行时间、核对结果写回任务卡和发布矩阵。用户报告公开成功后，再记录公开链接。
安全边界
- 不一键群发，不在未授权的平台上执行任何写操作。
- 不自动点赞、评论、关注、私信，不刷量。
- Cookie、Token、OAuth 凭据和账号密码只由用户本人或上传工具保存在本机；不读取、不回显，不写入任务卡、日志、发布包或仓库。
- 不代用户输入密码或验证码；登录由用户本人完成。
- 不为躲避版权识别而改变速、加噪音或裁切画面。
- 平台要求 AI 生成或合成内容声明时，如实勾选。
输出
返回每个平台的：发布级别、使用的适配器、上传或填表结果、公开范围或定时时间、回读核对结果、需要用户在后台完成的动作。未执行的平台写明原因（未授权、无适配器、风控停止），并附上该平台的手动发布包路径。
What ships with it
5 files 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.
- 16d ago Changed · +2 lines 674539366edf
- 25d ago First seen · 66 lines · 140 tokens per session scan A 833d6756e423
self-media-video-publisher is a skill published in the GitHub repository yanhua1010/self-media-content-workflow (626 stars, last pushed 14d ago), licensed MIT. It adds 140 tokens to every session and 1,427 once invoked, about $0.0006 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 2026-10-03.
Other skills, from other repositories
instagram-post-builder
Interactively builds a complete, copy-paste-ready Instagram post package - three hook variants using distinct patterns, a caption body, one clear CTA, a 15-20 hashtag set across reach tiers, alt text, and a visual direction with shot list or slide breakdown - through a one-question-at-a-time interview, optionally…
linkedin-warmup
Guide LinkedIn account warmup with engagement plans, SSI-building strategy, comment-first content, and post-warmup assessment. Triggers on "linkedin warmup", "warm up linkedin", "new linkedin account", "linkedin account warmup plan", "linkedin engagement plan", "warmup content linkedin", "linkedin trust score", "first…
instagram-warmup
Guide Instagram account warmup with engagement plans, Stories strategy, Reel and carousel warmup content, and post-warmup assessment frameworks. Triggers on "instagram warmup", "warm up instagram account", "new instagram account", "instagram account warmup plan", "instagram engagement plan", "warmup content…
x-warmup
Guide X/Twitter account warmup and source-backed X content hardening with engagement plans, reply-first strategy, warmup thread content, and post-warmup assessment. Triggers on "x warmup", "twitter warmup", "warm up x account", "new x account", "x account warmup plan", "x engagement plan", "warmup content x", "harder…
youtube-warmup
Guide YouTube channel warmup with engagement plans, channel optimization, warmup Shorts content, SEO-first setup, and post-warmup assessment. Triggers on "youtube warmup", "warm up youtube channel", "new youtube channel", "youtube channel warmup plan", "youtube engagement plan", "warmup content youtube", "youtube…
ad-copy-creator
Create paid ad copy for Meta, Google, LinkedIn, TikTok, and X using direct-response frameworks, platform limits, variants, and test plans. Triggers on ad headlines, ad creative, paid social ads, Google ads, and ad variants.