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 agentmods add skills/bytedance/agentkit-samples/hook-analyzer-skillnpx skills add bytedance/agentkit-samples --skill hook-analyzer-skillgit clone --depth 1 https://github.com/bytedance/agentkit-samplesWrote 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/bytedance/agentkit-samples/hook-analyzer-skill)<a href="https://agentmods.dev/skills/bytedance/agentkit-samples/hook-analyzer-skill"><img src="https://agentmods.dev/badge/skills/bytedance/agentkit-samples/hook-analyzer-skill.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.01148 |
| Opus 5 | $0.00046 | $0.00574 |
| Sonnet 5 | $0.00019 | $0.00230 |
| Haiku 4.5 | $0.00009 | $0.00115 |
Grade A, and why
hook-analyzer 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 3d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频前三秒钩子分析 (Hook Analyzer)
概述
视频前三秒钩子分析技能从分镜拆解结果中提取前三秒的分镜数据，并构造结构化的分析上下文，包含视觉内容描述、关键帧图片 URL、运镜方式等信息，为后续的 LLM 多维度评分分析提供输入。
适用场景
- 短视频优化：评估视频开头的吸引力，提升 3 秒留存率
- 创意评审：从5个维度量化分析钩子质量
- 竞品对标：对比不同视频开头的钩子策略
分析维度
本技能提取的数据供以下 5 个维度评分（由 LLM 完成评分）：
| 维度 | 权重 | 评估要点 |
|---|---|---|
| 视觉冲击力 | 30% | 画面构图、色彩、光影、运镜动感 |
| 语言钩子 | 25% | 文案与画面配合度、悬念制造 |
| 情绪唤起 | 15% | 画面情绪、人物表情、氛围营造 |
| 信息密度 | 15% | 有效信息量、核心价值传达 |
| 节奏掌控 | 15% | 分镜切换节奏、平台特性适配 |
使用步骤
方式一：从文件读取分镜数据
# 1. 先使用 video-breakdown skill 处理视频并获取分镜结果
python ../video-breakdown-skill/scripts/process_video.py "https://example.com/video.mp4" > breakdown.json
# 2. 提取前三秒分镜数据
python scripts/analyze_hook_segments.py breakdown.json
方式二：通过 stdin 管道传入
cat breakdown.json | python scripts/analyze_hook_segments.py -
输出格式
{
"segment_count": 3,
"total_duration": 2.8,
"total_video_segments": 15,
"analysis_mode": "multimodal",
"segments": [
{
"index": 0,
"start_time": 0.0,
"end_time": 1.0,
"duration": 1.0,
"visual_content": "画面描述",
"speech_text": "语音文字",
"shot_type": "特写",
"camera_movement": "推镜头",
"function_tag": "开场",
"frame_images": [
{"type": "image_url", "image_url": {"url": "https://..."}}
],
"frame_count": 3
}
]
}
钩子类型分类
分析结果可用于识别以下钩子类型：
- 痛点型：直击用户痛点，引发共鸣
- 好奇型：设置悬念，引发好奇
- 冲突型：制造对比或冲突吸引注意
- 价值型：直接展示价值承诺
- 情感型：以情感共鸣打动用户
- 视觉冲击型：通过强烈视觉效果吸引
- 悬念型：留下悬念引导继续观看
评分标准
| 分数段 | 等级 | 描述 |
|---|---|---|
| 9-10 | 顶级 | 极强的吸引力和创意 |
| 7-8 | 优秀 | 具备良好的吸引力 |
| 5-6 | 一般 | 有改进空间 |
| 3-4 | 较弱 | 需要重大改进 |
| 1-2 | 很差 | 基本没有吸引力 |
注意事项
- 此脚本只做数据提取，不做 LLM 评分（评分由 Agent 的 LLM 完成）
- 提取的
frame_images字段中包含关键帧 URL，可供 Vision 模型直接分析 - 每个分镜最多取前 3 帧关键帧，避免 token 超限
- 输入必须是
process_video返回的完整 JSON 数据
故障排除
| 问题 | 解决方案 |
|---|---|
| 输出为空 segments | 确认输入 JSON 包含 segments 字段且不为空 |
| 前三秒无分镜 | 视频可能从静止画面开始，检查原始数据 |
| 关键帧 URL 失效 | TOS 签名 URL 可能已过期，重新拆解获取 |
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.
- 3d ago First seen · 112 lines · 93 tokens per session scan A 1ec714cc0650
hook-analyzer is a skill published in the GitHub repository bytedance/agentkit-samples (445 stars, last pushed today), licensed Apache-2.0. It adds 93 tokens to every session and 1,148 once invoked, about $0.0005 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
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
browser_cdp
通过 Chrome DevTools Protocol (CDP) 连接已运行的浏览器，或扫描本机 CDP 端口，用于远程调试与多工具共享浏览器实例。.
meeting-summarizer
Summarize a completed meeting from its transcript. Produces a structured summary with key decisions, action items, and discussion highlights. Triggered automatically when a meeting ends.