What is video-agent-operator?

An operations analyst for TikTok video accounts that reviews performance data and suggests topics and competitor insights. It can read CSV or Excel files and is designed for three separate accounts.

Use it to analyse recent TikTok performance, identify patterns in better-performing videos, suggest future topics, and monitor competitors.

It helps replace guesswork with comparisons of views, likes, comments, shares, timing, duration, and other available video data.

video-agent-operator — Skill by chenyuxiaojin/video-agent-skills

Install

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.

Any agent

npx skills add chenyuxiaojin/video-agent-skills --skill video-agent-operator

Clone the repo

git clone --depth 1 https://github.com/chenyuxiaojin/video-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-operator/github.svg)](https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/video-agent-operator)

Your own site

<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.

Your own site · 80×15

<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>

Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,108 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.5	$0.00031	$0.01243
Sonnet 5.5	$0.00015	$0.00622
Haiku 4.5	$0.00008	$0.00311

Measured 2mo ago against content hash 11cfbaf1b186, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/analyze_competitors.py, scripts/analyze_performance.py, scripts/generate_topics.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

video-agent-operator/SKILL.md · 366 lines

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. ...

Read the full file on GitHub · 366 lines

Files

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.

Changes

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 · 366 lines · 77 tokens per session scan A 11cfbaf1b186

Subscribe to this mod's changes

video-agent-operator is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (14 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 3,108 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.

Analytics and metrics Claude Code Marketing and SEO agent-skills ai-video capcut content-automation davinci-resolve

video-agent-operator next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
video-agent-operatorchenyuxiaojin/video-agent-skills	Skill	14	5mo ago	MIT	A	77	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