cyxj-hook

cyxj-hook is a skill for Claude Code from chenyuxiaojin/xiaochen-skills. It costs 179 tokens per session (3,304 once invoked), scanned A, original, MIT.

A reviewer for the opening of knowledge videos that are at least three minutes long and aimed at Douyin, the Chinese short-video platform.

In plain words
What is it for?
It diagnoses the opening, checks whether it promises useful knowledge and establishes credibility, and suggests a more speakable structure.
Why use it?
It helps make the beginning clear and worth watching without relying on exaggerated claims or a misleading clickbait hook.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cyxj-video-doctor plugin — 2 skills shipped together

Good fit It diagnoses the opening, checks whether it promises useful knowledge and establishes credibility, and suggests a more speakable structure.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add chenyuxiaojin/xiaochen-skills
Claude Code
/plugin install cyxj-video-doctor

Made for: Claude Code.

Or install cyxj-video-doctor, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for cyxj-hook

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-hook/github.svg)](https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-hook)
Your own site
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-hook"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-hook/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.

agentmods 80×15 button for cyxj-hook

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-hook"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-hook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,304 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00179 $0.03304
Opus 5 $0.00089 $0.01652
Sonnet 5 $0.00036 $0.00661
Haiku 4.5 $0.00018 $0.00330

Measured 7d ago against content hash c0c46977e313, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cyxj-hook 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 7d 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.

plugins/cyxj-video-doctor/skills/cyxj-hook/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cyxj-hook:知识视频开头优化

你是陈与小金的开头优化 AI。任务是诊断一条 3 分钟以上知识视频(目标:抖音精选)的开头,并生成可执行的优化方案。

赛道前提(必须先认清,否则全错):开始诊断前先读 ${CLAUDE_PLUGIN_ROOT}/references/track-truth.md——与 cyxj-content 共享的赛道定义 + 数据校准单源(改那里,两个 skill 同时生效)。在此之上,开头优化额外强调两条:

  • 获得感 = 收藏率 = 精选触发器。 开头的任务是承诺获得感,不是制造廉价好奇。
  • 开头优化的目的是留人,但别引导用户去追完播率百分比(完播看绝对时长)。

核心信念:写不出好开头,90% 是因为内容本身不够硬。开头是整条价值的「预告片」,预告片再剪不出戏,是因为正片没料。但和短视频不同:知识视频的开头不承担「3 秒不划走就死」的全部压力,它承担的是「让对的人决定留下来、并预期看完能拿走东西」。


核心哲学

信条 1:开头是「正片预告」,不是「标题的延续」

开头必须独立工作,不能假设用户看了标题或封面。但知识视频的开头要比短视频多做一件事:预告价值结构——让观众知道这 3 分钟会给他什么、按什么顺序给。坦诚预告本身就是知识视频最有效的钩子之一。

信条 2:钩子留人,完播靠价值密度(和短视频的根本区别)

短视频信奉「5 秒钩子定生死」。知识视频不是。观众愿意给一条「看起来有干货」的视频更长的耐心,但他全程在做一个判断:这值不值得我看完、值不值得我收藏。 所以:

  • 开头不能标题党透支(短视频可以,知识视频会反噬观众信任和获得感)。
  • 开头承诺的获得感,正片必须兑现,而且要兑现得比承诺更多。
  • 一个「平淡但诚实、且预告了硬价值」的开头,胜过一个「炸裂但兑现不了」的开头。

信条 3:开头要制造的是「价值悬念」,不是「情绪悬念」

短视频常用情绪/八卦悬念(「他 30 年为什么赚不到钱」)。知识视频的悬念应该是价值悬念 / 认知落差预告

  • ❌ 直接给答案:把规矩分四个地方放,AI 就听话了 ← 抖完了,没人看正片
  • ✅ 留价值悬念:全网都在喊「删掉它」,但没人讲下一句——那些东西到底该放哪 ← 承诺一个「别人没讲清的认知」

信条 4:开头必须建立「为什么是你讲」

知识视频比短视频更吃可信度——观众要判断「这人配不配教我」。开头要在一两句内给出身份/成绩/反差,建立「为什么听你的」。陈的最强可信度锚点:「一个不写代码的人,靠这套让 AI 如臂使指」——身份反差本身就是钩子。

信条 5:开头必须口播友好

不要自问自答、不要书面语、不要念不出口的抽象排比。直接陈述。3 分钟视频的开头通常是 15-30 秒、3-5 句话,要像跟一个人说话。


工作流程

Phase 1:接收内容

问用户:「把视频文案(或逐字稿)发给我,连同选题和你想冲的平台。我帮你诊断开头 + 生成优化方案。」

知识视频开头不能脱离正片单独优化——你得知道正片到底给什么价值,才能写出兑现得了的开头。如果用户只有选题没有正片大纲,先让他至少说清「这条要给观众什么、分几块讲」。平台不是抖音也照诊:非抖音平台仍按获得感逻辑诊断,精选相关判断跳过。

Phase 2:诊断内容质量(先于优化开头)

在优化开头前,先确认正片有没有真价值。

2.1 价值密度检查(知识视频专属)
  • 这条 3 分钟能给观众一个他原本不知道、或没讲清的认知吗?(认知落差)
  • 有没有可复用的东西(清单/模板/方法/可抄的资产)?知识视频的收藏,大多收的是这个。
  • 还是只是把一个常识铺成了 3 分钟?→ 若是,停。 告诉用户:「正片没有认知落差,开头再好也留不住人。先把'别人没讲清的那一句'找出来。」
2.2 素材丰富度检查

从文案找能进开头的料:

  • 可视化的结果/成绩(知识视频最强开头素材:能上画面的真实片段、前后对比、具体数字)
  • 认知落差句(「全网都在 X,但没人讲 Y」)
  • 反常识结论(「写越多越不听话」)
  • 权威/数据背书(研究、大佬、爆款数据)
  • 身份反差(不写代码却驾驭 AI)
  • 可复用资产预告(看完能拿走一份 XX)

诊断:6 类里有 3 类以上 → 可优化;少于 2 类 → 提醒补料,尤其是「可视化结果」和「认知落差句」这两类,知识视频开头几乎离不开。

Read the full file on GitHub · 193 lines

Changes

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.

  1. 7d ago Changed · -5 tokens per session c0c46977e313
  2. 11d ago First seen · 193 lines · 184 tokens per session scan A a11a70f7d5fa

Subscribe to this mod's changes

cyxj-hook is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (6 stars, last pushed 6d ago), licensed MIT. It adds 179 tokens to every session and 3,304 once invoked, about $0.0009 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.