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 bozhouDev/video-skills-toolkit --skill hook-writinggit clone --depth 1 https://github.com/bozhouDev/video-skills-toolkitWrote 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/bozhoudev/video-skills-toolkit/hook-writing)<a href="https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/hook-writing"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/hook-writing/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/bozhoudev/video-skills-toolkit/hook-writing"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/hook-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00159 | $0.01671 |
| Opus 5 | $0.00079 | $0.00835 |
| Sonnet 5 | $0.00032 | $0.00334 |
| Haiku 4.5 | $0.00016 | $0.00167 |
Grade A, and why
hook-writing 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 10d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
钩子写作
钩子是读者看到的第一句话。读者愿意看完钩子之前,内容好坏都不重要。
三要素
- 粉丝画像:先明确谁在看。同一个钩子对不同人群吸引力完全不同。
- 承诺:给读者继续看的理由,例如学到方法、避开坑、看到反常识真相、获得情绪共鸣。
- 可信度:承诺要可信。优先使用数字、名字、时间线、具体场景、权威背书或亲身经历。
自检
- 钩子本身能被看完吗?够短、够抓人,不会中途被划走。
- 看完钩子后想看下一段吗?有悬念,或者承诺还没兑现。
- 钩子有没有具体信息?没有数字、对象、场景或冲突时,通常太虚。
- 钩子是不是万能开头?“最近发现”“今天聊聊”“分享一个”这类开头要谨慎。
常用类型(开放清单)
下面是常用调色板,按“靠什么把人留住”分组。不是封闭枚举——清单里没有的直接新命名,一个钩子常踩中多类就标“组合型”;新命名后固定下来复用,别同一种钩子起好几个名字。类型只管“怎么构造的”,“为什么抓人”交给情绪机制那栏。
靠信息本身
- 反差型:出人意料的事实或对比,颠覆认知。
- 数据冲击型:用一个惊人数字开场。
- 热点/时效型:“刚刚/最新”,蹭正在发生的事。
- 清单盘点型:“N 个你不知道的…”,用清单做承诺。
靠戳情绪
- 痛点共鸣型:“你是不是也…”,戳读者正在受的苦。
- 损失厌恶/威胁型:“还在用 X 你就亏了/落后了”,制造错过的恐惧。
- 身份认同型:“作为一个 X,你一定…”,圈定人群。
- 争议立场型:抛一个反主流的强观点,逼人站队。
靠制造悬念
- 好奇缺口/悬念型:卖关子,留着关键信息不给,逼人往下看。
- 问题型:直接抛出让人想知道答案的问题。
- 结果前置型:先甩出夸张成果,制造“怎么做到的”。
靠表达张力
- 金句型:用一句有分量的判断开场。
- 场景/故事型:把人拉进具体画面或一段经历。
- 类比型:“X 就像 Y”,把抽象讲具体。
靠直接给好处
- 教程承诺型:直说用什么方式教会什么,预告 1/2/3。适合干货、保姆级教程、短视频知识课。
- 利益/价值前置型:“读完你能…”,把好处提到最前。
钩子库
钩子库在 references/hook-library.md。当用户要求参考历史钩子、复用钩子模式、写多个开头时,先读取这个文件。
库里只收真正能复用的钩子,每项压到一行、便于扫读,不堆长拆解。每条记录保留:
- 原钩子 + 载体(出现在标题/首句/视频前几秒)
- 类型 & 情绪机制(它怎么带动情绪)
- 可复用公式(成分 + 各成分作用 + 顺序)
- 适用 / 不适用
- (可选)出处或数据、我的改写
拆解钩子
当用户给视频链接、视频逐字稿、文章、推文、短视频脚本或开头,并要求“拆解视频开头”“拆解逐字稿开头”“拆解钩子”“提取钩子”“收进钩子库”时,目标是拆出以后能直接参考复用的东西,只记关键信息,不堆砌。
- 定位钩子:找出真正承担留人作用的部分,通常是标题、第一句、前 3-5 句,或视频前 5-15 秒(口播和画面一起看)。同时记下它出现在哪个位置(载体),位置不同作用完全不同。
- 判类型:对照上面「常用类型」清单选最接近的;一个钩子常踩中多类就标“组合型”,清单里没有的直接新命名。
- 拆情绪机制(最关键):这个钩子在开头几秒里点起了什么情绪、击中谁、怎么带起来的——比如先勾焦虑再给安全感、用反差制造好奇缺口、用窥私欲让人想往下看。一句话说清“它怎么带动情绪”,这是它有效的内核,也是判断能不能复用的关键。
- 提公式:写成一套可复用的公式——拆出钩子由哪几个成分组成、每个成分干什么、按什么顺序排,写成“成分A(作用)+ 成分B(作用)+ …”。不要写成挖了空的完形填空(那只是换个名词、被原句的说法锁死);公式抓的是逻辑,换话题、换说法都套得上。
- 标适用:用这个钩子需要什么前提素材(如一个反直觉数据、一段真实经历),以及什么情况会翻车。
- 用户明确要求入库时,按
references/hook-library.md的格式追加,不要覆盖已有内容。
入库前先去重:已有相同结构或高度相似案例时,不新建重复条目。
输出方式
写钩子时,给用户 3-5 个候选,并标注类型。推荐 1 个最适合发布的版本,说明理由。必要时给一个更口语、更犀利、更克制的改写版本。
拆解钩子时,先输出拆解结果;如果已经入库,最后说明写入了哪条库记录。
What ships with it
1 file 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.
- 10d ago First seen · 88 lines · 159 tokens per session scan A 8cec153f564c
hook-writing is a skill published in the GitHub repository bozhouDev/video-skills-toolkit (139 stars, last pushed 1mo ago), licensed MIT. It adds 159 tokens to every session and 1,671 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
video-strategy-orchestrator
Decides WHEN to use Remotion, HyperFrames, AI video generation, or a hybrid of all three. Use when building video production pipelines, choosing a video tool for a task, or when the user asks 'which video tool should I use?'. Evaluates input type, complexity, determinism needs, and output format to pick the right…
video-hyperframes
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
remocn
Build Remotion videos with remocn — copy-paste animation components and timeline-driven UI primitives from a shadcn registry. Use when composing a video or scene in a Remotion project, adding a single animation, transition, background, or UI-block sim, or reaching for a video-ready UI primitive (button, dialog…
video-hyperframes
A web-based sequence of video frames designed for Hyperframes or Remotion, with each frame presenting one visual idea.
minimax-cli
Nested swiss-knife reference for the MiniMax mmx CLI and the canonical MiniMax CLI procedure shipped with the TUI: install mmx-cli, discover the correct TUI-managed MiniMax preset/key slot without leaking secrets, match mainland vs international regions, and route image/video/music/TTS generation or one-shot shell…
videoagent-audio-studio
Tired of juggling multiple audio APIs? This skill gives you one-command access to TTS, music generation, sound effects, and voice cloning. Use when you want to generate any audio without managing multiple API keys.