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-researchergit 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-researcher)<a href="https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/video-agent-researcher"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-researcher/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-researcher"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/video-agent-researcher.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 | $0.00130 | $0.02040 |
| Opus 5 | $0.00065 | $0.01020 |
| Sonnet 5 | $0.00026 | $0.00408 |
| Haiku 4.5 | $0.00013 | $0.00204 |
Grade A, and why
video-agent-researcher scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Python 3**：标准库（urllib, json, re, subprocess） How it starts
The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
video-agent-researcher
视频团队的通用调研员。两种工作模式：搜索模式（围绕主题搜集网页文章和 YouTube 字幕，提取核心论点，生成结构化大纲）和整理模式（用户已有完整素材时，按视频叙事逻辑重组素材，产出详细整理稿）。
触发条件
- 「搜索关于 [主题] 的素材」
- 「收集 [主题] 的资料」
- 「帮我找一些关于 [主题] 的文章和视频」
- 「整理素材生成大纲」
- 「整理这篇文章」
- 「把这个素材变成大纲」
- 「用这篇文章出视频」
- 由制片人（producer）调度时自动触发
输入 → 输出
- 输入：主题关键词（由制片人传入）+ 已有素材文件（可选）
- 输出：
- 搜索模式：
materials/sources.json+materials/articles/+materials/transcripts/+outline.md（标准大纲，~500 字论点摘要） - 整理模式：
outline.md（详细整理稿，≥ 原始素材 60% 字数，含原文引用 + 金句索引 + 编剧指引）
- 搜索模式：
工作流程
- 接收主题关键词
- 搜集素材（优先使用 WebSearch/WebFetch 工具，脚本作为离线备选）
- 用英文关键词搜索 5-8 篇高质量文章（英文源优先，中文源补充）
- 用 WebFetch 抓取关键文章的详细内容
- （可选）YouTube 字幕：如需参考同类视频的讲述方式，搜集 1-3 个相关视频字幕
- 汇总素材，生成
sources.json索引 - 分析所有素材，提取核心论点和案例
- 数据验证：搜索各关键实体（模型、公司、产品）的官方发布页，确认版本号、发布日期、基准数据为最新
- 生成结构化大纲，须包含：主题类型（cognitive / tech-sci / review 等）、主题定位、目标观众、3-5 个核心论点、每个论点的支撑案例、开头模式建议
- 返回
outline.md给制片人
整理模式（用户已有素材时）
触发条件
当用户已经提供了完整素材（文章、文档、笔记等），不需要搜索，需要按视频叙事逻辑整理。制片人会通过 has_source_material: true 标记。
工作流程
- 通读全部素材，理解核心主题和论点
- 按视频叙事逻辑重组（非原文顺序）——思考"观众应该先知道什么、再知道什么"
- 产出详细整理稿
outline.md，包含以下部分：
整理稿产出物要求
| 组成部分 | 要求 |
|---|---|
| 叙事结构 | 按视频逻辑重组，标注每部分的叙事目的（引入/论证/转折/升华） |
| 原文精彩引用 | 保留原文中有力量的表达，用引用块标注，不要过度改写 |
| 金句索引表 | 提取 5-10 句最适合口播的金句，标注出处和建议使用位置 |
| 编剧工作指引 | 每个段落末尾用 > 编剧指引： 说明这段的写作方向、情绪基调、建议时长 |
| 字数要求 | ≥ 原始素材 60%，宁多勿少——编剧做减法比加法容易 |
整理稿模板
# [主题]
> 主题类型：cognitive / tech-sci / review 等
> 原始素材字数：X 字
> 整理稿字数：Y 字（原文 Z%）
> 建议视频时长：N 分钟
## 金句索引
| # | 金句 | 出处 | 建议位置 |
|---|------|------|----------|
| 1 | "..." | 原文第 X 段 | 开头钩子 |
| 2 | "..." | 原文第 Y 段 | 案例一结尾 |
## 第一部分：[小标题]（叙事目的：引入）
[重组后的内容，保留原文引用]
> 编剧指引：这段用来建立问题意识，语气轻松，建议 1-2 分钟
## 第二部分：[小标题]（叙事目的：核心论证）
[重组后的内容]
> 原文引用："原文中的精彩表达"
> 编剧指引：这是全片重心，需要展开讲透，建议 3-4 分钟
质量标准
- 不要"摘要化"——保留素材的丰富度和细节
- 编剧拿到整理稿后，工作是"语言转换"（书面→口播），不是"从零创作"
- 如果原文有好的表达，直接保留，不要过度改写
素材搜集详细步骤
方式一：WebSearch/WebFetch（推荐，Claude Code 环境）
- 用 WebSearch 搜索 3-4 组关键词（英文优先），每组获取 10 条结果
- 从结果中筛选 5-8 篇高质量文章（优先选择：权威媒体、研究机构、行业分析）
- 用 WebFetch 抓取关键文章的详细内容
- 将抓取结果整理为
materials/research-report.md
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 · 194 lines · 130 tokens per session scan A 85fbaed26e13
video-agent-researcher is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 130 tokens to every session and 2,040 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.