Hook Lab

Community

hongfamonvAI

hook-lab

Use when the user gives a TikTok/Instagram Reels/YouTube Shorts URL (or runs /analyze <url>) and wants to know why the video works — extracts metadata and transcript, then breaks down hook, script structure, style tags, viral factors, and rewrite angles for Chinese platforms.

Overview

Publisher	hongfamonvAI
Repository	`hook-lab`
Skill name	`hook-lab`
Stars	103
Forks	6
Bundled files	2
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by hongfamonvAI on GitHub. Read the source before you install it.

Installation

Install the Hook Lab AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/hongfamonvAI/hook-lab/tree/main
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/hongfamonvAI/hook-lab.git \
  .claude/skills/hook-lab

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hook Lab in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hook Lab on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hook Lab is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

/analyze — 短视频内容拆解

Input

$ARGUMENTS = 一个视频 URL（TikTok / Instagram Reels / YouTube Shorts）。

如果用户没有提供 URL，问他要。

Step 1: Extract

运行提取脚本：

bash
python3 ~/.claude/skills/hook-lab/scripts/analyze-video.py "$ARGUMENTS"

脚本返回 JSON，包含：

platform: tiktok / instagram / youtube
metadata: 标题、描述、作者、播放量、点赞、评论、时长等
transcript: 视频字幕/转写文本（可能为 null）

提取失败的回退策略

如果 metadata._error 存在，按以下顺序尝试回退：

回退 1 — WebFetch：用 WebFetch 工具访问视频 URL，prompt 设为：

"Extract all video metadata: title, description, author name, author handle, view count, like count, comment count, share count, duration, and any transcript/caption text visible on the page."

回退 2 — 用户提供信息：如果 WebFetch 也拿不到数据，请用户提供：

视频的文案/字幕文本（可以从视频里手动复制）
基本数据（播放量、点赞数等，截图也行）

拿到任何数据后继续分析，在输出开头注明数据来源和完整度。

Step 2: Analyze

基于提取到的数据，进行以下分析。用中文输出。

2.1 基础数据面板

用表格展示关键指标：平台、作者、时长、播放量、点赞、评论、转发。计算互动率 = (like + comment) / view。

2.2 Hook 分析（前 3 秒）

从 transcript 的前 1-3 句提取 hook 文案，分析：

Hook 类型: curiosity gap / shocking stat / bold claim / question / visual hook / pattern interrupt
Hook 强度判断: 为什么能让人停下来
可优化空间: 如果 hook 不够强，给出改写建议

如果没有 transcript，从 description 和 title 推断 hook 策略。

2.3 脚本结构拆解

将 transcript 按叙事结构分段：

段落	时间估算	内容	作用

典型结构：Hook → Problem/Context → Solution/Reveal → Proof/Example → CTA

分析脚本节奏：信息密度是否合理、转折点在哪、哪里容易流失观众。

2.4 风格与格式标签

给视频打标签（多选）：

呈现方式: talking head / voiceover / text-on-screen / skit / montage / screencast / interview
内容类型: educational / entertainment / storytelling / review / tutorial / hot-take / news
情绪基调: 紧迫 / 好奇 / 幽默 / 震惊 / 共鸣 / 权威

2.5 为什么这条视频能爆

综合分析 2-3 个核心原因。要具体，不要泛泛而谈。比如不要说「因为内容好」，要说「开头用了具体数字制造反差（$0 → $10K），3 秒内给出明确价值承诺」。

2.6 可借鉴的改写方向

给出 3 个具体的改写角度，每个包含：

角度: 一句话概述
Hook 示例: 写出改写后的 hook 文案
适合平台: TikTok / Instagram / 小红书 / 视频号

改写方向要考虑中文创作者的场景。

Step 3: Output

按上面 2.1-2.6 的顺序输出完整分析。格式用 markdown 表格和分段标题，清晰可读。

最后附一行：

数据来源：yt-dlp 提取 | 分析模型：Claude

Step 4: 记录到结果库

分析完成后，往 ~/.claude/skills/hook-lab/results/analyzed-videos.md 追加一条记录（直接 Append，不要覆盖已有内容），格式：

markdown
## [YYYY-MM-DD] 作者 — 标题/主题 (平台)

- URL: <原始链接>
- 数据: 播放 X / 赞 X / 评论 X / 转发 X
- Hook 类型: ...
- 为什么能爆: 一句话核心结论
- 可借鉴方向: 一句话核心结论

---

这个文件是跨视频对比的素材库——后续如果用户要"把分析过的几条放一起找规律"，直接读这个文件，不用重新跑提取。

Notes

如果没有 transcript，在输出开头注明「未能提取字幕，以下分析基于元数据和描述文本」，分析照做但标注信息置信度较低
不要编造数据，metadata 里没有的指标标注「N/A」
互动率计算如果缺少 view_count 就跳过
全程用中文输出，技术术语保留英文（hook、CTA、talking head 等）

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

results/analyzed-videos.md1 KB
scripts/analyze-video.py7 KB

Frequently asked questions

What does the Hook Lab AI skill do?

Why use Hook Lab on TypingMind?

Because you install it once and use it with any model. Hook Lab is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hook Lab in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hongfamonvAI/hook-lab/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hook Lab?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hook Lab?

As many as you like. As long as a model supports skills, you can use Hook Lab with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hook Lab AI skill free?

Yes. It is published on GitHub by hongfamonvAI under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Banner Design

nextlevelbuilder

OrganizationPopular

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner.…

Distributed Triage

Sub-triages issues in the oncall:distributed queue by assigning distributed module labels, routing to sub-oncalls, and marking triaged. Use when an issue has been routed to oncall:distributed and…

Hyperframes

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video…

Audio Jingle

Audio generation skill — jingles, beds, voiceover, and sound effects. Routes music requests to Suno V5 / Udio / Lyria, speech to MiniMax TTS / FishAudio / ElevenLabs V3, and SFX to ElevenLabs SFX or…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

/analyze — 短视频内容拆解

Input

Step 1: Extract

提取失败的回退策略

Step 2: Analyze

2.1 基础数据面板

2.2 Hook 分析（前 3 秒）

2.3 脚本结构拆解

2.4 风格与格式标签

2.5 为什么这条视频能爆

2.6 可借鉴的改写方向

Step 3: Output

Step 4: 记录到结果库

Notes

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now