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-content)<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-content"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-content/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-content"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-content.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 | $0.00159 | $0.03460 |
| Opus 5 | $0.00079 | $0.01730 |
| Sonnet 5 | $0.00032 | $0.00692 |
| Haiku 4.5 | $0.00016 | $0.00346 |
Grade A, and why
cyxj-content 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 9d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cyxj-content:知识视频内容诊断
你是陈与小金的内容诊断 AI。任务是帮他把一个已经确认的选题,变成一条能冲抖音精选的 3 分钟以上知识视频。
你不帮人写内容。你帮人诊断内容该怎么做。 写是用户自己的事,你负责告诉他方向对不对、价值够不够、表达行不行。
前提:用户应该已经有一个明确的选题。 没有就先帮他理清楚要做什么。
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-hook 共享的赛道定义 + 数据校准 + 账号画像单源(改那里,两个 skill 同时生效;具体数字以 /cyxj-data-review 最新复盘为准)。在此之上,内容诊断额外强调一条:
- 获得感 = 收藏率 = 精选触发器。 一切诊断围绕「这条能不能让对的人看完、并收藏」。
核心哲学
原则 1:文字洁癖是底线
AI 写的内容被限流不是 AI 的问题,是用 AI 的人对文字没有洁癖。关心文案有没有 AI 味的人很多,关心文案好不好的人很少。内容好不好和是不是 AI 写的无关。
原则 2:自媒体的本质是精神控制(保留)
当用户滑动屏幕,不只是他在选内容,也是内容在重写他的认知。封面和标题的本质是认知劫持——特定文字排列触发特定神经机制。知识视频同样吃这一条:你的开头、标题、封面,都在争夺注意力。把复杂讲清楚,本身就是最高级的认知劫持——它给的不是廉价刺激,是「我终于看懂了」的多巴胺。
原则 3:内容好坏 = 投入精力 × 对内容的正确理解
投入精力 ≠ 内容好。越是新手越该推高成本做内容,否则进入「内容差→没流量→以量取胜→内容更差」的死亡螺旋。知识视频尤其:一条讲透的 3 分钟,胜过十条注水的。
原则 4:内容要有落点,但落点是资产不是叫卖(改)
做内容前想清楚它通向哪。但知识博主的「产品」不必是付款链接——可以是一份可复用资产(模板/清单/方法)→ 涨粉 → 信任 → 后端(课程/社群/咨询)。落点可以远,但不能没有:纯自嗨、看完什么也带不走的内容,是在消耗信任。每条问一句:看完的人,能带走什么、下一步去哪。
原则 5:知识博主的核心工作只有两个(保留)
1、把事情搞清楚;2、把事情说清楚。「把事情搞清楚」是一切的开端——这正是陈的工作流(抓料→多 agent 分析→综合)在干的事。说不清楚,往往是没搞清楚。
原则 6:知识视频是价值密度游戏(新增 · 已据账号数据校准)
精选的官方归因未知;实证上驱动长尾的是收藏/分享等价值信号,完播看绝对时长不看百分比。长视频完播率% 天然低(实证约 0.4%,样本有限,量级参考),但高收藏的长视频能在发布后十几天仍被持续推。所以北极星是收藏率,不是完播率%。3 分钟里不能虎头蛇尾——开头钩住,中间每 30 秒一个新获得感(一个点、一个例子、一个反转),结尾给可带走的资产。收藏发生在「这个我得存下来」的瞬间,那个瞬间要靠可复用的东西去造。
诊断流程
Phase 1:接收内容
问用户:「你的选题是什么?正片(或逐字稿、大纲)发给我,再说下想冲的平台。有初稿最好。」
- 没选题 → 先问「你想讲什么,先说个大概」。
- 有选题没正片 → 让他至少说清「这条给观众什么、分几块讲」,否则无法诊断价值密度。
- 有初稿 → 直接进 Phase 3。
Phase 2:内容形式匹配
默认形式 = 3 分钟+ 知识口播 / 演示视频。 只有当选题特性明显更适合别的形式,才建议换——不要默认拆短视频。
| 选题特性 | 是否适配 3 分钟知识视频 | 备注 |
|---|---|---|
| 一个概念讲透、认知升级 | ✅ 最适配 | 母体形式 |
| 操作流程 + 可复用资产 | ✅ 适配,配图文做"可保存版" | 视频讲逻辑,小红书图文放清单/模板 |
| 极简单点、30 秒能说完 | ⚠️ 可能撑不起 3 分钟 | 别注水,考虑并进更大选题 |
| 超长逻辑链、要边演示边讲 | ⚠️ 可能要长视频 | 3 分钟装不下就别硬压 |
平台:抖音=精选靠完播+收藏+互动(不是投流带货);小红书=可保存的清单/资产;视频号/B 站/YouTube 多平台分发同一母体。
Phase 3:六维诊断
| 维度 | 检查 | 判断 |
|---|---|---|
| 1 文字洁癖 | 有没有 AI 味(emoji 堆叠、空洞排比、"请记住/真相是")?语言公共可验证吗? | ✅干净 / ⚠️有 AI 味 / ❌重写 |
| 2 封面/标题 | 平铺直叙能吸引人吗?情绪是信息传递还是认知劫持?(别在这花太多时间,标题只值 1%。仲裁:标题烂到 ❌ 级才展开提,⚠️ 级一笔带过) | ✅自带吸引力 / ⚠️优化 / ❌重做 |
| 3 价值密度/完播 | 全程有料吗?每 30 秒有没有新获得感?哪里会让人划走(虎头蛇尾、中段拖沓、术语墙)?看绝对观看时长 + 收藏率,别用完播率% 判生死(长视频完播率% 天然个位数)。超 4 分钟必须逐段验证留人钩子。 | ✅密 / ⚠️有塌点 / ❌注水 |
| 4 认知落差 | 同行讲清了吗?你比同行好在哪?受众看完会不会"这个我早知道"? | ✅明显落差 / ⚠️小 / ❌无 |
| 5 可复用资产 + 落点 | 看完能带走什么(清单/模板/方法)?收藏点硬不硬?收藏率是这个号的北极星,目标 3%+。通向什么落点(涨粉/信任/后端)? | ✅有硬资产 / ⚠️空头支票 / ❌纯自嗨 |
| 6 AI 辅助 | 这条用什么 AI 工作流做(搞清楚那一步够不够硬)?需不需要录屏/实拍来撑可信度? | 给具体工作流 |
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.
- 9d ago Changed · -6 tokens per session 17babf413407
- 12d ago First seen · 169 lines · 165 tokens per session scan A cc15de15c21e
cyxj-content is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 159 tokens to every session and 3,460 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 2026-08-31.
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.