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 chenyuxiaojin/video-agent-skills --skill video-agent-publishergit clone --depth 1 https://github.com/chenyuxiaojin/video-agent-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/chenyuxiaojin/video-agent-skills/video-agent-publisher)<a href="https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/video-agent-publisher"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-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/chenyuxiaojin/video-agent-skills/video-agent-publisher"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-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 | $0.00067 | $0.00841 |
| Opus 5.5 | $0.00027 | $0.00336 |
| Sonnet 5.5 | $0.00013 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
video-agent-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 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.
What it actually says
video-agent-publisher
认知成长视频团队的运营。生成各平台（抖音/B站/YouTube）的发布元数据，包括标题、描述、标签，以及引用出处列表。
触发条件
- 「准备发布素材」
- 「生成封面和标题」
- 「生成发布信息」
- 由制片人（producer）调度时自动触发
输入 → 输出
- 输入：
script.md+materials/sources.json - 输出：
publish/metadata.json+publish/sources.md
平台规则
- 抖音：标题 ≤ 30 字，描述 ≤ 300 字，标签 5-10 个
- B 站：标题 ≤ 40 字，描述 ≤ 250 字，标签 ≤ 12 个
- YouTube：标题 ≤ 100 字符，描述 ≤ 5000 字符，标签 ≤ 500 字符总长
- 所有平台标题都需要包含钩子元素
处理流程
步骤 1：读取输入文件
读取 script.md 和 sources.json，提取主题、论点、关键词。
步骤 2：生成发布元数据
python scripts/generate_metadata.py <script.md> <outline.md> [output_dir]
生成 metadata.json，包含：
- 多个标题候选（不同风格）
- 视频描述
- 标签/Hashtags
- BGM 推荐
步骤 3：整理引用出处
python scripts/compile_sources_list.py <script.md> [output.md]
从逐字稿中提取所有【出处：...】标注，生成格式化的引用列表。
标题生成策略
| 策略 | 模板 | 适用场景 |
|---|---|---|
| 疑问式 | 为什么 [主题] 如此重要？ | 引发好奇心 |
| 数字式 | 关于 [主题]，你必须知道的 N 件事 | 信息密度高 |
| 反常识 | 你以为的 [主题]，可能完全是错的 | 颠覆认知 |
| 故事式 | 从 [案例] 说起：重新理解 [主题] | 叙事型内容 |
BGM 推荐规则
| 内容类型 | 推荐风格 | 关键词 |
|---|---|---|
| 认知/科普 | 轻松思考 | calm, thinking, ambient |
| 故事/叙事 | 温暖叙事 | warm, narrative, gentle |
| 励志/成长 | 积极向上 | uplifting, inspiring, motivational |
| 反思/深度 | 沉静内省 | reflective, minimal, piano |
推荐来源：Pixabay Music（免费商用）
metadata.json 格式
{
"topic": "主题",
"titles": ["标题1", "标题2", "标题3", "标题4"],
"description": "视频描述",
"hashtags": ["#标签1", "#标签2"],
"keywords": ["关键词1", "关键词2"],
"recommended_bgm": [
{"name": "名称", "mood": "风格", "source": "pixabay"}
]
}
依赖
- Python 3：标准库（json, re, pathlib）
脚本文件
scripts/generate_metadata.py- 发布元数据生成scripts/compile_sources_list.py- 引用出处整理
What ships with it
2 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.
- 2mo ago First seen · 101 lines · 67 tokens per session scan A 26e06b140098
video-agent-publisher is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (14 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 841 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 2026-08-31.
video-agent-publisher compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| video-agent-publisherchenyuxiaojin/video-agent-skills | Skill | 14 | 5mo ago | MIT | A | 67 | Claude Code, Codex |
| talking-head-editpireel/pireel | Skill | 1.4k | yesterday | AGPL-3.0 | A | 79 | Claude Code, Codex |
| montage-editpireel/pireel | Skill | 1.4k | yesterday | AGPL-3.0 | A | 35 | Claude Code, Codex |
| audio-and-musicpireel/pireel | Skill | 1.4k | yesterday | AGPL-3.0 | A | 0 | Claude Code, Codex |
| suggest-sfxhassancs91/claude-faceless-shorts-creator | Skill | 305 | 2mo ago | MIT | A | 169 | Claude Code |
| make-ai-shorthassancs91/claude-faceless-shorts-creator | Skill | 305 | 2mo ago | MIT | A | 180 | Claude Code |
| make-shorthassancs91/claude-faceless-shorts-creator | Skill | 305 | 2mo ago | MIT | A | 183 | Claude Code |