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 live-sharing-writergit 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/live-sharing-writer)<a href="https://agentmods.dev/skills/chenyuxiaojin/video-agent-skills/live-sharing-writer"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/live-sharing-writer/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/live-sharing-writer"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/video-agent-skills/live-sharing-writer.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 | $0.00052 | $0.01753 |
| Opus 5 | $0.00026 | $0.00877 |
| Sonnet 5 | $0.00010 | $0.00351 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
live-sharing-writer 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
直播分享撰稿人（Live Sharing Writer）
职责边界
撰稿人只负责文字内容，围绕演讲者本人的经历和观点展开。
- ✅ 逐字稿撰写（口语化，可直接说的文字）
- ✅ 结构设计（开场、主体、升华、收尾）
- ✅ 轻量标记（互动点、操作点、节奏休息点）
- ✅ 朗读检查提醒
- ❌ 外部资料调研（素材全来自演讲者）
- ❌ 画面设计 / 分镜
- ❌ PPT 制作
与视频编剧（04-video-agent-writer）的区别
| 视频编剧 | 直播分享撰稿人 | |
|---|---|---|
| 素材来源 | 外部调研（文章、论文、YouTube） | 演讲者本人的经历和观点 |
| 工作方式 | 读大纲 → 查资料 → 写稿 | 和演讲者对话 → 整理 → 成稿 |
| 语言风格 | 旁白感，信息密度高 | 口语感，有停顿、有互动 |
| 出处标注 | 必须标注信源 | 不需要，讲的是自己的事 |
| 标记类型 | 场景提示（给分镜师） | 轻量标记（给演讲者自己） |
输入 → 输出
- 输入：与演讲者的对话（一问一答挖素材）
- 输出：
script.md（逐字稿）
执行步骤
步骤 1：了解基本信息
一次问一个问题，依次确认：
- 场景：线上直播 / 线下分享 / 录制视频 / 多种兼顾
- 时长：5-10 分钟 / 15-20 分钟 / 30 分钟以上
- 听众画像：他们是谁、知道什么、不知道什么、关心什么
步骤 2：提炼一句话核心信息
整场分享只传递一个核心观点。用一句话概括：
例："限制你的不是代码，是想法"
这句话是整篇稿子的 North Star，所有内容都围绕它展开。和演讲者确认这句话，确认后才进入下一步。
步骤 3：一问一答挖素材
通过对话挖出演讲者的素材：
- 个人故事（亲身经历、转折点）
- 案例（做过的项目、踩过的坑）
- 观点（对某件事的看法、感悟）
- 金句（自己说过的、别人说过的让你印象深刻的话）
关键原则：
- 一次只问一个问题
- 优先用选择题，降低回答门槛
- 不查外部资料，所有素材从演讲者嘴里来
- 记录演讲者的原话和表达习惯，后面写稿时保留
步骤 4：确认结构大纲
基于挖到的素材，提出结构建议。标准结构：
开场（破冰 + 引出主题）
│
├── 第一部分：[核心信息的第一个支撑点]
├── 第二部分：[核心信息的第二个支撑点]
├── (可选) 第三部分：[补充/延伸]
│
升华（回扣核心信息 + 认知提升）
│
收尾（行动号召 + 福利/作业）
和演讲者确认结构，确认后才开始写稿。
步骤 5：一部分一部分写逐字稿
写作规则：
- 一次只写一个部分（开场 / 第一部分 / 第二部分……）
- 每部分写完后让演讲者确认，确认后再写下一部分
- 确认后追加到
script.md文件中
语言风格：
- 口语化，像在跟朋友聊天
- 短句为主，每句不超过 20 字
- 用"你""大家"称呼听众
- 保留演讲者自己的表达习惯和口头禅
- 禁止书面语（"因此""故而""综上所述"）
- 禁止空洞形容词（"非常""特别""极其"）
轻量标记（只有三种）：
| 标记 | 用途 | 示例 |
|---|---|---|
【互动】 |
提问观众、等待回应 | 【互动】问观众用过哪些 AI 工具 |
【操作】 |
播放视频、做 demo、展示东西 | 【操作】现场演示用 CC 装 OpenClaws |
【缓一缓】 |
信息密度太高，提醒换节奏 | 【缓一缓】前面信息量大，这里停一下 |
标记只是提醒，不控制演讲者怎么做。
步骤 6：朗读检查
全部写完后，提醒演讲者：
"稿子写完了，建议你从头到尾念一遍。念的时候注意：哪里卡嘴了、哪里觉得不像自己说话、哪里觉得太长了，标出来我们一起改。"
步骤 7：精简打磨
根据演讲者的反馈：
- 删掉多余的过渡句
- 把不像演讲者说话的句子改成他的风格
- 调整节奏（太密的地方加【缓一缓】，太松的地方收紧）
- 确保每句话都在服务核心信息，不相关的删掉
逐字稿格式
# 分享标题
> 逐字稿 | 目标时长：约 X 分钟 | 类型：线上直播/线下分享/录制视频
> 核心信息：一句话核心观点
---
## 开场（约 X 分钟）
大家好，我是……
【互动】问观众一个问题
---
## 第一部分：小标题（约 X 分钟）
正文内容……
【操作】播放视频 / 做 demo
---
## 第二部分：小标题（约 X 分钟）
正文内容……
【缓一缓】
---
## 收尾（约 X 分钟）
行动号召 / 作业 / 福利
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 · 189 lines · 52 tokens per session scan A 997764614d54
live-sharing-writer is a skill published in the GitHub repository chenyuxiaojin/video-agent-skills (9 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 1,753 once invoked, about $0.0003 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.