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.
/plugin marketplace add chenyuxiaojin/xiaochen-skills/plugin install cyxj-video-doctorWrote 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/xiaochen-skills/cyxj-hook)<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.
<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>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 | $0.00179 | $0.03304 |
| Opus 5 | $0.00089 | $0.01652 |
| Sonnet 5 | $0.00036 | $0.00661 |
| Haiku 4.5 | $0.00018 | $0.00330 |
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.
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。
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.
- 7d ago Changed · -5 tokens per session c0c46977e313
- 11d ago First seen · 193 lines · 184 tokens per session scan A a11a70f7d5fa
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.
Other skills, from other repositories
import
Import a tasks.md into the coco tracker as an epic with dependencies, and create matching issues in the configured issue tracker.
document
Generate minimal documentation through parallel agents.
grill-me
Internal requirements-interview engine for the CCF commands plan and init. Invoked only by those commands through the Skill tool with a mode argument (plan / init); it interrogates the user one question at a time, exploring the code to self-answer first, and returns a summary of the decisions. Not a standalone…
prd-gen
A guide for turning a feature idea into a product requirements document (PRD), a structured plan that explains what to build and how success will be judged.
full-pm-cycle
A product-management workflow covering the path from market and user research through product strategy, requirements, prototype design, release planning, and post-launch review. It uses defined stages and checkpoints, and can produce HTML prototypes.
market-research
A research skill for understanding markets and users. It can study market trends, market size, competitors, and opportunities, or help design interviews, surveys, and user profiles.