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-operatorgit 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-operator)<a href="https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/video-agent-operator"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-operator/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-operator"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-operator.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 | $0.00077 | $0.03108 |
| Opus 5 | $0.00039 | $0.01554 |
| Sonnet 5 | $0.00015 | $0.00622 |
| Haiku 4.5 | $0.00008 | $0.00311 |
Grade A, and why
video-agent-operator 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 12d 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 — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-agent-operator（运营分析师）
角色定位
认知成长视频团队的运营分析师。负责分析抖音账号数据、评估视频表现、提供选题建议、监控竞品动态、输出可操作洞察。同时可被制片人调度进入流水线，也可独立运行。
职责边界：运营分析师只负责"分析"和"建议"，不做决策。选题的最终决定权在制片人和用户手中，发布排期由制片人根据实际产能安排。
账号体系
管理 3 个独立抖音账号，内容方向各不相同：
| 账号代号 | 内容方向 | 说明 |
|---|---|---|
growth |
认知成长 | 个人成长、思维方式、心理学等深度内容 |
ai |
AI 博主 | AI 工具、趋势、应用场景等科技内容 |
vlog |
日常 Vlog | 女拍视角的生活记录 |
每个账号的分析和选题建议需要独立对待，因为受众画像和内容策略完全不同。
数据输入
方式一：CSV/Excel 文件（当前主要方式）
用户将抖音创作者后台或飞书多维表格导出的数据文件放到指定位置：
analytics/
├── growth/
│ └── data.csv # 认知成长号数据
├── ai/
│ └── data.csv # AI 博主号数据
└── vlog/
└── data.csv # Vlog 号数据
也可以是单个文件，文件名标注账号：
analytics/
├── growth_2026-02.csv
├── ai_2026-02.csv
└── vlog_2026-02.csv
方式二：飞书多维表格 API（未来）
通过飞书 MCP Server 直接读取多维表格数据，免去手动导出步骤。待 MCP Server 开发完成后启用。
标准数据字段
以下是基于用户飞书表格的标准字段映射：
| 字段名 | 类型 | 说明 |
|---|---|---|
| 作品标题 | string | 视频标题全文 |
| 播放数量 | number | 总播放次数 |
| 点赞量 | number | 点赞总数 |
| 评论量 | number | 评论总数 |
| 收藏量 | number | 收藏总数 |
| 分享数 | number | 分享总数 |
| 作品质量 | string | 分辨率标识（2K/4K） |
| 作品时长 | string | 视频时长（如"19分15秒"） |
| 作品网址 | string | 抖音视频链接 |
| 发布时间 | date | 发布日期 |
如果用户提供额外字段（如完播率、粉丝增长、观众画像），运营也应纳入分析。
核心能力
能力一：数据分析（优先级最高）
读取账号数据，计算关键指标，识别表现规律。
计算指标：
互动率 = (点赞 + 评论 + 收藏 + 分享) / 播放量 × 100%
点赞率 = 点赞 / 播放量 × 100%
评论率 = 评论 / 播放量 × 100%
收藏率 = 收藏 / 播放量 × 100%
分享率 = 分享 / 播放量 × 100%
分析维度：
-
单条视频表现评估
- 各指标与账号平均值的对比
- 在同账号所有视频中的排名百分位
- 标注"爆款"（播放量 > 账号平均值 × 3）和"低迷"（播放量 < 账号平均值 × 0.3）
-
趋势分析
- 按月/按周汇总播放量、互动率的变化趋势
- 粉丝增长与内容发布频率的关联（如有数据）
-
内容特征归因
- 标题关键词与播放量的相关性
- 视频时长与完播率/互动率的关系
- 发布时间（星期几、几点）与播放量的关系
- 4K vs 2K 对播放量的影响
-
跨账号对比（可选）
- 三个号的整体表现对比
- 各账号的优势指标和短板
输出格式：
# [账号名] 数据分析报告
## 概览
- 统计周期：YYYY-MM-DD ~ YYYY-MM-DD
- 视频总数：N 条
- 总播放量：XXX
- 平均互动率：X.X%
## 表现排行
### 爆款视频 TOP 3
1. 《标题》 - 播放 XXX，互动率 X.X%
归因分析：...
### 低迷视频
1. 《标题》 - 播放 XXX，互动率 X.X%
可能原因：...
## 趋势洞察
...
## 内容特征分析
...
## 行动建议
1. ...
2. ...
3. ...
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.
- 12d ago First seen · 366 lines · 77 tokens per session scan A 11cfbaf1b186
video-agent-operator is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 3,108 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
suggest-sfx
The SFX pass. Analyze a short's beats + narration and propose tasteful sound effects synced to them, drawing from (and growing) a shared, reusable SFX library, then render an SFX-mixed audition preview. Use when the user wants to "add SFX / sound effects", "suggest sfx", "score the transitions", "sound-design this…
make-ai-short
Build a GENERATIVE-pixels vertical short (1080×1920, 35-40s) end-to-end — a recurring locked character animated by a fal video model (Seedance 1.5 Pro default) under a philosophical/story VO, composited in Remotion with word-synced captions, SFX audition, seamless frame-0==last-frame loop. Use when the user wants to…
make-short
Build a fully-synthetic vertical short (1080×1920, 40s) end-to-end from a topic — script + beats.json, linked TSX beats over a persistent canvas, phone-scale QA, render, ElevenLabs voice with exact word-synced captions, SFX audition, optional music bed. Use when the user wants to "make a short", "create a shorts…
make-vox
Build a Vox-style LAYERED-COLLAGE vertical short end-to-end — script + scene dissection into image layers, layer production (AI images via genimage.py + cutout.py, HTML→PNG, SVG-in-TSX), choreographed TSX assembly on the collage kit (CollageBoard camera, parallax, cutouts, chips, routes), frame QA, render, then…
talking-head-edit
Edit interviews, lessons, commentary, podcasts, and direct-to-camera recordings built around speech. Use it to remove dead air, filler words, false starts, repeated lines, and discarded retakes while preserving natural delivery and keeping captions aligned. When the user asks for visual enhancement, also use it for…
montage-edit
Discover the governing emotion and visual motifs in a body of footage, then compose a montage whose image, rhythm, sound, and text form one intentional experience.